{
  "aboutHtml": "<p>GPT-4o Transcribe Diarize je model OpenAI za samodejno prepoznavanje govora z vgrajeno diarizacijo govorcev. Prepisane zvočne segmente poveže z različnimi govorci v pogovoru. Uporaben rezultat je prepis, urejen po govorcih in času, namesto zgolj neprekinjenega bloka besed. Namenjen je posnetemu govoru, ki potrebuje oznake govorcev, na primer sestanku, intervjuju ali razpravi več oseb.</p><h4>Pripravite dokončani posnetek</h4><p>Predložite posnetek za prepis. Dokumentirani datotečni potek sprejema MP3, MP4, MPEG, MPGA, M4A, WAV in WebM z omejitvijo velikosti datoteke 25 MB. Izvorni posnetek ohranite dostopen, da je mogoče posamezni govorčev prispevek, ime ali nejasno frazo preveriti glede na dejanski zvok.</p><p>Pri sestanku ohranite zaporedje pogovora, namesto da izrežete kratke premore, ki pomagajo razlikovati govorne odseke. Pri intervjuju vprašanje in odgovor ohranite skupaj, kadar naloga potrebuje njuno povezavo. Priprava zvoka mora zagotoviti slišnost govora, ne da bi odstranila informacije, pomembne za rezultat z označenimi govorci.</p><p>To je potek prepisa datoteke. Obdelava dokončanega posnetka in prepoznavanje zvočnega toka, ki še prihaja, sta različni nalogi; označevanje govorcev tega modela ni podprto v sejah prepisa Realtime.</p><h4>Zahtevajte prepis z označenimi govorci</h4><p>Izhodni format <code>diarized_json</code> vrne segmente z identifikacijskimi oznakami govorcev ter začetnim in končnim časom. Vsak segment vsebuje tudi svoje prepisano besedilo. Ta polja ohranite skupaj, da je mogoče besede povezati z ustreznim delom posnetka.</p><p>Za uporaben prepis sestanka ohranite zaporedje segmentov in besede vsakega govorca prikažite z njihovimi časovnimi podatki. Poznejša naloga lahko s tem prepisom pripravi zapisnik ali seznam nalog, diarizacija sama pa ne odloči, kaj je bilo na sestanku dogovorjeno, in ne ustvari preverjenega povzetka.</p><p>Oznake govorcev opisujejo modelovo združevanje govora. Preglejte prehode, pri katerih se ljudje prekinjajo, govorijo na kratko ali hkrati. Dobro strukturiran rezultat pomaga pri navigaciji in pregledu, posamezna pripisava pa lahko še vedno zahteva poslušanje izvirnega zvoka.</p><h4>Reference znanih govorcev</h4><p>Dokumentirani potek lahko sprejme do štirih poimenovanih referenc govorcev. Vsaka referenca je kratek zvočni izsek, dolg 2–10 sekund, v formatu, podprtem pri glavnem nalaganju. Imena in reference se predložijo skupaj, da je segmente mogoče povezati z znanimi govorci.</p><p>Pripravite referenco, ki jasno vsebuje predvidenega govorca, in njeno ime ohranite skladno s predvidenimi oznakami prepisa. Pri intervjuju lahko referenca voditelja pomaga urediti rezultat z označenimi govorci, ne da bi vsak udeleženec dobil anonimno oznako. Referenca je vhod za pripisovanje; ni splošna operacija kloniranja glasu ali dokaz identitete osebe.</p><p>Poimenovanja govorca ne zamenjujte z urejanjem izgovorjenih besed. Uporaben izhod mora še vedno ohraniti vsebino posnetka in dejanski vrstni red govornih odsekov.</p><h4>Delitev na dele in omejitve modela</h4><p>Za zvok, daljši od 30 sekund, proizvajalec zahteva strategijo delitve na dele, bodisi samodejno delitev bodisi konfiguracijo zaznavanja govorne aktivnosti. Ta zahteva ni največja dolžina posnetka. Opisuje, kako se daljši vhod razdeli za obdelavo.</p><p>Kartica modela navaja kontekstno okno 16000 tokenov in največ 2000 izhodnih tokenov. To so omejitve tokenov modela, ločene od omejitve nalaganja 25 MB v datotečnem poteku in praga delitve na dele. Ne smejo se pretvoriti v izmišljeno število minut, ki bi veljalo za vsak posnetek.</p><p>Pri sestavljanju ali pregledu daljšega prepisa ohranite časovne podatke in identiteto segmentov. Če je bil posnetek pred oddajo razdeljen, ohranite povezavo vsakega dela z izvirnim zvokom, da se lokalna časovna oznaka ne zamenja s položajem v celotnem pogovoru.</p><h4>Pretočno podajanje dokončanih segmentov</h4><p>Datotečni potek prepisa lahko besedilo pretočno podaja med obdelavo posnetka. Pri pretočnem podajanju z označenimi govorci dokončani segmenti ustvarijo dogodke segmentov. Prirastki besedila vključujejo identifikator segmenta, ne vsebujejo pa delnih pripisav govorcev; govorec se določi, ko je segment dokončan.</p><p>Ta razlika je pomembna pri prikazu. Začasno besedilo in dokončani govorni odsek prikažite kot različni stanji, namesto da negotovo oznako govorca pripnete, preden model dokonča segment. Dokončani rezultat ohranite, kadar je prepis potreben za poznejše urejanje ali analizo.</p><h4>Meje modela in izhoda</h4><p>Ta profil je model za diarizacijo, ločen od običajnega prepisa GPT-4o, prepisa Mini, sinteze govora in modelov za pogovor v živo. Ne podpira pozivov za prepis; morebitni pregled terminologije ali popravek ohranite kot ločen korak, preverjen glede na izvirni zvok. Njegov proizvajalčev vmesnik je prepis posnetega zvoka v besedilo. Ne ustvari zvočnega odgovora in ne prevede posnetka prek ločenega poteka zvočnega prevajanja.</p><p>Uporabite ga za prepise, ki potrebujejo vsebino in strukturo govorcev. Imena, tehnične izraze, številke, meje govornih odsekov in pripisave preverite glede na posnetek. Ohranite zvok, izbrani format rezultata, reference in dokončani prepis, da lahko popravek obravnava konkretno frazo ali pripisavo govorca.</p>",
  "aboutText": "GPT-4o Transcribe Diarize je model OpenAI za samodejno prepoznavanje govora z vgrajeno diarizacijo govorcev. Prepisane zvočne segmente poveže z različnimi govorci v pogovoru. Uporaben rezultat je prepis, urejen po govorcih in času, namesto zgolj neprekinjenega bloka besed. Namenjen je posnetemu govoru, ki potrebuje oznake govorcev, na primer sestanku, intervjuju ali razpravi več oseb.\n\n### Pripravite dokončani posnetek\n\nPredložite posnetek za prepis. Dokumentirani datotečni potek sprejema MP3, MP4, MPEG, MPGA, M4A, WAV in WebM z omejitvijo velikosti datoteke 25 MB. Izvorni posnetek ohranite dostopen, da je mogoče posamezni govorčev prispevek, ime ali nejasno frazo preveriti glede na dejanski zvok.\n\nPri sestanku ohranite zaporedje pogovora, namesto da izrežete kratke premore, ki pomagajo razlikovati govorne odseke. Pri intervjuju vprašanje in odgovor ohranite skupaj, kadar naloga potrebuje njuno povezavo. Priprava zvoka mora zagotoviti slišnost govora, ne da bi odstranila informacije, pomembne za rezultat z označenimi govorci.\n\nTo je potek prepisa datoteke. Obdelava dokončanega posnetka in prepoznavanje zvočnega toka, ki še prihaja, sta različni nalogi; označevanje govorcev tega modela ni podprto v sejah prepisa Realtime.\n\n### Zahtevajte prepis z označenimi govorci\n\nIzhodni format `diarized_json` vrne segmente z identifikacijskimi oznakami govorcev ter začetnim in končnim časom. Vsak segment vsebuje tudi svoje prepisano besedilo. Ta polja ohranite skupaj, da je mogoče besede povezati z ustreznim delom posnetka.\n\nZa uporaben prepis sestanka ohranite zaporedje segmentov in besede vsakega govorca prikažite z njihovimi časovnimi podatki. Poznejša naloga lahko s tem prepisom pripravi zapisnik ali seznam nalog, diarizacija sama pa ne odloči, kaj je bilo na sestanku dogovorjeno, in ne ustvari preverjenega povzetka.\n\nOznake govorcev opisujejo modelovo združevanje govora. Preglejte prehode, pri katerih se ljudje prekinjajo, govorijo na kratko ali hkrati. Dobro strukturiran rezultat pomaga pri navigaciji in pregledu, posamezna pripisava pa lahko še vedno zahteva poslušanje izvirnega zvoka.\n\n### Reference znanih govorcev\n\nDokumentirani potek lahko sprejme do štirih poimenovanih referenc govorcev. Vsaka referenca je kratek zvočni izsek, dolg 2–10 sekund, v formatu, podprtem pri glavnem nalaganju. Imena in reference se predložijo skupaj, da je segmente mogoče povezati z znanimi govorci.\n\nPripravite referenco, ki jasno vsebuje predvidenega govorca, in njeno ime ohranite skladno s predvidenimi oznakami prepisa. Pri intervjuju lahko referenca voditelja pomaga urediti rezultat z označenimi govorci, ne da bi vsak udeleženec dobil anonimno oznako. Referenca je vhod za pripisovanje; ni splošna operacija kloniranja glasu ali dokaz identitete osebe.\n\nPoimenovanja govorca ne zamenjujte z urejanjem izgovorjenih besed. Uporaben izhod mora še vedno ohraniti vsebino posnetka in dejanski vrstni red govornih odsekov.\n\n### Delitev na dele in omejitve modela\n\nZa zvok, daljši od 30 sekund, proizvajalec zahteva strategijo delitve na dele, bodisi samodejno delitev bodisi konfiguracijo zaznavanja govorne aktivnosti. Ta zahteva ni največja dolžina posnetka. Opisuje, kako se daljši vhod razdeli za obdelavo.\n\nKartica modela navaja kontekstno okno 16000 tokenov in največ 2000 izhodnih tokenov. To so omejitve tokenov modela, ločene od omejitve nalaganja 25 MB v datotečnem poteku in praga delitve na dele. Ne smejo se pretvoriti v izmišljeno število minut, ki bi veljalo za vsak posnetek.\n\nPri sestavljanju ali pregledu daljšega prepisa ohranite časovne podatke in identiteto segmentov. Če je bil posnetek pred oddajo razdeljen, ohranite povezavo vsakega dela z izvirnim zvokom, da se lokalna časovna oznaka ne zamenja s položajem v celotnem pogovoru.\n\n### Pretočno podajanje dokončanih segmentov\n\nDatotečni potek prepisa lahko besedilo pretočno podaja med obdelavo posnetka. Pri pretočnem podajanju z označenimi govorci dokončani segmenti ustvarijo dogodke segmentov. Prirastki besedila vključujejo identifikator segmenta, ne vsebujejo pa delnih pripisav govorcev; govorec se določi, ko je segment dokončan.\n\nTa razlika je pomembna pri prikazu. Začasno besedilo in dokončani govorni odsek prikažite kot različni stanji, namesto da negotovo oznako govorca pripnete, preden model dokonča segment. Dokončani rezultat ohranite, kadar je prepis potreben za poznejše urejanje ali analizo.\n\n### Meje modela in izhoda\n\nTa profil je model za diarizacijo, ločen od običajnega prepisa GPT-4o, prepisa Mini, sinteze govora in modelov za pogovor v živo. Ne podpira pozivov za prepis; morebitni pregled terminologije ali popravek ohranite kot ločen korak, preverjen glede na izvirni zvok. Njegov proizvajalčev vmesnik je prepis posnetega zvoka v besedilo. Ne ustvari zvočnega odgovora in ne prevede posnetka prek ločenega poteka zvočnega prevajanja.\n\nUporabite ga za prepise, ki potrebujejo vsebino in strukturo govorcev. Imena, tehnične izraze, številke, meje govornih odsekov in pripisave preverite glede na posnetek. Ohranite zvok, izbrani format rezultata, reference in dokončani prepis, da lahko popravek obravnava konkretno frazo ali pripisavo govorca.",
  "editorialOverlay": {
    "copy_fields": null,
    "copy_sha256": null,
    "copy_source": null,
    "html_sha256": "609423e260e329d6965eb907788b7b5bf3183bcb8192527156565b48ec9e5672",
    "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06",
    "raw_model_unchanged": true,
    "schema": "ailoot-native-model-editorial-v1"
  },
  "locale": "sl",
  "methods": [
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">O</span><h2 id=\"sheet-title\">gpt-4o-transcribe-diarize</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"Zapri\">×</button></div><div class=\"idline\"><span>OpenAI /</span><code>openai/gpt-4o-transcribe-diarize</code><button type=\"button\" id=\"copy-id\">Kopiraj ID</button></div><nav class=\"card-jump-nav\" aria-label=\"Razdelki kartice modela\"><button type=\"button\" data-card-jump=\"overview\">Začetek</button><button type=\"button\" data-card-jump=\"methods\">Vhodi in metode</button><button type=\"button\" data-card-jump=\"pricing\">Cenik</button><button type=\"button\" data-card-jump=\"examples\">Primeri</button><button type=\"button\" data-card-jump=\"results\">Rezultati</button><button type=\"button\" data-card-jump=\"aliases\">Druga imena</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"Metode API\"><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-0\" data-card-method=\"Ultra|transcriptions|/v1/audio/transcriptions|openai%2Fgpt-4o-transcribe-diarize\">Prepoznavanje</button></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-0\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">Začetek</h3><p class=\"mdesc-full\">GPT-4o Transcribe Diarize pretvori posneti govor v besedilo s segmenti, označenimi po govorcih, in časovnimi podatki. Primeren je za sestanke, intervjuje in posnetke več oseb, pri katerih mora prepis pokazati, kdo je kdaj govoril, z izbirnimi kratkimi glasovnimi referencami za znane govorce.</p><dl class=\"card-io\" data-card-io><div><dt>Dovoljeni vhodi</dt><dd>Zvok</dd></div><div><dt>Rezultati</dt><dd>transcription</dd></div></dl><details class=\"card-about\"><summary>O modelu</summary><p class=\"note-s\" data-model-method-boundary>Ta opis zajema zmožnosti modela. Vhodi, izhodi in možnosti, ki so na voljo v Ailoot, so spodaj navedeni za izbrano metodo.</p><div class=\"mabout\" id=\"m-about\"><p>GPT-4o Transcribe Diarize je model OpenAI za samodejno prepoznavanje govora z vgrajeno diarizacijo govorcev. Prepisane zvočne segmente poveže z različnimi govorci v pogovoru. Uporaben rezultat je prepis, urejen po govorcih in času, namesto zgolj neprekinjenega bloka besed. Namenjen je posnetemu govoru, ki potrebuje oznake govorcev, na primer sestanku, intervjuju ali razpravi več oseb.</p><h4>Pripravite dokončani posnetek</h4><p>Predložite posnetek za prepis. Dokumentirani datotečni potek sprejema MP3, MP4, MPEG, MPGA, M4A, WAV in WebM z omejitvijo velikosti datoteke 25 MB. Izvorni posnetek ohranite dostopen, da je mogoče posamezni govorčev prispevek, ime ali nejasno frazo preveriti glede na dejanski zvok.</p><p>Pri sestanku ohranite zaporedje pogovora, namesto da izrežete kratke premore, ki pomagajo razlikovati govorne odseke. Pri intervjuju vprašanje in odgovor ohranite skupaj, kadar naloga potrebuje njuno povezavo. Priprava zvoka mora zagotoviti slišnost govora, ne da bi odstranila informacije, pomembne za rezultat z označenimi govorci.</p><p>To je potek prepisa datoteke. Obdelava dokončanega posnetka in prepoznavanje zvočnega toka, ki še prihaja, sta različni nalogi; označevanje govorcev tega modela ni podprto v sejah prepisa Realtime.</p><h4>Zahtevajte prepis z označenimi govorci</h4><p>Izhodni format <code>diarized_json</code> vrne segmente z identifikacijskimi oznakami govorcev ter začetnim in končnim časom. Vsak segment vsebuje tudi svoje prepisano besedilo. Ta polja ohranite skupaj, da je mogoče besede povezati z ustreznim delom posnetka.</p><p>Za uporaben prepis sestanka ohranite zaporedje segmentov in besede vsakega govorca prikažite z njihovimi časovnimi podatki. Poznejša naloga lahko s tem prepisom pripravi zapisnik ali seznam nalog, diarizacija sama pa ne odloči, kaj je bilo na sestanku dogovorjeno, in ne ustvari preverjenega povzetka.</p><p>Oznake govorcev opisujejo modelovo združevanje govora. Preglejte prehode, pri katerih se ljudje prekinjajo, govorijo na kratko ali hkrati. Dobro strukturiran rezultat pomaga pri navigaciji in pregledu, posamezna pripisava pa lahko še vedno zahteva poslušanje izvirnega zvoka.</p><h4>Reference znanih govorcev</h4><p>Dokumentirani potek lahko sprejme do štirih poimenovanih referenc govorcev. Vsaka referenca je kratek zvočni izsek, dolg 2–10 sekund, v formatu, podprtem pri glavnem nalaganju. Imena in reference se predložijo skupaj, da je segmente mogoče povezati z znanimi govorci.</p><p>Pripravite referenco, ki jasno vsebuje predvidenega govorca, in njeno ime ohranite skladno s predvidenimi oznakami prepisa. Pri intervjuju lahko referenca voditelja pomaga urediti rezultat z označenimi govorci, ne da bi vsak udeleženec dobil anonimno oznako. Referenca je vhod za pripisovanje; ni splošna operacija kloniranja glasu ali dokaz identitete osebe.</p><p>Poimenovanja govorca ne zamenjujte z urejanjem izgovorjenih besed. Uporaben izhod mora še vedno ohraniti vsebino posnetka in dejanski vrstni red govornih odsekov.</p><h4>Delitev na dele in omejitve modela</h4><p>Za zvok, daljši od 30 sekund, proizvajalec zahteva strategijo delitve na dele, bodisi samodejno delitev bodisi konfiguracijo zaznavanja govorne aktivnosti. Ta zahteva ni največja dolžina posnetka. Opisuje, kako se daljši vhod razdeli za obdelavo.</p><p>Kartica modela navaja kontekstno okno 16000 tokenov in največ 2000 izhodnih tokenov. To so omejitve tokenov modela, ločene od omejitve nalaganja 25 MB v datotečnem poteku in praga delitve na dele. Ne smejo se pretvoriti v izmišljeno število minut, ki bi veljalo za vsak posnetek.</p><p>Pri sestavljanju ali pregledu daljšega prepisa ohranite časovne podatke in identiteto segmentov. Če je bil posnetek pred oddajo razdeljen, ohranite povezavo vsakega dela z izvirnim zvokom, da se lokalna časovna oznaka ne zamenja s položajem v celotnem pogovoru.</p><h4>Pretočno podajanje dokončanih segmentov</h4><p>Datotečni potek prepisa lahko besedilo pretočno podaja med obdelavo posnetka. Pri pretočnem podajanju z označenimi govorci dokončani segmenti ustvarijo dogodke segmentov. Prirastki besedila vključujejo identifikator segmenta, ne vsebujejo pa delnih pripisav govorcev; govorec se določi, ko je segment dokončan.</p><p>Ta razlika je pomembna pri prikazu. Začasno besedilo in dokončani govorni odsek prikažite kot različni stanji, namesto da negotovo oznako govorca pripnete, preden model dokonča segment. Dokončani rezultat ohranite, kadar je prepis potreben za poznejše urejanje ali analizo.</p><h4>Meje modela in izhoda</h4><p>Ta profil je model za diarizacijo, ločen od običajnega prepisa GPT-4o, prepisa Mini, sinteze govora in modelov za pogovor v živo. Ne podpira pozivov za prepis; morebitni pregled terminologije ali popravek ohranite kot ločen korak, preverjen glede na izvirni zvok. Njegov proizvajalčev vmesnik je prepis posnetega zvoka v besedilo. Ne ustvari zvočnega odgovora in ne prevede posnetka prek ločenega poteka zvočnega prevajanja.</p><p>Uporabite ga za prepise, ki potrebujejo vsebino in strukturo govorcev. Imena, tehnične izraze, številke, meje govornih odsekov in pripisave preverite glede na posnetek. Ohranite zvok, izbrani format rezultata, reference in dokončani prepis, da lahko popravek obravnava konkretno frazo ali pripisavo govorca.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Na voljo v Ailoot · vhodi in metode</h3><details class=\"card-method\" open><summary><b>Ailoot Ultra · Prepoznavanje govora</b> <code>POST /v1/audio/transcriptions</code></summary><dl class=\"method-capabilities\"><div><dt>Vhod</dt><dd><code>audio</code></dd></div><div><dt>Izhod</dt><dd><code>transcription</code></dd></div><div><dt>Izhodni format</dt><dd>json</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>Polje</th><th>Vrsta</th><th>Zahteva</th><th>Vrednosti in omejitve</th><th>Privzeto</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Polje\" scope=\"row\"><span class=\"card-cell-label\">Polje</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"Vrsta\" data-field-type><span class=\"card-cell-label\">Vrsta</span><code>string</code></td><td data-cell-label=\"Zahteva\"><span class=\"card-cell-label\">Zahteva</span>Obvezno</td><td data-cell-label=\"Vrednosti in omejitve\"><span class=\"card-cell-label\">Vrednosti in omejitve</span><div>openai/gpt-4o-transcribe-diarize</div></td><td data-cell-label=\"Privzeto\" data-default=\"unspecified\"><span class=\"card-cell-label\">Privzeto</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Polje\" scope=\"row\"><span class=\"card-cell-label\">Polje</span><code class=\"card-field-name\">file</code></th><td data-cell-label=\"Vrsta\" data-field-type><span class=\"card-cell-label\">Vrsta</span><code>file</code></td><td data-cell-label=\"Zahteva\"><span class=\"card-cell-label\">Zahteva</span>Obvezno</td><td data-cell-label=\"Vrednosti in omejitve\"><span class=\"card-cell-label\">Vrednosti in omejitve</span><div>Največ bajtov: 26.214.400</div><div>Vrste MIME: audio/mpeg</div><div>Pripona datoteke: .mp3</div><div>Najdaljše trajanje, sekunde: 30</div></td><td data-cell-label=\"Privzeto\" data-default=\"unspecified\"><span class=\"card-cell-label\">Privzeto</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"Polje\" scope=\"row\"><span class=\"card-cell-label\">Polje</span><code class=\"card-field-name\">response_format</code></th><td data-cell-label=\"Vrsta\" data-field-type><span class=\"card-cell-label\">Vrsta</span><code>string</code></td><td data-cell-label=\"Zahteva\"><span class=\"card-cell-label\">Zahteva</span>Obvezno</td><td data-cell-label=\"Vrednosti in omejitve\"><span class=\"card-cell-label\">Vrednosti in omejitve</span><div>diarized_json</div></td><td data-cell-label=\"Privzeto\" data-default=\"unspecified\"><span class=\"card-cell-label\">Privzeto</span>—</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>Kombinacije vhodnih gradiv</summary><p class=\"note-s\"><b>diarized_transcription</b></p></details><details class=\"note-s\" data-method-contract><summary>Parametri in življenjski cikel metode</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>Parameter</th><th>Specifikacija</th></tr></thead><tbody><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>content_type</code></th><td data-cell-label=\"Specifikacija\"><span class=\"card-cell-label\">Specifikacija</span>multipart/form-data</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>required</code></th><td data-cell-label=\"Specifikacija\"><span class=\"card-cell-label\">Specifikacija</span>model, file, response_format</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>file_formats</code></th><td data-cell-label=\"Specifikacija\"><span class=\"card-cell-label\">Specifikacija</span>mp3</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>max_audio_seconds</code></th><td data-cell-label=\"Specifikacija\"><span class=\"card-cell-label\">Specifikacija</span>30</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>max_bytes</code></th><td data-cell-label=\"Specifikacija\"><span class=\"card-cell-label\">Specifikacija</span>26214400</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>response_format</code></th><td data-cell-label=\"Specifikacija\"><span class=\"card-cell-label\">Specifikacija</span>diarized_json</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>other_options</code></th><td data-cell-label=\"Specifikacija\"><span class=\"card-cell-label\">Specifikacija</span>false</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>material_types</code></th><td data-cell-label=\"Specifikacija\"><span class=\"card-cell-label\">Specifikacija</span>audio</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>additional_properties</code></th><td data-cell-label=\"Specifikacija\"><span class=\"card-cell-label\">Specifikacija</span>false</td></tr><tr><th data-cell-label=\"Parameter\" scope=\"row\"><span class=\"card-cell-label\">Parameter</span><code>form_string_maximum_bytes</code></th><td data-cell-label=\"Specifikacija\"><span class=\"card-cell-label\">Specifikacija</span>256</td></tr></tbody></table></div><p>Druga imena metode: <code>/audio/transcriptions</code></p><p>Življenjski cikel: <code>synchronous_result_then_owned_library</code></p><p class=\"note-s\"><code>GET /v1/media/tasks/{task_id}</code> · Dejansko vrnjeni task_id ali zapis v medijski knjižnici</p><p class=\"note-s\"><code>GET /v1/media/assets/{asset_id}/content</code></p><p class=\"note-s\"><code>GET /v1/media/assets</code></p><p class=\"note-s\"><code>GET /v1/media/assets/{asset_id}</code></p><p class=\"note-s\">Uporabite dejanski posnetek in ustrezno obliko.</p><p class=\"note-s\">Ohranite celoten prepis, segmente, ID-je govorcev in časovne podatke.</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">Cenik</h3><div data-native-semantic-method=\"v1\" data-tariff-reference-only><p class=\"note-s\" data-rate-support-note>Tarifni podatki ne dodajajo možnosti zahteve. Podprti parametri so navedeni pri izbrani metodi.</p><dl data-price-conditions><dt>Hitri način</dt><dd>Ni navedeno <span class=\"note-s\">Ko je izbran hitri način</span></dd><dt>Način flex</dt><dd>Ni navedeno <span class=\"note-s\">Ko je izbran način flex</span></dd><dt>Najvišja raven razmišljanja</dt><dd>Ni navedeno <span class=\"note-s\">Ko najvišja raven razmišljanja uporablja privzeto prilagoditev (default)</span></dd></dl></div><div data-declared-tariff-pricing><h4>Cene Ailoot</h4><h4>Cene po nastavitvah</h4><p class=\"note-s\">Vsak strošek povežite s prikazanimi pogoji. Za vsak nabor alternativnih nastavitev uporabite eno ceno.</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>Nastavitev</th><th>Cenovna lestvica</th><th>Obračunska enota</th><th>Strošek</th></tr></thead><tbody><tr><th data-cell-label=\"Nastavitev\" scope=\"row\"><span class=\"card-cell-label\">Nastavitev</span>Osnovne cene žetonov</th><td data-cell-label=\"Cenovna lestvica\"><span class=\"card-cell-label\">Cenovna lestvica</span>Osnovna cena</td><td data-cell-label=\"Obračunska enota\"><span class=\"card-cell-label\">Obračunska enota</span>—</td><td data-cell-label=\"Strošek\"><span class=\"card-cell-label\">Strošek</span><div><span>Vhod · Vhodni žetoni</span> <b>—</b> <span class=\"price-unit\">/ 1K žetonov</span></div><div><span>Izhod · Izhodni žetoni</span> <b>—</b> <span class=\"price-unit\">/ 1K žetonov</span></div><div><span>Vhod · Branje predpomnilnika</span> <b>—</b> <span class=\"price-unit\">/ 1K žetonov</span></div><div><span>Vhod · Zapis v predpomnilnik</span> <b>—</b> <span class=\"price-unit\">/ 1K žetonov</span></div><div><span>Vhod · Zapis v predpomnilnik, 1 ura</span> <b>—</b> <span class=\"price-unit\">/ 1K žetonov</span></div></td></tr><tr><th data-cell-label=\"Nastavitev\" scope=\"row\"><span class=\"card-cell-label\">Nastavitev</span>Ultra</th><td data-cell-label=\"Cenovna lestvica\"><span class=\"card-cell-label\">Cenovna lestvica</span>—</td><td data-cell-label=\"Obračunska enota\"><span class=\"card-cell-label\">Obračunska enota</span>/ 1K zvočnih žetonov</td><td data-cell-label=\"Strošek\"><span class=\"card-cell-label\">Strošek</span><div><span>Vhod · vhodni zvočni žeton</span> <b>$0.012</b> <span class=\"price-unit\">/ 1K zvočnih žetonov</span></div></td></tr><tr><th data-cell-label=\"Nastavitev\" scope=\"row\"><span class=\"card-cell-label\">Nastavitev</span>Ultra</th><td data-cell-label=\"Cenovna lestvica\"><span class=\"card-cell-label\">Cenovna lestvica</span>—</td><td data-cell-label=\"Obračunska enota\"><span class=\"card-cell-label\">Obračunska enota</span>/ 1K zvočnih žetonov</td><td data-cell-label=\"Strošek\"><span class=\"card-cell-label\">Strošek</span><div><span>Izhod · izhodni zvočni žeton</span> <b>$0.02</b> <span class=\"price-unit\">/ 1K zvočnih žetonov</span></div></td></tr></tbody></table></div></div><p class=\"note-s\">Ailoot pred zahtevo rezervira ocenjeni znesek. Po rezultatu obračuna končni strošek na podlagi izmerjene porabe. Obračun pretakanja uporablja končni zapis porabe. <a href=\"/docs/sl/billing/reserve/\">Kako delujeta rezervacija in obračun →</a></p></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">Primeri zahtev</h3><h4>Ailoot Ultra · Prepoznavanje govora</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"Primeri kode\"><button class=\"cg-tab\" id=\"model-code-2050-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-2050-panel-0\" aria-selected=\"true\" tabindex=\"0\">curl · natančno ohranjena zahteva za ustvarjanje</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"Kopiraj kodo\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-2050-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-2050-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_AUDIO_FILE:?Set the path to your actual MP3 recording}&quot;\nexport AILOOT_AUDIO_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport os\nfrom pathlib import Path\np=Path(os.environ[&quot;AILOOT_AUDIO_FILE&quot;])\nif not p.is_file() or p.suffix.lower()!=&quot;.mp3&quot;:raise SystemExit(&quot;Choose an existing MP3 recording&quot;)\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/audio/transcriptions \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; \\\n  --form-string model=openai/gpt-4o-transcribe-diarize -F &quot;file=@$AILOOT_AUDIO_FILE&quot; --form-string response_format=diarized_json \\\n  -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;result.json&quot;).read_text())))\nPY_RESULT\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">Prejmi in shrani rezultate</h3><h4>Ailoot Ultra · Prepoznavanje govora</h4><p class=\"note-s\">json</p><ul class=\"card-result-paths\"><li><code>GET /v1/media/tasks/{task_id}</code></li><li><code>GET /v1/media/assets/{asset_id}/content</code></li><li><code>GET /v1/media/assets</code></li><li><code>GET /v1/media/assets/{asset_id}</code></li></ul><details class=\"card-about\"><summary>Branje druge vsebine</summary><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"Primeri kode\"><button class=\"cg-tab\" id=\"model-code-2051-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-2051-panel-0\" aria-selected=\"true\" tabindex=\"0\">Shrani vsak vrnjen prepis, ki vam pripada</button><button class=\"cg-tab\" id=\"model-code-2051-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-2051-panel-1\" aria-selected=\"false\" tabindex=\"-1\">Medijska knjižnica</button><button class=\"cg-tab\" id=\"model-code-2051-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-2051-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Stanje opravila</button><button class=\"cg-tab\" id=\"model-code-2051-tab-3\" role=\"tab\" type=\"button\" aria-controls=\"model-code-2051-panel-3\" aria-selected=\"false\" tabindex=\"-1\">Podrobnosti gradiva</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"Kopiraj kodo\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-2051-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-2051-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\nexport AILOOT_API_KEY\npython3 - &lt;&lt;&#39;PY_ASSETS&#39;\nimport json,os,subprocess\nfrom pathlib import Path\nfrom urllib.parse import urljoin,urlsplit\nr=json.loads(Path(&#39;result.json&#39;).read_text())\nurls=[]\nif isinstance(r.get(&#39;asset_url&#39;),str) and r[&#39;asset_url&#39;]:urls.append((&#39;transcript&#39;,r[&#39;asset_url&#39;]))\nfor label,path in urls:\n    u=urljoin(&#39;https://api.ailoot.ai&#39;,path);z=urlsplit(u)\n    if z.scheme!=&#39;https&#39; or z.netloc!=&#39;api.ailoot.ai&#39; or z.username or z.password:raise SystemExit(&#39;Use the actual returned Ailoot owned content URL&#39;)\n    target=Path(&#39;owned-&#39;+label+&#39;.bin&#39;)\n    subprocess.run([&#39;curl&#39;,&#39;--fail-with-body&#39;,&#39;--silent&#39;,&#39;--show-error&#39;,u,&#39;-H&#39;,&#39;Authorization: Bearer &#39;+os.environ[&#39;AILOOT_API_KEY&#39;],&#39;-D&#39;,str(target)+&#39;.headers&#39;,&#39;-o&#39;,str(target)],check=True)\nprint(&#39;All returned owned URLs saved; complete metadata, timing and usage remain in the JSON.&#39;)\nPY_ASSETS\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-2051-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-2051-tab-1\" hidden><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/media/assets \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -o media-assets.json\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-2051-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-2051-tab-2\" hidden><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_MEDIA_TASK_ID:?Set the actual ID returned by the response or media-library metadata}&quot;\nexport AILOOT_MEDIA_TASK_ID\nresource_id=$(python3 -c &#39;import os,urllib.parse;print(urllib.parse.quote(os.environ[&quot;AILOOT_MEDIA_TASK_ID&quot;],safe=&quot;&quot;))&#39;)\ncurl --fail-with-body --silent --show-error &quot;https://api.ailoot.ai/v1/media/tasks/$resource_id&quot; \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -o media-task.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;media-task.json&quot;).read_text())))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-2051-panel-3\" role=\"tabpanel\" aria-labelledby=\"model-code-2051-tab-3\" hidden><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_ASSET_ID:?Set the actual ID returned by the response or media-library metadata}&quot;\nexport AILOOT_ASSET_ID\nresource_id=$(python3 -c &#39;import os,urllib.parse;print(urllib.parse.quote(os.environ[&quot;AILOOT_ASSET_ID&quot;],safe=&quot;&quot;))&#39;)\ncurl --fail-with-body --silent --show-error &quot;https://api.ailoot.ai/v1/media/assets/$resource_id&quot; \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -o media-asset.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;media-asset.json&quot;).read_text())))\nPY_RESULT\n</code></pre></div></div></div></details><div class=\"card-result-process\" data-all-results><h5>Ohrani vse dokončane rezultate</h5><p class=\"note-s\">Shranite vsak v celoti vrnjen odgovor, datoteko in del vsebine.</p><p class=\"note-s\">Ohranite celoten JSON in ne samo besedila; ohranite vsak razpoložljivi segment/govorca/časovno oznako in dejansko identiteto opravila/sredstva.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>Če je treba preveriti izvirni odgovor</h5><p class=\"note-s\">Shranite izvirni operation_id/X-Client-Request-ID za uskladitev evidenc brez ponovnega pošiljanja; namenska pot za periodično preverjanje zvoka ne obstaja.</p></div><details class=\"card-about\" data-output-fields><summary>Polja odgovora</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>Polje</th><th>Vrsta</th></tr></thead><tbody><tr><th data-cell-label=\"Polje\" scope=\"row\"><span class=\"card-cell-label\">Polje</span><code class=\"card-field-name\">text</code></th><td data-cell-label=\"Vrsta\" data-field-type><span class=\"card-cell-label\">Vrsta</span>string</td></tr><tr><th data-cell-label=\"Polje\" scope=\"row\"><span class=\"card-cell-label\">Polje</span><code class=\"card-field-name\">segments[]</code></th><td data-cell-label=\"Vrsta\" data-field-type><span class=\"card-cell-label\">Vrsta</span>object</td></tr><tr><th data-cell-label=\"Polje\" scope=\"row\"><span class=\"card-cell-label\">Polje</span><code class=\"card-field-name\">task_id</code></th><td data-cell-label=\"Vrsta\" data-field-type><span class=\"card-cell-label\">Vrsta</span>string</td></tr><tr><th data-cell-label=\"Polje\" scope=\"row\"><span class=\"card-cell-label\">Polje</span><code class=\"card-field-name\">asset_url</code></th><td data-cell-label=\"Vrsta\" data-field-type><span class=\"card-cell-label\">Vrsta</span>string</td></tr><tr><th data-cell-label=\"Polje\" scope=\"row\"><span class=\"card-cell-label\">Polje</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"Vrsta\" data-field-type><span class=\"card-cell-label\">Vrsta</span>object</td></tr><tr><th data-cell-label=\"Polje\" scope=\"row\"><span class=\"card-cell-label\">Polje</span><code class=\"card-field-name\">segments[].speaker</code></th><td data-cell-label=\"Vrsta\" data-field-type><span class=\"card-cell-label\">Vrsta</span>string</td></tr><tr><th data-cell-label=\"Polje\" scope=\"row\"><span class=\"card-cell-label\">Polje</span><code class=\"card-field-name\">segments[].start</code></th><td data-cell-label=\"Vrsta\" data-field-type><span class=\"card-cell-label\">Vrsta</span>number</td></tr><tr><th data-cell-label=\"Polje\" scope=\"row\"><span class=\"card-cell-label\">Polje</span><code class=\"card-field-name\">segments[].end</code></th><td data-cell-label=\"Vrsta\" data-field-type><span class=\"card-cell-label\">Vrsta</span>number</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>Napake in naslednji koraki</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>Odgovor</th><th>Pogoj</th><th>Naslednji korak</th></tr></thead><tbody><tr><th data-cell-label=\"Odgovor\" scope=\"row\"><span class=\"card-cell-label\">Odgovor</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"Pogoj\"><span class=\"card-cell-label\">Pogoj</span>Neveljavna obvezna polja, predstavitev gradiva ali vrednost parametra</td><td data-cell-label=\"Naslednji korak\"><span class=\"card-cell-label\">Naslednji korak</span>Pred novo zahtevo za ustvarjanje popravite navedena polja.</td></tr><tr><th data-cell-label=\"Odgovor\" scope=\"row\"><span class=\"card-cell-label\">Odgovor</span><code>server_error</code></th><td data-cell-label=\"Pogoj\"><span class=\"card-cell-label\">Pogoj</span>Vrnjeni odgovor navaja, da je treba operacijo ali rezultat preveriti</td><td data-cell-label=\"Naslednji korak\"><span class=\"card-cell-label\">Naslednji korak</span>Shranite izvirni vrnjeni ID operacije/opravila, glave zahteve in odgovor; nadaljujte s podprtimi branji te izvirne operacije. Zahteve za ustvarjanje ne pošiljajte znova.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">Druga imena</h3><h4>Druga imena modelov</h4><p class=\"note-s\"><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=openai%2Fgpt-4o-transcribe-diarize&amp;route=Ultra&amp;caller=openai%2Fgpt-4o-transcribe-diarize&amp;fmt=transcriptions\"><code>openai/gpt-4o-transcribe-diarize</code></a></span></p><h4>Druga imena poti metod</h4><p class=\"note-s\"><code>/audio/transcriptions</code></p><h4>Povezani ID-ji za klic</h4><p class=\"note-s\"><a href=\"#m=openai%2Fgpt-4o-transcribe-diarize&amp;route=Ultra&amp;caller=openai%2Fgpt-4o-transcribe-diarize&amp;fmt=transcriptions\"><code>openai/gpt-4o-transcribe-diarize</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "openai/gpt-4o-transcribe-diarize",
        "fmt": "transcriptions",
        "http": "POST",
        "path": "/v1/audio/transcriptions",
        "request_model_id": "openai/gpt-4o-transcribe-diarize",
        "route_label": "Ultra"
      },
      "method_key": "Ultra|transcriptions|/v1/audio/transcriptions|openai%2Fgpt-4o-transcribe-diarize",
      "ordinal": 0,
      "rawMethod": {
        "available": null,
        "cache_read": null,
        "cache_write": null,
        "cache_write_1h": null,
        "contract": {
          "data": {
            "all_results": "Retain complete JSON, not only text; preserve every available segment/speaker/timestamp and actual task/asset identity.",
            "errors": [
              {
                "code": null,
                "condition": "Neveljavna obvezna polja, predstavitev gradiva ali vrednost parametra",
                "http_status": 400,
                "recovery": "Pred novo zahtevo za ustvarjanje popravite navedena polja.",
                "type": "invalid_request_error"
              },
              {
                "code": null,
                "condition": "Vrnjeni odgovor navaja, da je treba operacijo ali rezultat preveriti",
                "http_status": null,
                "recovery": "Shranite izvirni vrnjeni ID operacije/opravila, glave zahteve in odgovor; nadaljujte s podprtimi branji te izvirne operacije. Zahteve za ustvarjanje ne pošiljajte znova.",
                "type": "server_error"
              }
            ],
            "hints": [],
            "ignored_fields": [],
            "lifecycle": {
              "all_results": "Follow everyactualreturnedoutputandownedasset; no result is discardedbecauseindex0orcontent_urlalreadyexists.",
              "assets": [
                {
                  "http": "GET",
                  "path": "/v1/media/assets"
                },
                {
                  "http": "GET",
                  "path": "/v1/media/assets/{asset_id}"
                }
              ],
              "content": [
                {
                  "http": "GET",
                  "path": "/v1/media/assets/{asset_id}/content",
                  "url_source": "exact returned signed URL; never construct token"
                }
              ],
              "mode": "synchronous_result_then_owned_library",
              "operation_id_is_not_task_id": true,
              "status": [
                {
                  "http": "GET",
                  "id_source": "actual returned task_id or media library record",
                  "path": "/v1/media/tasks/{task_id}"
                }
              ],
              "unknown": "Shranite izvirni operation_id/X-Client-Request-ID za uskladitev evidenc brez ponovnega pošiljanja; namenska pot za periodično preverjanje zvoka ne obstaja."
            },
            "limits": {
              "decoded_audio_max_bytes": 26214400
            },
            "material_combinations": [
              {
                "content_type": "multipart/form-data",
                "file_formats": [
                  "mp3"
                ],
                "maximum_seconds": 30,
                "mode": "diarized_transcription"
              }
            ],
            "media_library": {
              "asset": {
                "fields": [
                  {
                    "description": null,
                    "name": "asset_id",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "task_id",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "output_key",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "family",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "model",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "method",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "status",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "content_type",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "sha256",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "size_bytes",
                    "type": "integer"
                  },
                  {
                    "description": null,
                    "name": "content_url",
                    "type": "string"
                  }
                ],
                "http": "GET",
                "id_source": "actual returned asset_id",
                "path": "/v1/media/assets/{asset_id}"
              },
              "content": {
                "http": "GET",
                "path": "/v1/media/assets/{asset_id}/content",
                "range_header_supported": true,
                "url_source": "Use exact returned signed content_url including its token; do not construct a token."
              },
              "expired_link": {
                "code": "link_expired",
                "http_status": 404,
                "recovery": "Read the asset again to obtain its refreshed signed content_url, then fetch that URL. Do not regenerate."
              },
              "list": {
                "all_pages": "Follow every returned next_cursor, then select records by their actual task_id/output_key.",
                "http": "GET",
                "output_fields": [
                  {
                    "description": null,
                    "name": "object",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "data",
                    "type": "asset[]"
                  },
                  {
                    "description": null,
                    "name": "next_cursor",
                    "type": "string|null"
                  }
                ],
                "parameters": [
                  {
                    "availability": "source_interface",
                    "default": null,
                    "default_known": false,
                    "enum": null,
                    "enum_known": false,
                    "name": "family",
                    "required": false,
                    "type": "string"
                  },
                  {
                    "availability": "source_interface",
                    "default": null,
                    "default_known": false,
                    "enum": null,
                    "enum_known": false,
                    "name": "cursor",
                    "required": false,
                    "type": "string"
                  },
                  {
                    "availability": "source_interface",
                    "default": 20,
                    "default_known": true,
                    "enum": null,
                    "enum_known": false,
                    "maximum": 100,
                    "minimum": 1,
                    "name": "limit",
                    "required": false,
                    "type": "integer"
                  }
                ],
                "path": "/v1/media/assets"
              },
              "revoke": {
                "http": "DELETE",
                "meaning": "Revokes/deletes the existing owned file; this is not generation cancellation.",
                "path": "/v1/media/assets/{asset_id}",
                "pending_status": "revoking",
                "success_statuses": [
                  202,
                  204
                ]
              },
              "task": {
                "http": "GET",
                "id_source": "actual returned task_id or media library record; operation_id is not task_id",
                "path": "/v1/media/tasks/{task_id}"
              }
            },
            "operation_modes": [
              "diarized_transcription"
            ],
            "outputs": {
              "all_results": "Ohranite celoten JSON in ne samo besedila; ohranite vsak razpoložljivi segment/govorca/časovno oznako in dejansko identiteto opravila/sredstva.",
              "family": "transcription",
              "fields": [
                {
                  "description": null,
                  "name": "text",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "segments[]",
                  "type": "object"
                },
                {
                  "description": null,
                  "name": "task_id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "asset_url",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                },
                {
                  "description": null,
                  "name": "segments[].speaker",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "segments[].start",
                  "type": "number"
                },
                {
                  "description": null,
                  "name": "segments[].end",
                  "type": "number"
                }
              ],
              "format": "json"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "openai/gpt-4o-transcribe-diarize"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "file_extension": ".mp3",
                "maximum_bytes": 26214400,
                "maximum_seconds": 30,
                "mime_types": [
                  "audio/mpeg"
                ],
                "name": "file",
                "required": true,
                "type": "file"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "diarized_json"
                ],
                "enum_known": true,
                "name": "response_format",
                "required": true,
                "type": "string"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": [
              "JSONinput_audio",
              "nonMP3",
              "audioover30seconds",
              "otheroptions"
            ]
          },
          "hints": [
            "Uporabite dejanski posnetek in ustrezno obliko.",
            "Ohranite celoten prepis, segmente, ID-je govorcev in časovne podatke."
          ],
          "input": {
            "additional_properties": false,
            "content_type": "multipart/form-data",
            "file_formats": [
              "mp3"
            ],
            "form_string_maximum_bytes": 256,
            "material_types": [
              "audio"
            ],
            "max_audio_seconds": 30,
            "max_bytes": 26214400,
            "other_options": false,
            "required": [
              "model",
              "file",
              "response_format"
            ],
            "response_format": [
              "diarized_json"
            ]
          },
          "lifecycle": {
            "all_results": "Follow everyactualreturnedoutputandownedasset; no result is discardedbecauseindex0orcontent_urlalreadyexists.",
            "assets": [
              {
                "http": "GET",
                "path": "/v1/media/assets"
              },
              {
                "http": "GET",
                "path": "/v1/media/assets/{asset_id}"
              }
            ],
            "content": [
              {
                "http": "GET",
                "path": "/v1/media/assets/{asset_id}/content",
                "url_source": "exact returned signed URL; never construct token"
              }
            ],
            "mode": "synchronous_result_then_owned_library",
            "operation_id_is_not_task_id": true,
            "status": [
              {
                "http": "GET",
                "id_source": "Dejansko vrnjeni task_id ali zapis v medijski knjižnici",
                "path": "/v1/media/tasks/{task_id}"
              }
            ],
            "unknown": "Retain original operation_id/X-Client-Request-ID for reconciliation without resubmission; no dedicated audio poll route."
          },
          "method": {
            "http": "POST",
            "path": "/v1/audio/transcriptions"
          },
          "method_aliases": [
            "/audio/transcriptions"
          ],
          "operation_modes": [
            "diarized_transcription"
          ],
          "output": {
            "all_results": "Retain complete JSON, not only text; preserve every available segment/speaker/timestamp and actual task/asset identity.",
            "family": "transcription",
            "fields": [
              {
                "description": null,
                "name": "text",
                "type": "string"
              },
              {
                "description": null,
                "name": "segments[]",
                "type": "object"
              },
              {
                "description": null,
                "name": "task_id",
                "type": "string"
              },
              {
                "description": null,
                "name": "asset_url",
                "type": "string"
              },
              {
                "description": null,
                "name": "usage",
                "type": "object"
              },
              {
                "description": null,
                "name": "segments[].speaker",
                "type": "string"
              },
              {
                "description": null,
                "name": "segments[].start",
                "type": "number"
              },
              {
                "description": null,
                "name": "segments[].end",
                "type": "number"
              }
            ],
            "format": "json",
            "owned_result_extra_fields": [
              "task_id",
              "asset_url"
            ],
            "preserve_original_json_fields": [
              "text",
              "task",
              "duration",
              "segments",
              "usage"
            ],
            "segment_fields": [
              "type",
              "text",
              "speaker",
              "start",
              "end",
              "id"
            ]
          }
        },
        "ctx": null,
        "declared_pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "dimensions": {
              "quoted_unit": "/ 1K audio tokens"
            },
            "label": "Ultra",
            "units": [
              {
                "amount": "0.012000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "audio_input_token",
                "label": "audio input token",
                "native_amount_usd_per_unit": "0.000012",
                "native_quantity": 1,
                "native_unit": "audio_input_token",
                "public_unit_label": "/ 1K audio tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "audio_input_token"
              }
            ]
          },
          {
            "dimensions": {
              "quoted_unit": "/ 1K audio tokens"
            },
            "label": "Ultra",
            "units": [
              {
                "amount": "0.02000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "audio_output_token",
                "label": "audio output token",
                "native_amount_usd_per_unit": "0.00002",
                "native_quantity": 1,
                "native_unit": "audio_output_token",
                "public_unit_label": "/ 1K audio tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "audio_output_token"
              }
            ]
          }
        ],
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_AUDIO_FILE:?Set the path to your actual MP3 recording}\"\nexport AILOOT_AUDIO_FILE\npython3 - <<'PY_REQUEST'\nimport os\nfrom pathlib import Path\np=Path(os.environ[\"AILOOT_AUDIO_FILE\"])\nif not p.is_file() or p.suffix.lower()!=\".mp3\":raise SystemExit(\"Choose an existing MP3 recording\")\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/audio/transcriptions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" \\\n  --form-string model=openai/gpt-4o-transcribe-diarize -F \"file=@$AILOOT_AUDIO_FILE\" --form-string response_format=diarized_json \\\n  -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text())))\nPY_RESULT\n",
            "label": "curl · exact retained creation",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\nexport AILOOT_API_KEY\npython3 - <<'PY_ASSETS'\nimport json,os,subprocess\nfrom pathlib import Path\nfrom urllib.parse import urljoin,urlsplit\nr=json.loads(Path('result.json').read_text())\nurls=[]\nif isinstance(r.get('asset_url'),str) and r['asset_url']:urls.append(('transcript',r['asset_url']))\nfor label,path in urls:\n    u=urljoin('https://api.ailoot.ai',path);z=urlsplit(u)\n    if z.scheme!='https' or z.netloc!='api.ailoot.ai' or z.username or z.password:raise SystemExit('Use the actual returned Ailoot owned content URL')\n    target=Path('owned-'+label+'.bin')\n    subprocess.run(['curl','--fail-with-body','--silent','--show-error',u,'-H','Authorization: Bearer '+os.environ['AILOOT_API_KEY'],'-D',str(target)+'.headers','-o',str(target)],check=True)\nprint('All returned owned URLs saved; complete metadata, timing and usage remain in the JSON.')\nPY_ASSETS\n",
            "label": "Save every returned owned transcript",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/media/assets \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -o media-assets.json\n",
            "label": "List actual media assets",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_MEDIA_TASK_ID:?Set the actual ID returned by the response or media-library metadata}\"\nexport AILOOT_MEDIA_TASK_ID\nresource_id=$(python3 -c 'import os,urllib.parse;print(urllib.parse.quote(os.environ[\"AILOOT_MEDIA_TASK_ID\"],safe=\"\"))')\ncurl --fail-with-body --silent --show-error \"https://api.ailoot.ai/v1/media/tasks/$resource_id\" \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -o media-task.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"media-task.json\").read_text())))\nPY_RESULT\n",
            "label": "Read actual media task",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_ASSET_ID:?Set the actual ID returned by the response or media-library metadata}\"\nexport AILOOT_ASSET_ID\nresource_id=$(python3 -c 'import os,urllib.parse;print(urllib.parse.quote(os.environ[\"AILOOT_ASSET_ID\"],safe=\"\"))')\ncurl --fail-with-body --silent --show-error \"https://api.ailoot.ai/v1/media/assets/$resource_id\" \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -o media-asset.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"media-asset.json\").read_text())))\nPY_RESULT\n",
            "label": "Read actual asset metadata",
            "language": "bash"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "transcriptions",
        "hints": [
          "Use actual recording and matching format.",
          "Preserve full transcript, segments, speaker IDs and timing."
        ],
        "http": "POST",
        "in": null,
        "input": [
          "audio"
        ],
        "label": "Распознавание речи",
        "max_out": null,
        "max_reasoning_effort_multiplier": null,
        "method_aliases": [
          "/audio/transcriptions"
        ],
        "out": null,
        "output": [
          "transcription"
        ],
        "path": "/v1/audio/transcriptions",
        "price_conditions": [
          {
            "label": "Fast mode",
            "value": "Not specified",
            "when": "When fast mode is selected"
          },
          {
            "label": "Flex mode",
            "value": "Not specified",
            "when": "When flex mode is selected"
          },
          {
            "label": "Maximum reasoning effort",
            "value": "Not specified",
            "when": "When maximum reasoning effort uses the default adjustment"
          }
        ],
        "pricing": {
          "billing_mode": "per_request",
          "image_input_price": null,
          "image_output_price": null,
          "per_request_price": null,
          "unit_prices": {
            "audio_input_token": 1.2e-05,
            "audio_output_token": 2e-05
          }
        },
        "pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "dimensions": {
              "quoted_unit": "/ 1K audio tokens"
            },
            "label": "Ultra",
            "units": [
              {
                "amount": "0.012000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "audio_input_token",
                "label": "audio input token",
                "native_amount_usd_per_unit": "0.000012",
                "native_quantity": 1,
                "native_unit": "audio_input_token",
                "public_unit_label": "/ 1K audio tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "audio_input_token"
              }
            ]
          },
          {
            "dimensions": {
              "quoted_unit": "/ 1K audio tokens"
            },
            "label": "Ultra",
            "units": [
              {
                "amount": "0.02000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "audio_output_token",
                "label": "audio output token",
                "native_amount_usd_per_unit": "0.00002",
                "native_quantity": 1,
                "native_unit": "audio_output_token",
                "public_unit_label": "/ 1K audio tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "audio_output_token"
              }
            ]
          }
        ],
        "request_model_id": "openai/gpt-4o-transcribe-diarize",
        "route_label": "Ultra",
        "status_reads": [
          "GET /v1/media/tasks/{task_id}",
          "GET /v1/media/assets/{asset_id}/content"
        ],
        "tiers": [],
        "units": [
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "input_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "output_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "output_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_read_price",
            "label": "Cache read",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "cached_input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "cached_input_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_price",
            "label": "Cache write",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "generic_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "generic_cache_creation_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_1h_price",
            "label": "Cache write, 1 hour",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "one_hour_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "one_hour_cache_creation_token"
          },
          {
            "amount": "0.012000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "audio_input_token",
            "label": "audio input token",
            "native_amount_usd_per_unit": "0.000012",
            "native_quantity": 1,
            "native_unit": "audio_input_token",
            "public_unit_label": "/ 1K audio tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "audio_input_token"
          },
          {
            "amount": "0.02000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "audio_output_token",
            "label": "audio output token",
            "native_amount_usd_per_unit": "0.00002",
            "native_quantity": 1,
            "native_unit": "audio_output_token",
            "public_unit_label": "/ 1K audio tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "audio_output_token"
          }
        ]
      }
    }
  ],
  "model_id": "openai/gpt-4o-transcribe-diarize",
  "nativeProvenance": {
    "input_facts_canonical_sha256": "808db0799f8fb6086aefaf73880a7ace9ee2dcb0fe24da2ecd4d92cc3e956c3d",
    "input_html_sha256": "ba06704a23cb0f22e55019b38802b7206114b333700100cce1ac7e3633d0e84c",
    "private_audit_sha256": "84226dfa66cdb47d6bc33d151a6ca626b0d4520db672630c06654f8ba46b3d99",
    "role": "historical-normalized-input-audit-hashes",
    "schema": "ailoot-native-model-provenance-v2"
  },
  "page": {
    "canonical": "https://ailoot.ai/models/sl/openai-gpt-4o-transcribe-diarize/",
    "description": "GPT-4o Transcribe Diarize pretvori posneti govor v besedilo s segmenti, označenimi po govorcih, in časovnimi podatki. Primeren je za sestanke, intervjuje in posnetke več oseb, pri katerih mora prepis pokazati, kdo je kdaj govoril, z izbirnimi kratkimi glasovnimi referencami za znane govorce.",
    "locale": "sl",
    "md_url": "https://ailoot.ai/models/sl/openai-gpt-4o-transcribe-diarize/index.md",
    "title": "gpt-4o-transcribe-diarize — Ailoot",
    "url": "https://ailoot.ai/models/sl/openai-gpt-4o-transcribe-diarize/"
  },
  "rawModel": {
    "about": "GPT-4o Transcribe Diarize je model OpenAI za samodejno prepoznavanje govora z vgrajeno diarizacijo govorcev. Prepisane zvočne segmente poveže z različnimi govorci v pogovoru. Uporaben rezultat je prepis, urejen po govorcih in času, namesto zgolj neprekinjenega bloka besed. Namenjen je posnetemu govoru, ki potrebuje oznake govorcev, na primer sestanku, intervjuju ali razpravi več oseb.\n\n### Pripravite dokončani posnetek\n\nPredložite posnetek za prepis. Dokumentirani datotečni potek sprejema MP3, MP4, MPEG, MPGA, M4A, WAV in WebM z omejitvijo velikosti datoteke 25 MB. Izvorni posnetek ohranite dostopen, da je mogoče posamezni govorčev prispevek, ime ali nejasno frazo preveriti glede na dejanski zvok.\n\nPri sestanku ohranite zaporedje pogovora, namesto da izrežete kratke premore, ki pomagajo razlikovati govorne odseke. Pri intervjuju vprašanje in odgovor ohranite skupaj, kadar naloga potrebuje njuno povezavo. Priprava zvoka mora zagotoviti slišnost govora, ne da bi odstranila informacije, pomembne za rezultat z označenimi govorci.\n\nTo je potek prepisa datoteke. Obdelava dokončanega posnetka in prepoznavanje zvočnega toka, ki še prihaja, sta različni nalogi; označevanje govorcev tega modela ni podprto v sejah prepisa Realtime.\n\n### Zahtevajte prepis z označenimi govorci\n\nIzhodni format `diarized_json` vrne segmente z identifikacijskimi oznakami govorcev ter začetnim in končnim časom. Vsak segment vsebuje tudi svoje prepisano besedilo. Ta polja ohranite skupaj, da je mogoče besede povezati z ustreznim delom posnetka.\n\nZa uporaben prepis sestanka ohranite zaporedje segmentov in besede vsakega govorca prikažite z njihovimi časovnimi podatki. Poznejša naloga lahko s tem prepisom pripravi zapisnik ali seznam nalog, diarizacija sama pa ne odloči, kaj je bilo na sestanku dogovorjeno, in ne ustvari preverjenega povzetka.\n\nOznake govorcev opisujejo modelovo združevanje govora. Preglejte prehode, pri katerih se ljudje prekinjajo, govorijo na kratko ali hkrati. Dobro strukturiran rezultat pomaga pri navigaciji in pregledu, posamezna pripisava pa lahko še vedno zahteva poslušanje izvirnega zvoka.\n\n### Reference znanih govorcev\n\nDokumentirani potek lahko sprejme do štirih poimenovanih referenc govorcev. Vsaka referenca je kratek zvočni izsek, dolg 2–10 sekund, v formatu, podprtem pri glavnem nalaganju. Imena in reference se predložijo skupaj, da je segmente mogoče povezati z znanimi govorci.\n\nPripravite referenco, ki jasno vsebuje predvidenega govorca, in njeno ime ohranite skladno s predvidenimi oznakami prepisa. Pri intervjuju lahko referenca voditelja pomaga urediti rezultat z označenimi govorci, ne da bi vsak udeleženec dobil anonimno oznako. Referenca je vhod za pripisovanje; ni splošna operacija kloniranja glasu ali dokaz identitete osebe.\n\nPoimenovanja govorca ne zamenjujte z urejanjem izgovorjenih besed. Uporaben izhod mora še vedno ohraniti vsebino posnetka in dejanski vrstni red govornih odsekov.\n\n### Delitev na dele in omejitve modela\n\nZa zvok, daljši od 30 sekund, proizvajalec zahteva strategijo delitve na dele, bodisi samodejno delitev bodisi konfiguracijo zaznavanja govorne aktivnosti. Ta zahteva ni največja dolžina posnetka. Opisuje, kako se daljši vhod razdeli za obdelavo.\n\nKartica modela navaja kontekstno okno 16000 tokenov in največ 2000 izhodnih tokenov. To so omejitve tokenov modela, ločene od omejitve nalaganja 25 MB v datotečnem poteku in praga delitve na dele. Ne smejo se pretvoriti v izmišljeno število minut, ki bi veljalo za vsak posnetek.\n\nPri sestavljanju ali pregledu daljšega prepisa ohranite časovne podatke in identiteto segmentov. Če je bil posnetek pred oddajo razdeljen, ohranite povezavo vsakega dela z izvirnim zvokom, da se lokalna časovna oznaka ne zamenja s položajem v celotnem pogovoru.\n\n### Pretočno podajanje dokončanih segmentov\n\nDatotečni potek prepisa lahko besedilo pretočno podaja med obdelavo posnetka. Pri pretočnem podajanju z označenimi govorci dokončani segmenti ustvarijo dogodke segmentov. Prirastki besedila vključujejo identifikator segmenta, ne vsebujejo pa delnih pripisav govorcev; govorec se določi, ko je segment dokončan.\n\nTa razlika je pomembna pri prikazu. Začasno besedilo in dokončani govorni odsek prikažite kot različni stanji, namesto da negotovo oznako govorca pripnete, preden model dokonča segment. Dokončani rezultat ohranite, kadar je prepis potreben za poznejše urejanje ali analizo.\n\n### Meje modela in izhoda\n\nTa profil je model za diarizacijo, ločen od običajnega prepisa GPT-4o, prepisa Mini, sinteze govora in modelov za pogovor v živo. Ne podpira pozivov za prepis; morebitni pregled terminologije ali popravek ohranite kot ločen korak, preverjen glede na izvirni zvok. Njegov proizvajalčev vmesnik je prepis posnetega zvoka v besedilo. Ne ustvari zvočnega odgovora in ne prevede posnetka prek ločenega poteka zvočnega prevajanja.\n\nUporabite ga za prepise, ki potrebujejo vsebino in strukturo govorcev. Imena, tehnične izraze, številke, meje govornih odsekov in pripisave preverite glede na posnetek. Ohranite zvok, izbrani format rezultata, reference in dokončani prepis, da lahko popravek obravnava konkretno frazo ali pripisavo govorca.",
    "alias_of": null,
    "aliases": [],
    "author": "OpenAI",
    "available": null,
    "canonical_model": "openai/gpt-4o-transcribe-diarize",
    "capabilities": {
      "context_length": 16000,
      "manufacturer_input": [],
      "manufacturer_output": []
    },
    "card_routes": [
      {
        "label": "Ultra",
        "rates": [
          {
            "amount": "0.012000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "audio_input_token",
            "label": "audio input token",
            "native_amount_usd_per_unit": "0.000012",
            "native_quantity": 1,
            "native_unit": "audio_input_token",
            "public_unit_label": "/ 1K audio tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "audio_input_token"
          },
          {
            "amount": "0.02000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "audio_output_token",
            "label": "audio output token",
            "native_amount_usd_per_unit": "0.00002",
            "native_quantity": 1,
            "native_unit": "audio_output_token",
            "public_unit_label": "/ 1K audio tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "audio_output_token"
          }
        ],
        "summary": "Celoten cenik konfiguracije je v podrobnostih."
      }
    ],
    "ctx": null,
    "entity_type": "model",
    "formats": [
      "transcriptions"
    ],
    "id": "openai/gpt-4o-transcribe-diarize",
    "input": [
      "audio"
    ],
    "kind": "unresolved_method_or_category",
    "max_out": null,
    "methods": [
      {
        "available": null,
        "cache_read": null,
        "cache_write": null,
        "cache_write_1h": null,
        "contract": {
          "data": {
            "all_results": "Retain complete JSON, not only text; preserve every available segment/speaker/timestamp and actual task/asset identity.",
            "errors": [
              {
                "code": null,
                "condition": "Neveljavna obvezna polja, predstavitev gradiva ali vrednost parametra",
                "http_status": 400,
                "recovery": "Pred novo zahtevo za ustvarjanje popravite navedena polja.",
                "type": "invalid_request_error"
              },
              {
                "code": null,
                "condition": "Vrnjeni odgovor navaja, da je treba operacijo ali rezultat preveriti",
                "http_status": null,
                "recovery": "Shranite izvirni vrnjeni ID operacije/opravila, glave zahteve in odgovor; nadaljujte s podprtimi branji te izvirne operacije. Zahteve za ustvarjanje ne pošiljajte znova.",
                "type": "server_error"
              }
            ],
            "hints": [],
            "ignored_fields": [],
            "lifecycle": {
              "all_results": "Follow everyactualreturnedoutputandownedasset; no result is discardedbecauseindex0orcontent_urlalreadyexists.",
              "assets": [
                {
                  "http": "GET",
                  "path": "/v1/media/assets"
                },
                {
                  "http": "GET",
                  "path": "/v1/media/assets/{asset_id}"
                }
              ],
              "content": [
                {
                  "http": "GET",
                  "path": "/v1/media/assets/{asset_id}/content",
                  "url_source": "exact returned signed URL; never construct token"
                }
              ],
              "mode": "synchronous_result_then_owned_library",
              "operation_id_is_not_task_id": true,
              "status": [
                {
                  "http": "GET",
                  "id_source": "actual returned task_id or media library record",
                  "path": "/v1/media/tasks/{task_id}"
                }
              ],
              "unknown": "Shranite izvirni operation_id/X-Client-Request-ID za uskladitev evidenc brez ponovnega pošiljanja; namenska pot za periodično preverjanje zvoka ne obstaja."
            },
            "limits": {
              "decoded_audio_max_bytes": 26214400
            },
            "material_combinations": [
              {
                "content_type": "multipart/form-data",
                "file_formats": [
                  "mp3"
                ],
                "maximum_seconds": 30,
                "mode": "diarized_transcription"
              }
            ],
            "media_library": {
              "asset": {
                "fields": [
                  {
                    "description": null,
                    "name": "asset_id",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "task_id",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "output_key",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "family",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "model",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "method",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "status",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "content_type",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "sha256",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "size_bytes",
                    "type": "integer"
                  },
                  {
                    "description": null,
                    "name": "content_url",
                    "type": "string"
                  }
                ],
                "http": "GET",
                "id_source": "actual returned asset_id",
                "path": "/v1/media/assets/{asset_id}"
              },
              "content": {
                "http": "GET",
                "path": "/v1/media/assets/{asset_id}/content",
                "range_header_supported": true,
                "url_source": "Use exact returned signed content_url including its token; do not construct a token."
              },
              "expired_link": {
                "code": "link_expired",
                "http_status": 404,
                "recovery": "Read the asset again to obtain its refreshed signed content_url, then fetch that URL. Do not regenerate."
              },
              "list": {
                "all_pages": "Follow every returned next_cursor, then select records by their actual task_id/output_key.",
                "http": "GET",
                "output_fields": [
                  {
                    "description": null,
                    "name": "object",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "data",
                    "type": "asset[]"
                  },
                  {
                    "description": null,
                    "name": "next_cursor",
                    "type": "string|null"
                  }
                ],
                "parameters": [
                  {
                    "availability": "source_interface",
                    "default": null,
                    "default_known": false,
                    "enum": null,
                    "enum_known": false,
                    "name": "family",
                    "required": false,
                    "type": "string"
                  },
                  {
                    "availability": "source_interface",
                    "default": null,
                    "default_known": false,
                    "enum": null,
                    "enum_known": false,
                    "name": "cursor",
                    "required": false,
                    "type": "string"
                  },
                  {
                    "availability": "source_interface",
                    "default": 20,
                    "default_known": true,
                    "enum": null,
                    "enum_known": false,
                    "maximum": 100,
                    "minimum": 1,
                    "name": "limit",
                    "required": false,
                    "type": "integer"
                  }
                ],
                "path": "/v1/media/assets"
              },
              "revoke": {
                "http": "DELETE",
                "meaning": "Revokes/deletes the existing owned file; this is not generation cancellation.",
                "path": "/v1/media/assets/{asset_id}",
                "pending_status": "revoking",
                "success_statuses": [
                  202,
                  204
                ]
              },
              "task": {
                "http": "GET",
                "id_source": "actual returned task_id or media library record; operation_id is not task_id",
                "path": "/v1/media/tasks/{task_id}"
              }
            },
            "operation_modes": [
              "diarized_transcription"
            ],
            "outputs": {
              "all_results": "Ohranite celoten JSON in ne samo besedila; ohranite vsak razpoložljivi segment/govorca/časovno oznako in dejansko identiteto opravila/sredstva.",
              "family": "transcription",
              "fields": [
                {
                  "description": null,
                  "name": "text",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "segments[]",
                  "type": "object"
                },
                {
                  "description": null,
                  "name": "task_id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "asset_url",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                },
                {
                  "description": null,
                  "name": "segments[].speaker",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "segments[].start",
                  "type": "number"
                },
                {
                  "description": null,
                  "name": "segments[].end",
                  "type": "number"
                }
              ],
              "format": "json"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "openai/gpt-4o-transcribe-diarize"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "file_extension": ".mp3",
                "maximum_bytes": 26214400,
                "maximum_seconds": 30,
                "mime_types": [
                  "audio/mpeg"
                ],
                "name": "file",
                "required": true,
                "type": "file"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "diarized_json"
                ],
                "enum_known": true,
                "name": "response_format",
                "required": true,
                "type": "string"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": [
              "JSONinput_audio",
              "nonMP3",
              "audioover30seconds",
              "otheroptions"
            ]
          },
          "hints": [
            "Uporabite dejanski posnetek in ustrezno obliko.",
            "Ohranite celoten prepis, segmente, ID-je govorcev in časovne podatke."
          ],
          "input": {
            "additional_properties": false,
            "content_type": "multipart/form-data",
            "file_formats": [
              "mp3"
            ],
            "form_string_maximum_bytes": 256,
            "material_types": [
              "audio"
            ],
            "max_audio_seconds": 30,
            "max_bytes": 26214400,
            "other_options": false,
            "required": [
              "model",
              "file",
              "response_format"
            ],
            "response_format": [
              "diarized_json"
            ]
          },
          "lifecycle": {
            "all_results": "Follow everyactualreturnedoutputandownedasset; no result is discardedbecauseindex0orcontent_urlalreadyexists.",
            "assets": [
              {
                "http": "GET",
                "path": "/v1/media/assets"
              },
              {
                "http": "GET",
                "path": "/v1/media/assets/{asset_id}"
              }
            ],
            "content": [
              {
                "http": "GET",
                "path": "/v1/media/assets/{asset_id}/content",
                "url_source": "exact returned signed URL; never construct token"
              }
            ],
            "mode": "synchronous_result_then_owned_library",
            "operation_id_is_not_task_id": true,
            "status": [
              {
                "http": "GET",
                "id_source": "Dejansko vrnjeni task_id ali zapis v medijski knjižnici",
                "path": "/v1/media/tasks/{task_id}"
              }
            ],
            "unknown": "Retain original operation_id/X-Client-Request-ID for reconciliation without resubmission; no dedicated audio poll route."
          },
          "method": {
            "http": "POST",
            "path": "/v1/audio/transcriptions"
          },
          "method_aliases": [
            "/audio/transcriptions"
          ],
          "operation_modes": [
            "diarized_transcription"
          ],
          "output": {
            "all_results": "Retain complete JSON, not only text; preserve every available segment/speaker/timestamp and actual task/asset identity.",
            "family": "transcription",
            "fields": [
              {
                "description": null,
                "name": "text",
                "type": "string"
              },
              {
                "description": null,
                "name": "segments[]",
                "type": "object"
              },
              {
                "description": null,
                "name": "task_id",
                "type": "string"
              },
              {
                "description": null,
                "name": "asset_url",
                "type": "string"
              },
              {
                "description": null,
                "name": "usage",
                "type": "object"
              },
              {
                "description": null,
                "name": "segments[].speaker",
                "type": "string"
              },
              {
                "description": null,
                "name": "segments[].start",
                "type": "number"
              },
              {
                "description": null,
                "name": "segments[].end",
                "type": "number"
              }
            ],
            "format": "json",
            "owned_result_extra_fields": [
              "task_id",
              "asset_url"
            ],
            "preserve_original_json_fields": [
              "text",
              "task",
              "duration",
              "segments",
              "usage"
            ],
            "segment_fields": [
              "type",
              "text",
              "speaker",
              "start",
              "end",
              "id"
            ]
          }
        },
        "ctx": null,
        "declared_pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "dimensions": {
              "quoted_unit": "/ 1K audio tokens"
            },
            "label": "Ultra",
            "units": [
              {
                "amount": "0.012000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "audio_input_token",
                "label": "audio input token",
                "native_amount_usd_per_unit": "0.000012",
                "native_quantity": 1,
                "native_unit": "audio_input_token",
                "public_unit_label": "/ 1K audio tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "audio_input_token"
              }
            ]
          },
          {
            "dimensions": {
              "quoted_unit": "/ 1K audio tokens"
            },
            "label": "Ultra",
            "units": [
              {
                "amount": "0.02000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "audio_output_token",
                "label": "audio output token",
                "native_amount_usd_per_unit": "0.00002",
                "native_quantity": 1,
                "native_unit": "audio_output_token",
                "public_unit_label": "/ 1K audio tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "audio_output_token"
              }
            ]
          }
        ],
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_AUDIO_FILE:?Set the path to your actual MP3 recording}\"\nexport AILOOT_AUDIO_FILE\npython3 - <<'PY_REQUEST'\nimport os\nfrom pathlib import Path\np=Path(os.environ[\"AILOOT_AUDIO_FILE\"])\nif not p.is_file() or p.suffix.lower()!=\".mp3\":raise SystemExit(\"Choose an existing MP3 recording\")\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/audio/transcriptions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" \\\n  --form-string model=openai/gpt-4o-transcribe-diarize -F \"file=@$AILOOT_AUDIO_FILE\" --form-string response_format=diarized_json \\\n  -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text())))\nPY_RESULT\n",
            "label": "curl · exact retained creation",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\nexport AILOOT_API_KEY\npython3 - <<'PY_ASSETS'\nimport json,os,subprocess\nfrom pathlib import Path\nfrom urllib.parse import urljoin,urlsplit\nr=json.loads(Path('result.json').read_text())\nurls=[]\nif isinstance(r.get('asset_url'),str) and r['asset_url']:urls.append(('transcript',r['asset_url']))\nfor label,path in urls:\n    u=urljoin('https://api.ailoot.ai',path);z=urlsplit(u)\n    if z.scheme!='https' or z.netloc!='api.ailoot.ai' or z.username or z.password:raise SystemExit('Use the actual returned Ailoot owned content URL')\n    target=Path('owned-'+label+'.bin')\n    subprocess.run(['curl','--fail-with-body','--silent','--show-error',u,'-H','Authorization: Bearer '+os.environ['AILOOT_API_KEY'],'-D',str(target)+'.headers','-o',str(target)],check=True)\nprint('All returned owned URLs saved; complete metadata, timing and usage remain in the JSON.')\nPY_ASSETS\n",
            "label": "Save every returned owned transcript",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/media/assets \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -o media-assets.json\n",
            "label": "List actual media assets",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_MEDIA_TASK_ID:?Set the actual ID returned by the response or media-library metadata}\"\nexport AILOOT_MEDIA_TASK_ID\nresource_id=$(python3 -c 'import os,urllib.parse;print(urllib.parse.quote(os.environ[\"AILOOT_MEDIA_TASK_ID\"],safe=\"\"))')\ncurl --fail-with-body --silent --show-error \"https://api.ailoot.ai/v1/media/tasks/$resource_id\" \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -o media-task.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"media-task.json\").read_text())))\nPY_RESULT\n",
            "label": "Read actual media task",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_ASSET_ID:?Set the actual ID returned by the response or media-library metadata}\"\nexport AILOOT_ASSET_ID\nresource_id=$(python3 -c 'import os,urllib.parse;print(urllib.parse.quote(os.environ[\"AILOOT_ASSET_ID\"],safe=\"\"))')\ncurl --fail-with-body --silent --show-error \"https://api.ailoot.ai/v1/media/assets/$resource_id\" \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -o media-asset.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"media-asset.json\").read_text())))\nPY_RESULT\n",
            "label": "Read actual asset metadata",
            "language": "bash"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "transcriptions",
        "hints": [
          "Use actual recording and matching format.",
          "Preserve full transcript, segments, speaker IDs and timing."
        ],
        "http": "POST",
        "in": null,
        "input": [
          "audio"
        ],
        "label": "Распознавание речи",
        "max_out": null,
        "max_reasoning_effort_multiplier": null,
        "method_aliases": [
          "/audio/transcriptions"
        ],
        "out": null,
        "output": [
          "transcription"
        ],
        "path": "/v1/audio/transcriptions",
        "price_conditions": [
          {
            "label": "Fast mode",
            "value": "Not specified",
            "when": "When fast mode is selected"
          },
          {
            "label": "Flex mode",
            "value": "Not specified",
            "when": "When flex mode is selected"
          },
          {
            "label": "Maximum reasoning effort",
            "value": "Not specified",
            "when": "When maximum reasoning effort uses the default adjustment"
          }
        ],
        "pricing": {
          "billing_mode": "per_request",
          "image_input_price": null,
          "image_output_price": null,
          "per_request_price": null,
          "unit_prices": {
            "audio_input_token": 1.2e-05,
            "audio_output_token": 2e-05
          }
        },
        "pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "dimensions": {
              "quoted_unit": "/ 1K audio tokens"
            },
            "label": "Ultra",
            "units": [
              {
                "amount": "0.012000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "audio_input_token",
                "label": "audio input token",
                "native_amount_usd_per_unit": "0.000012",
                "native_quantity": 1,
                "native_unit": "audio_input_token",
                "public_unit_label": "/ 1K audio tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "audio_input_token"
              }
            ]
          },
          {
            "dimensions": {
              "quoted_unit": "/ 1K audio tokens"
            },
            "label": "Ultra",
            "units": [
              {
                "amount": "0.02000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "audio_output_token",
                "label": "audio output token",
                "native_amount_usd_per_unit": "0.00002",
                "native_quantity": 1,
                "native_unit": "audio_output_token",
                "public_unit_label": "/ 1K audio tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "audio_output_token"
              }
            ]
          }
        ],
        "request_model_id": "openai/gpt-4o-transcribe-diarize",
        "route_label": "Ultra",
        "status_reads": [
          "GET /v1/media/tasks/{task_id}",
          "GET /v1/media/assets/{asset_id}/content"
        ],
        "tiers": [],
        "units": [
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "input_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "output_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "output_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_read_price",
            "label": "Cache read",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "cached_input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "cached_input_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_price",
            "label": "Cache write",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "generic_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "generic_cache_creation_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_1h_price",
            "label": "Cache write, 1 hour",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "one_hour_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "one_hour_cache_creation_token"
          },
          {
            "amount": "0.012000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "audio_input_token",
            "label": "audio input token",
            "native_amount_usd_per_unit": "0.000012",
            "native_quantity": 1,
            "native_unit": "audio_input_token",
            "public_unit_label": "/ 1K audio tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "audio_input_token"
          },
          {
            "amount": "0.02000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "audio_output_token",
            "label": "audio output token",
            "native_amount_usd_per_unit": "0.00002",
            "native_quantity": 1,
            "native_unit": "audio_output_token",
            "public_unit_label": "/ 1K audio tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "audio_output_token"
          }
        ]
      }
    ],
    "model_aliases": [
      {
        "canonical_model_id": "openai/gpt-4o-transcribe-diarize",
        "request_model_id": "openai/gpt-4o-transcribe-diarize",
        "route_label": "Ultra"
      }
    ],
    "name": "gpt-4o-transcribe-diarize",
    "price": {
      "in": null,
      "in_label": null,
      "out": 0.02,
      "out_label": "/ 1K audio tokens",
      "sort_in": null,
      "sort_out": 0.02,
      "varies": true
    },
    "pricing_profiles": [],
    "public_id": "openai/gpt-4o-transcribe-diarize",
    "short": "GPT-4o Transcribe Diarize pretvori posneti govor v besedilo s segmenti, označenimi po govorcih, in časovnimi podatki. Primeren je za sestanke, intervjuje in posnetke več oseb, pri katerih mora prepis pokazati, kdo je kdaj govoril, z izbirnimi kratkimi glasovnimi referencami za znane govorce."
  },
  "renderer_schema": {
    "method_order": "Original DTO methods order; every exact route/format/path/caller survives.",
    "prices": "Original public DTO fields and original native display HTML; no flattened or normalized offers."
  },
  "representation": "exact-public-dto-and-native-renderer-html",
  "representationNotes": {
    "current_reference": {
      "about_json_pointer": "/aboutHtml",
      "methods": [
        {
          "contract_json_pointer": "/methods/0/rawMethod/contract",
          "html_json_pointer": "/methods/0/html",
          "method_ordinal": 0
        }
      ],
      "role": "current-semantic-reference"
    },
    "raw_input": {
      "examples_role": "historical-input-not-current-ready-examples",
      "json_pointers": [
        "/rawModel",
        "/methods/0/rawMethod"
      ],
      "role": "historical-owner-input"
    },
    "schema": "ailoot-native-model-representations-v1"
  },
  "schema": "ailoot-static-model-facts-v1",
  "schema_version": 1,
  "shortText": "GPT-4o Transcribe Diarize pretvori posneti govor v besedilo s segmenti, označenimi po govorcih, in časovnimi podatki. Primeren je za sestanke, intervjuje in posnetke več oseb, pri katerih mora prepis pokazati, kdo je kdaj govoril, z izbirnimi kratkimi glasovnimi referencami za znane govorce.",
  "source": {
    "audit_sha256": "2e00086bcbfc28e64d0cebe97aa47c17d8d5618963027f8ffb9dc6123d7d25b1",
    "bridge_map_sha256": "1125275768b9636fc8461bc7da5061239a81ddfe508e2557843ca42c58ab0036",
    "raw_model_json_sha256": "07a3114e67d13893c35cca94f4fee50bcf63ba44b127b6e0c12a740a6359aac1",
    "renderer_sha256": "dcba2271c18b0f9570a8b166e8d1e3166f121e096a58609c3a46da31562a1bf2"
  },
  "sourceRevision": "a2d29c62b2c556447dbbd141cb43dac4cb3065c59549a9dd0585b0b1c1d72f16"
}