{ "aboutHtml": "

Živ govor z drobnimi zvočnimi podrobnostmi

Speech 2.8 HD je usmerjen v naraven in čist zven. Glavna značilnost generacije so zvočne oznake, ki omogočajo vključevanje pogovornih podrobnosti v govor: smeha, rahlega hihitanja, dihanja, vdiha, izdiha, vzdiha, kašlja, odkašljevanja in drugih kratkih zvokov. Pomagajo prenesti ritem in premore žive replike, ne da bi vsako poved spremenile v enakomerno napovedovalsko branje.

Oznake se vstavijo v besedilo v obliki, določeni za model: na primer (chuckle), (breath) in (sighs) označujejo ustrezna zvočna dejanja. Zmožnost zvočnih oznak velja prav za Speech 2.8. To so podrobnosti glasu znotraj sinteze govora in ne ustvarjanje ločene glasbene ali zvočne skladbe.

Barva glasu in čistost

Proizvajalec izpostavlja prenašanje značilnih lastnosti glasu: teksture, dihanja in načina izgovarjave. Zmožnosti družine vključujejo sintezo z že pripravljenim kloniranim glasom; ustvarjanje takšnega glasu je ločen proces. Pri Speech 2.8 je prenovljena tudi obdelava za zmanjševanje hrupa v ozadju in digitalnih popačenj.

Jeziki in izraznost

Speech 2.8 podpira 40 jezikov, vključno z ruščino. Proizvajalec posebej opisuje delo z medjezikovno izgovarjavo pri kitajsko-japonski kombinaciji. Takšen scenarij se nanaša na ohranjanje naravnega zvena pri uporabi različnih jezikov in ne na samodejno prevajanje besedila.

MiniMax predvideva izbiro glasu ter upravljanje tempa, glasnosti in višine tona. Hitrost se določi v razponu 0,5–2, glasnost je večja od 0 in do 10, sprememba višine pa od −12 do 12. Izbiro čustva lahko glede na pomen besedila prepustite modelu ali ga določite ročno: veselje, žalost, jeza, strah, gnus, presenečenje ali umirjenost.

Izgovarjavo lahko natančneje določite s slovarjem zamenjav in fonetičnim zapisom; predvideni so mednarodna fonetična abeceda, kitajski pinjin in japonske različice branja. Premori se določijo med izgovorjenimi odseki v razponu 0,01–99,99 sekunde. Trajanje premora se določi na dve decimalni mesti natančno; oznake se postavijo med izgovorjene odseke in ne druga za drugo. Takšne nastavitve omogočajo uskladitev zvena imen, kratic in dvoumnih besed z zamislijo govorne izvedbe.

Zvočni rezultat

Sinteza sprejema besedilo z manj kot 10 000 znaki. Za dolgo besedilo z več kot 3000 znaki proizvajalec priporoča pretočni izhod; predvideno je tudi pridobivanje končnega zvoka v celoti. Splošne nastavitve sinteze vključujejo MP3, PCM, FLAC, WAV, Opus in različice G.711 μ-law, mono ali stereo; razpoložljivi nabor formatov konkretne zahteve določajo sredstva Ailoot.

Ta kartica pretvarja besedilo v govorni zvok. Zmožnosti nastavljanja glasu opisujejo model MiniMax; ustvarjanje klona glasu, ločeni podnapisi in posebni načini povezovanja niso samodejno vključeni v zahtevo za govorno izvedbo.

Dodatne nastavitve zvoka vključujejo frekvence vzorčenja 8, 16, 22,05, 24, 32 in 44,1 kHz. Za MP3 je predvidena bitna hitrost 32, 64, 128 ali 256 kbit/s. Spreminjate lahko tudi barvo glasu in uporabite en učinek: prostoren odmev, odmev dvorane, telefonski zven ali robotski glas. Učinki spreminjanja glasu so pri pridobivanju zvoka v celoti podprti za MP3, WAV in FLAC, pri pretočnem izhodu pa samo za MP3. Formati G.711 μ-law uporabljajo frekvenco 8 kHz. Te zmožnosti veljajo za nastavitve sinteze MiniMax.

Proizvajalec predvideva sinhronizacijo govora z besedilom: časovne oznake po povedih, besedah ali besedah pri postopnem izhodu. Takšen rezultat pomaga uskladiti izgovarjavo s prikazom besedila. Ta dodatna zmožnost zahteva podporo ustreznemu formatu odgovora.

", "aboutText": "### Živ govor z drobnimi zvočnimi podrobnostmi\n\nSpeech 2.8 HD je usmerjen v naraven in čist zven. Glavna značilnost generacije so zvočne oznake, ki omogočajo vključevanje pogovornih podrobnosti v govor: smeha, rahlega hihitanja, dihanja, vdiha, izdiha, vzdiha, kašlja, odkašljevanja in drugih kratkih zvokov. Pomagajo prenesti ritem in premore žive replike, ne da bi vsako poved spremenile v enakomerno napovedovalsko branje.\n\nOznake se vstavijo v besedilo v obliki, določeni za model: na primer `(chuckle)`, `(breath)` in `(sighs)` označujejo ustrezna zvočna dejanja. Zmožnost zvočnih oznak velja prav za Speech 2.8. To so podrobnosti glasu znotraj sinteze govora in ne ustvarjanje ločene glasbene ali zvočne skladbe.\n\n### Barva glasu in čistost\n\nProizvajalec izpostavlja prenašanje značilnih lastnosti glasu: teksture, dihanja in načina izgovarjave. Zmožnosti družine vključujejo sintezo z že pripravljenim kloniranim glasom; ustvarjanje takšnega glasu je ločen proces. Pri Speech 2.8 je prenovljena tudi obdelava za zmanjševanje hrupa v ozadju in digitalnih popačenj.\n\n### Jeziki in izraznost\n\nSpeech 2.8 podpira **40 jezikov**, vključno z ruščino. Proizvajalec posebej opisuje delo z medjezikovno izgovarjavo pri kitajsko-japonski kombinaciji. Takšen scenarij se nanaša na ohranjanje naravnega zvena pri uporabi različnih jezikov in ne na samodejno prevajanje besedila.\n\nMiniMax predvideva izbiro glasu ter upravljanje tempa, glasnosti in višine tona. Hitrost se določi v razponu **0,5–2**, glasnost je večja od 0 in do **10**, sprememba višine pa od **−12 do 12**. Izbiro čustva lahko glede na pomen besedila prepustite modelu ali ga določite ročno: veselje, žalost, jeza, strah, gnus, presenečenje ali umirjenost.\n\nIzgovarjavo lahko natančneje določite s slovarjem zamenjav in fonetičnim zapisom; predvideni so mednarodna fonetična abeceda, kitajski pinjin in japonske različice branja. Premori se določijo med izgovorjenimi odseki v razponu **0,01–99,99 sekunde**. Trajanje premora se določi na dve decimalni mesti natančno; oznake se postavijo med izgovorjene odseke in ne druga za drugo. Takšne nastavitve omogočajo uskladitev zvena imen, kratic in dvoumnih besed z zamislijo govorne izvedbe.\n\n### Zvočni rezultat\n\nSinteza sprejema besedilo z manj kot **10 000 znaki**. Za dolgo besedilo z več kot 3000 znaki proizvajalec priporoča pretočni izhod; predvideno je tudi pridobivanje končnega zvoka v celoti. Splošne nastavitve sinteze vključujejo MP3, PCM, FLAC, WAV, Opus in različice G.711 μ-law, mono ali stereo; razpoložljivi nabor formatov konkretne zahteve določajo sredstva Ailoot.\n\nTa kartica pretvarja besedilo v govorni zvok. Zmožnosti nastavljanja glasu opisujejo model MiniMax; ustvarjanje klona glasu, ločeni podnapisi in posebni načini povezovanja niso samodejno vključeni v zahtevo za govorno izvedbo.\n\nDodatne nastavitve zvoka vključujejo frekvence vzorčenja **8, 16, 22,05, 24, 32 in 44,1 kHz**. Za MP3 je predvidena bitna hitrost **32, 64, 128 ali 256 kbit/s**. Spreminjate lahko tudi barvo glasu in uporabite en učinek: prostoren odmev, odmev dvorane, telefonski zven ali robotski glas. Učinki spreminjanja glasu so pri pridobivanju zvoka v celoti podprti za MP3, WAV in FLAC, pri pretočnem izhodu pa samo za MP3. Formati G.711 μ-law uporabljajo frekvenco 8 kHz. Te zmožnosti veljajo za nastavitve sinteze MiniMax.\n\nProizvajalec predvideva sinhronizacijo govora z besedilom: časovne oznake po povedih, besedah ali besedah pri postopnem izhodu. Takšen rezultat pomaga uskladiti izgovarjavo s prikazom besedila. Ta dodatna zmožnost zahteva podporo ustreznemu formatu odgovora.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "1e1ea9d1a28ca7e5fdabd09de69fcd1b94f68201584844adf68aa0528f148a21", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "sl", "methods": [ { "html": "
MM

MiniMax: Speech 2.8 HD

MiniMax /minimax/speech-2.8-hd

Začetek

Speech 2.8 HD sintetizira izrazen govor z upravljanjem čustev in zvočnimi podrobnostmi, kot sta dihanje in smeh.

Dovoljeni vhodi
Besedilo
Rezultati
Zvok
O modelu

Ta opis zajema zmožnosti modela. Vhodi, izhodi in možnosti, ki so na voljo v Ailoot, so spodaj navedeni za izbrano metodo.

Živ govor z drobnimi zvočnimi podrobnostmi

Speech 2.8 HD je usmerjen v naraven in čist zven. Glavna značilnost generacije so zvočne oznake, ki omogočajo vključevanje pogovornih podrobnosti v govor: smeha, rahlega hihitanja, dihanja, vdiha, izdiha, vzdiha, kašlja, odkašljevanja in drugih kratkih zvokov. Pomagajo prenesti ritem in premore žive replike, ne da bi vsako poved spremenile v enakomerno napovedovalsko branje.

Oznake se vstavijo v besedilo v obliki, določeni za model: na primer (chuckle), (breath) in (sighs) označujejo ustrezna zvočna dejanja. Zmožnost zvočnih oznak velja prav za Speech 2.8. To so podrobnosti glasu znotraj sinteze govora in ne ustvarjanje ločene glasbene ali zvočne skladbe.

Barva glasu in čistost

Proizvajalec izpostavlja prenašanje značilnih lastnosti glasu: teksture, dihanja in načina izgovarjave. Zmožnosti družine vključujejo sintezo z že pripravljenim kloniranim glasom; ustvarjanje takšnega glasu je ločen proces. Pri Speech 2.8 je prenovljena tudi obdelava za zmanjševanje hrupa v ozadju in digitalnih popačenj.

Jeziki in izraznost

Speech 2.8 podpira 40 jezikov, vključno z ruščino. Proizvajalec posebej opisuje delo z medjezikovno izgovarjavo pri kitajsko-japonski kombinaciji. Takšen scenarij se nanaša na ohranjanje naravnega zvena pri uporabi različnih jezikov in ne na samodejno prevajanje besedila.

MiniMax predvideva izbiro glasu ter upravljanje tempa, glasnosti in višine tona. Hitrost se določi v razponu 0,5–2, glasnost je večja od 0 in do 10, sprememba višine pa od −12 do 12. Izbiro čustva lahko glede na pomen besedila prepustite modelu ali ga določite ročno: veselje, žalost, jeza, strah, gnus, presenečenje ali umirjenost.

Izgovarjavo lahko natančneje določite s slovarjem zamenjav in fonetičnim zapisom; predvideni so mednarodna fonetična abeceda, kitajski pinjin in japonske različice branja. Premori se določijo med izgovorjenimi odseki v razponu 0,01–99,99 sekunde. Trajanje premora se določi na dve decimalni mesti natančno; oznake se postavijo med izgovorjene odseke in ne druga za drugo. Takšne nastavitve omogočajo uskladitev zvena imen, kratic in dvoumnih besed z zamislijo govorne izvedbe.

Zvočni rezultat

Sinteza sprejema besedilo z manj kot 10 000 znaki. Za dolgo besedilo z več kot 3000 znaki proizvajalec priporoča pretočni izhod; predvideno je tudi pridobivanje končnega zvoka v celoti. Splošne nastavitve sinteze vključujejo MP3, PCM, FLAC, WAV, Opus in različice G.711 μ-law, mono ali stereo; razpoložljivi nabor formatov konkretne zahteve določajo sredstva Ailoot.

Ta kartica pretvarja besedilo v govorni zvok. Zmožnosti nastavljanja glasu opisujejo model MiniMax; ustvarjanje klona glasu, ločeni podnapisi in posebni načini povezovanja niso samodejno vključeni v zahtevo za govorno izvedbo.

Dodatne nastavitve zvoka vključujejo frekvence vzorčenja 8, 16, 22,05, 24, 32 in 44,1 kHz. Za MP3 je predvidena bitna hitrost 32, 64, 128 ali 256 kbit/s. Spreminjate lahko tudi barvo glasu in uporabite en učinek: prostoren odmev, odmev dvorane, telefonski zven ali robotski glas. Učinki spreminjanja glasu so pri pridobivanju zvoka v celoti podprti za MP3, WAV in FLAC, pri pretočnem izhodu pa samo za MP3. Formati G.711 μ-law uporabljajo frekvenco 8 kHz. Te zmožnosti veljajo za nastavitve sinteze MiniMax.

Proizvajalec predvideva sinhronizacijo govora z besedilom: časovne oznake po povedih, besedah ali besedah pri postopnem izhodu. Takšen rezultat pomaga uskladiti izgovarjavo s prikazom besedila. Ta dodatna zmožnost zahteva podporo ustreznemu formatu odgovora.

Na voljo v Ailoot · vhodi in metode

Ailoot Ultra · Pretvorba v govor POST /v1/audio/speech
Vhod
text
Izhod
audio
Izhodni format
mp3
PoljeVrstaZahtevaVrednosti in omejitvePrivzeto
PoljemodelVrstastringZahtevaObveznoVrednosti in omejitve
minimax/speech-2.8-hd
Privzeto—
PoljeinputVrstastringZahtevaObveznoVrednosti in omejitve
Najmanjša dolžina: 1
Enota: znaki Unicode
Privzeto—
PoljevoiceVrstastringZahtevaObveznoVrednosti in omejitve
English_expressive_narrator, English_radiant_girl, English_magnetic_voiced_man, English_compelling_lady1, English_Aussie_Bloke, English_captivating_female1, English_Upbeat_Woman, English_Trustworth_Man, English_CalmWoman, English_UpsetGirl, English_Gentle-voiced_man, English_Whispering_girl, English_Diligent_Man, English_Graceful_Lady, English_ReservedYoungMan, English_PlayfulGirl, English_ManWithDeepVoice, English_MaturePartner, English_FriendlyPerson, English_MatureBoss, English_Debator, English_LovelyGirl, English_Steadymentor, English_Deep-VoicedGentleman, English_Wiselady, English_CaptivatingStoryteller, English_DecentYoungMan, English_SentimentalLady, English_ImposingManner, English_SadTeen, English_PassionateWarrior, English_WiseScholar, English_Soft-spokenGirl, English_SereneWoman, English_ConfidentWoman, English_PatientMan, English_Comedian, English_BossyLeader, English_Strong-WilledBoy, English_StressedLady, English_AssertiveQueen, English_AnimeCharacter, English_Jovialman, English_WhimsicalGirl, English_Kind-heartedGirl
Privzeto—
Poljeresponse_formatVrstastringZahtevaObveznoVrednosti in omejitve
mp3
Privzeto—
Kombinacije vhodnih gradiv

text_to_speech · Obvezno: input

Parametri in življenjski cikel metode
ParameterSpecifikacija
Parametercontent_typeSpecifikacijaapplication/json
ParameterrequiredSpecifikacijamodel, input, voice, response_format
Parametervoice_idsSpecifikacijaEnglish_expressive_narrator, English_radiant_girl, English_magnetic_voiced_man, English_compelling_lady1, English_Aussie_Bloke, English_captivating_female1, English_Upbeat_Woman, English_Trustworth_Man, English_CalmWoman, English_UpsetGirl, English_Gentle-voiced_man, English_Whispering_girl, English_Diligent_Man, English_Graceful_Lady, English_ReservedYoungMan, English_PlayfulGirl, English_ManWithDeepVoice, English_MaturePartner, English_FriendlyPerson, English_MatureBoss, English_Debator, English_LovelyGirl, English_Steadymentor, English_Deep-VoicedGentleman, English_Wiselady, English_CaptivatingStoryteller, English_DecentYoungMan, English_SentimentalLady, English_ImposingManner, English_SadTeen, English_PassionateWarrior, English_WiseScholar, English_Soft-spokenGirl, English_SereneWoman, English_ConfidentWoman, English_PatientMan, English_Comedian, English_BossyLeader, English_Strong-WilledBoy, English_StressedLady, English_AssertiveQueen, English_AnimeCharacter, English_Jovialman, English_WhimsicalGirl, English_Kind-heartedGirl
Parameterresponse_formatSpecifikacijamp3
Parametermax_input_charactersSpecifikacijanull
Parameterother_optionsSpecifikacijafalse
ParameterinputSpecifikacijanatančno besedilo UTF-8; število znakov Unicode brez normalizacije
Parametermaterial_typesSpecifikacijatext

Življenjski cikel: synchronous_result_then_owned_library

GET /v1/media/tasks/{task_id} · Dejansko vrnjeni task_id ali zapis v medijski knjižnici

GET /v1/media/assets/{asset_id}/content

GET /v1/media/assets

GET /v1/media/assets/{asset_id}

Izberite natančen glas iz profila tega modela.

Vhodni znaki in zvočne sekunde so različni merili porabe.

Cenik

Tarifni podatki ne dodajajo možnosti zahteve. Podprti parametri so navedeni pri izbrani metodi.

Hitri način
Ni navedeno Ko je izbran hitri način
Način flex
Ni navedeno Ko je izbran način flex
Najvišja raven razmišljanja
Ni navedeno Ko najvišja raven razmišljanja uporablja privzeto prilagoditev (default)

Cene Ailoot

Cene po nastavitvah

Vsak strošek povežite s prikazanimi pogoji. Za vsak nabor alternativnih nastavitev uporabite eno ceno.

NastavitevCenovna lestvicaObračunana količinaObračunska enotaStrošek
NastavitevOsnovne cene žetonovCenovna lestvicaOsnovna cenaObračunana količina—Obračunska enota—Strošek
Vhod · Vhodni žetoni — / 1K žetonov
Izhod · Izhodni žetoni — / 1K žetonov
Vhod · Branje predpomnilnika — / 1K žetonov
Vhod · Zapis v predpomnilnik — / 1K žetonov
Vhod · Zapis v predpomnilnik, 1 ura — / 1K žetonov
NastavitevUltraCenovna lestvica—Obračunana količinaVsaka kodna točka Unicode šteje kot en znak, vključno z znaki Han.Obračunska enotana 1K vhodnih znakovStrošek
Vhod · vhodni znak $0.2 na 1K vhodnih znakov

Podrobnosti referenčne tarife

Referenčne lestvice modela ne spreminjajo izbire metode, ocen cen ali stroškov. Veljavni stroški uporabljajo cene izbrane metode Ailoot.

MiniMax: Speech 2.8 HD

Cene po nastavitvah

NastavitevObračunski pogojiStrošek
NastavitevMiniMax: Speech 2.8 HD · Privzeta konfiguracijaObračunski pogojiPrivzeta konfiguracijaStrošek
Vhod · Vhodni znaki 0,0002 $ na vhodni znak

Ailoot pred zahtevo rezervira ocenjeni znesek. Po rezultatu obračuna končni strošek na podlagi izmerjene porabe. Obračun pretakanja uporablja končni zapis porabe. Kako delujeta rezervacija in obračun →

Primeri zahtev

Ailoot Ultra · Pretvorba v govor

set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_VOICE_ID:?Choose an accepted voice ID from this exact model profile}"\nexport AILOOT_VOICE_ID\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "minimax/speech-2.8-hd", "input": "Good afternoon! This is a short voice take."}')\nvoice=os.environ["AILOOT_VOICE_ID"]\nallowed=json.loads('["English_expressive_narrator", "English_radiant_girl", "English_magnetic_voiced_man", "English_compelling_lady1", "English_Aussie_Bloke", "English_captivating_female1", "English_Upbeat_Woman", "English_Trustworth_Man", "English_CalmWoman", "English_UpsetGirl", "English_Gentle-voiced_man", "English_Whispering_girl", "English_Diligent_Man", "English_Graceful_Lady", "English_ReservedYoungMan", "English_PlayfulGirl", "English_ManWithDeepVoice", "English_MaturePartner", "English_FriendlyPerson", "English_MatureBoss", "English_Debator", "English_LovelyGirl", "English_Steadymentor", "English_Deep-VoicedGentleman", "English_Wiselady", "English_CaptivatingStoryteller", "English_DecentYoungMan", "English_SentimentalLady", "English_ImposingManner", "English_SadTeen", "English_PassionateWarrior", "English_WiseScholar", "English_Soft-spokenGirl", "English_SereneWoman", "English_ConfidentWoman", "English_PatientMan", "English_Comedian", "English_BossyLeader", "English_Strong-WilledBoy", "English_StressedLady", "English_AssertiveQueen", "English_AnimeCharacter", "English_Jovialman", "English_WhimsicalGirl", "English_Kind-heartedGirl"]')\nif voice not in allowed: raise SystemExit("Choose an accepted voice ID from this exact model profile")\np["voice"]=voice\np["response_format"]="mp3"\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/audio/speech \\\n  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o speech.mp3\n

Prejmi in shrani rezultate

Ailoot Ultra · Pretvorba v govor

mp3

Branje druge vsebine
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
Ohrani vse dokončane rezultate

Shranite vsak v celoti vrnjen odgovor, datoteko in del vsebine.

Shranite celoten binarni rezultat in glave. Če so vrnjeni podatki JSON ali več izhodov, shranite vsak podatkovni element in pridobite vsebino z vsakega dejanskega podpisanega URL datoteke.

Če je treba preveriti izvirni odgovor

Shranite izvirni operation_id/X-Client-Request-ID za uskladitev evidenc brez ponovnega pošiljanja; namenska pot za periodično preverjanje zvoka ne obstaja.

Polja odgovora
PoljeVrsta
Poljebinary audioVrstabytes
Poljeresponse headersVrstaheaders
Napake in naslednji koraki
OdgovorPogojNaslednji korak
Odgovor400 · invalid_request_errorPogojNeveljavna obvezna polja, predstavitev gradiva ali vrednost parametraNaslednji korakPred novo zahtevo za ustvarjanje popravite navedena polja.
Odgovorserver_errorPogojVrnjeni odgovor navaja, da je treba operacijo ali rezultat preveritiNaslednji korakShranite izvirni vrnjeni ID operacije/opravila, glave zahteve in odgovor; nadaljujte s podprtimi branji te izvirne operacije. Zahteve za ustvarjanje ne pošiljajte znova.

Druga imena

Druga imena modelov

Ailoot Ultra minimax/speech-2.8-hd

Druga imena poti metod

Uporabite zgoraj navedene poti metod.

Povezani ID-ji za klic

minimax/speech-2.8-hd

", "method_identity": { "effective_request_model_id": "minimax/speech-2.8-hd", "fmt": "speech", "http": "POST", "path": "/v1/audio/speech", "request_model_id": "minimax/speech-2.8-hd", "route_label": "Ultra" }, "method_key": "Ultra|speech|/v1/audio/speech|minimax%2Fspeech-2.8-hd", "ordinal": 0, "rawMethod": { "available": null, "cache_read": null, "cache_write": null, "cache_write_1h": null, "contract": { "data": { "all_results": "Keep the complete binary result and headers. If JSON/multiple outputs are returned, retain every data item and fetch each actual signed asset URL.", "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." }, "material_combinations": [ { "content_type": "application/json", "mode": "text_to_speech", "required": [ "input" ] } ], "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": [ "text_to_speech" ], "outputs": { "all_results": "Shranite celoten binarni rezultat in glave. Če so vrnjeni podatki JSON ali več izhodov, shranite vsak podatkovni element in pridobite vsebino z vsakega dejanskega podpisanega URL datoteke.", "family": "audio", "fields": [ { "description": null, "name": "binary audio", "type": "bytes" }, { "description": null, "name": "response headers", "type": "headers" } ], "format": "mp3", "http_success": 200 }, "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "minimax/speech-2.8-hd" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "limit_known": false, "maximum_length": null, "min_length": 1, "name": "input", "required": true, "type": "string", "unit": "znaki Unicode" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "English_expressive_narrator", "English_radiant_girl", "English_magnetic_voiced_man", "English_compelling_lady1", "English_Aussie_Bloke", "English_captivating_female1", "English_Upbeat_Woman", "English_Trustworth_Man", "English_CalmWoman", "English_UpsetGirl", "English_Gentle-voiced_man", "English_Whispering_girl", "English_Diligent_Man", "English_Graceful_Lady", "English_ReservedYoungMan", "English_PlayfulGirl", "English_ManWithDeepVoice", "English_MaturePartner", "English_FriendlyPerson", "English_MatureBoss", "English_Debator", "English_LovelyGirl", "English_Steadymentor", "English_Deep-VoicedGentleman", "English_Wiselady", "English_CaptivatingStoryteller", "English_DecentYoungMan", "English_SentimentalLady", "English_ImposingManner", "English_SadTeen", "English_PassionateWarrior", "English_WiseScholar", "English_Soft-spokenGirl", "English_SereneWoman", "English_ConfidentWoman", "English_PatientMan", "English_Comedian", "English_BossyLeader", "English_Strong-WilledBoy", "English_StressedLady", "English_AssertiveQueen", "English_AnimeCharacter", "English_Jovialman", "English_WhimsicalGirl", "English_Kind-heartedGirl" ], "enum_known": true, "name": "voice", "required": true, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "mp3" ], "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": [ "every field outside exactmodel,input,voice,response_format", "stream/speed/reference speech options" ] }, "hints": [ "Izberite natančen glas iz profila tega modela.", "Vhodni znaki in zvočne sekunde so različni merili porabe." ], "input": { "content_type": "application/json", "input": "natančno besedilo UTF-8; število znakov Unicode brez normalizacije", "material_types": [ "text" ], "max_input_characters": null, "other_options": false, "required": [ "model", "input", "voice", "response_format" ], "response_format": [ "mp3" ], "voice_ids": [ "English_expressive_narrator", "English_radiant_girl", "English_magnetic_voiced_man", "English_compelling_lady1", "English_Aussie_Bloke", "English_captivating_female1", "English_Upbeat_Woman", "English_Trustworth_Man", "English_CalmWoman", "English_UpsetGirl", "English_Gentle-voiced_man", "English_Whispering_girl", "English_Diligent_Man", "English_Graceful_Lady", "English_ReservedYoungMan", "English_PlayfulGirl", "English_ManWithDeepVoice", "English_MaturePartner", "English_FriendlyPerson", "English_MatureBoss", "English_Debator", "English_LovelyGirl", "English_Steadymentor", "English_Deep-VoicedGentleman", "English_Wiselady", "English_CaptivatingStoryteller", "English_DecentYoungMan", "English_SentimentalLady", "English_ImposingManner", "English_SadTeen", "English_PassionateWarrior", "English_WiseScholar", "English_Soft-spokenGirl", "English_SereneWoman", "English_ConfidentWoman", "English_PatientMan", "English_Comedian", "English_BossyLeader", "English_Strong-WilledBoy", "English_StressedLady", "English_AssertiveQueen", "English_AnimeCharacter", "English_Jovialman", "English_WhimsicalGirl", "English_Kind-heartedGirl" ] }, "lifecycle": { "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." }, "manufacturer_capability": null, "method": { "http": "POST", "path": "/v1/audio/speech" }, "method_aliases": [], "operation_modes": [ "text_to_speech" ], "output": { "family": "audio", "format": "mp3", "http_success": 200, "response": "full binary MP3 plus response headers", "result": "complete playable owned MP3" } }, "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": { "quantity_meter": "utf8.RuneCountInString(validUTF8): one Han codepoint=1; no Han weighting", "quoted_unit": "per 1000 input character" }, "label": "Ultra", "units": [ { "amount": "0.2000", "amount_unit": "usd_per_1000_characters", "billing_input": true, "estimate_only": false, "key": "audio_input_character", "label": "input character", "native_amount_usd_per_unit": "0.0002", "native_quantity": 1, "public_unit_label": "per 1000 input character", "quantity": "1000", "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_character" } ] } ], "declared_tariff_references": [ { "client_selectable": false, "key": "811df870581b3a6d28c7", "label": "MiniMax: Speech 2.8 HD", "profiles": [ { "basis": "", "dimensions": { "conditions": "Privzeta konfiguracija" }, "label": "MiniMax: Speech 2.8 HD · Privzeta konfiguracija", "units": [ { "amount": "0.0002", "amount_unit": "usd_per_exact_physical_unit", "billing_input": false, "key": "3075a39a90ece77c41dc1677", "label": "Input characters", "public_unit_label": "per input character", "quantity": "1", "rate_role": "declared_tariff_rate", "side": "in", "unit": "input_character" } ] } ] } ], "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_VOICE_ID:?Choose an accepted voice ID from this exact model profile}\"\nexport AILOOT_VOICE_ID\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"minimax/speech-2.8-hd\", \"input\": \"Good afternoon! This is a short voice take.\"}')\nvoice=os.environ[\"AILOOT_VOICE_ID\"]\nallowed=json.loads('[\"English_expressive_narrator\", \"English_radiant_girl\", \"English_magnetic_voiced_man\", \"English_compelling_lady1\", \"English_Aussie_Bloke\", \"English_captivating_female1\", \"English_Upbeat_Woman\", \"English_Trustworth_Man\", \"English_CalmWoman\", \"English_UpsetGirl\", \"English_Gentle-voiced_man\", \"English_Whispering_girl\", \"English_Diligent_Man\", \"English_Graceful_Lady\", \"English_ReservedYoungMan\", \"English_PlayfulGirl\", \"English_ManWithDeepVoice\", \"English_MaturePartner\", \"English_FriendlyPerson\", \"English_MatureBoss\", \"English_Debator\", \"English_LovelyGirl\", \"English_Steadymentor\", \"English_Deep-VoicedGentleman\", \"English_Wiselady\", \"English_CaptivatingStoryteller\", \"English_DecentYoungMan\", \"English_SentimentalLady\", \"English_ImposingManner\", \"English_SadTeen\", \"English_PassionateWarrior\", \"English_WiseScholar\", \"English_Soft-spokenGirl\", \"English_SereneWoman\", \"English_ConfidentWoman\", \"English_PatientMan\", \"English_Comedian\", \"English_BossyLeader\", \"English_Strong-WilledBoy\", \"English_StressedLady\", \"English_AssertiveQueen\", \"English_AnimeCharacter\", \"English_Jovialman\", \"English_WhimsicalGirl\", \"English_Kind-heartedGirl\"]')\nif voice not in allowed: raise SystemExit(\"Choose an accepted voice ID from this exact model profile\")\np[\"voice\"]=voice\np[\"response_format\"]=\"mp3\"\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/audio/speech \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o speech.mp3\n", "label": "curl", "language": "bash" }, { "code": "set -eu\n: \"${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": "speech", "hints": [ "Select exact voice from this model profile.", "Input characters and audio seconds are different meters." ], "http": "POST", "in": null, "input": [ "text" ], "label": "Озвучка текста", "max_out": null, "max_reasoning_effort_multiplier": null, "method_aliases": [], "out": null, "output": [ "audio" ], "path": "/v1/audio/speech", "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_character": 0.0002 } }, "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": { "quantity_meter": "utf8.RuneCountInString(validUTF8): one Han codepoint=1; no Han weighting", "quoted_unit": "per 1000 input character" }, "label": "Ultra", "units": [ { "amount": "0.2000", "amount_unit": "usd_per_1000_characters", "billing_input": true, "estimate_only": false, "key": "audio_input_character", "label": "input character", "native_amount_usd_per_unit": "0.0002", "native_quantity": 1, "public_unit_label": "per 1000 input character", "quantity": "1000", "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_character" } ] } ], "request_model_id": "minimax/speech-2.8-hd", "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": "0.2000", "amount_unit": "usd_per_1000_characters", "billing_input": true, "estimate_only": false, "key": "audio_input_character", "label": "input character", "native_amount_usd_per_unit": "0.0002", "native_quantity": 1, "public_unit_label": "per 1000 input character", "quantity": "1000", "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_character" } ] } } ], "model_id": "minimax/speech-2.8-hd", "nativeProvenance": { "input_facts_canonical_sha256": "4af2e7e02c35d2ef4bb3b020ea78a7bedebe4409320d75210d135d4f85fb93a5", "input_html_sha256": "b86f6f78fd92b321e3b4995b8f359c10832535bf814d78db7a46382a49ad8b86", "private_audit_sha256": "c1a817a1e72e6021bb5642ef0686685f005da308dbf94f4ce6f50d4ad2b27540", "role": "historical-normalized-input-audit-hashes", "schema": "ailoot-native-model-provenance-v2" }, "page": { "canonical": "https://ailoot.ai/models/sl/minimax-speech-2-8-hd/", "description": "Speech 2.8 HD sintetizira izrazen govor z upravljanjem čustev in zvočnimi podrobnostmi, kot sta dihanje in smeh.", "locale": "sl", "md_url": "https://ailoot.ai/models/sl/minimax-speech-2-8-hd/index.md", "title": "MiniMax: Speech 2.8 HD — Ailoot", "url": "https://ailoot.ai/models/sl/minimax-speech-2-8-hd/" }, "rawModel": { "about": "### Živ govor z drobnimi zvočnimi podrobnostmi\n\nSpeech 2.8 HD je usmerjen v naraven in čist zven. Glavna značilnost generacije so zvočne oznake, ki omogočajo vključevanje pogovornih podrobnosti v govor: smeha, rahlega hihitanja, dihanja, vdiha, izdiha, vzdiha, kašlja, odkašljevanja in drugih kratkih zvokov. Pomagajo prenesti ritem in premore žive replike, ne da bi vsako poved spremenile v enakomerno napovedovalsko branje.\n\nOznake se vstavijo v besedilo v obliki, določeni za model: na primer `(chuckle)`, `(breath)` in `(sighs)` označujejo ustrezna zvočna dejanja. Zmožnost zvočnih oznak velja prav za Speech 2.8. To so podrobnosti glasu znotraj sinteze govora in ne ustvarjanje ločene glasbene ali zvočne skladbe.\n\n### Barva glasu in čistost\n\nProizvajalec izpostavlja prenašanje značilnih lastnosti glasu: teksture, dihanja in načina izgovarjave. Zmožnosti družine vključujejo sintezo z že pripravljenim kloniranim glasom; ustvarjanje takšnega glasu je ločen proces. Pri Speech 2.8 je prenovljena tudi obdelava za zmanjševanje hrupa v ozadju in digitalnih popačenj.\n\n### Jeziki in izraznost\n\nSpeech 2.8 podpira **40 jezikov**, vključno z ruščino. Proizvajalec posebej opisuje delo z medjezikovno izgovarjavo pri kitajsko-japonski kombinaciji. Takšen scenarij se nanaša na ohranjanje naravnega zvena pri uporabi različnih jezikov in ne na samodejno prevajanje besedila.\n\nMiniMax predvideva izbiro glasu ter upravljanje tempa, glasnosti in višine tona. Hitrost se določi v razponu **0,5–2**, glasnost je večja od 0 in do **10**, sprememba višine pa od **−12 do 12**. Izbiro čustva lahko glede na pomen besedila prepustite modelu ali ga določite ročno: veselje, žalost, jeza, strah, gnus, presenečenje ali umirjenost.\n\nIzgovarjavo lahko natančneje določite s slovarjem zamenjav in fonetičnim zapisom; predvideni so mednarodna fonetična abeceda, kitajski pinjin in japonske različice branja. Premori se določijo med izgovorjenimi odseki v razponu **0,01–99,99 sekunde**. Trajanje premora se določi na dve decimalni mesti natančno; oznake se postavijo med izgovorjene odseke in ne druga za drugo. Takšne nastavitve omogočajo uskladitev zvena imen, kratic in dvoumnih besed z zamislijo govorne izvedbe.\n\n### Zvočni rezultat\n\nSinteza sprejema besedilo z manj kot **10 000 znaki**. Za dolgo besedilo z več kot 3000 znaki proizvajalec priporoča pretočni izhod; predvideno je tudi pridobivanje končnega zvoka v celoti. Splošne nastavitve sinteze vključujejo MP3, PCM, FLAC, WAV, Opus in različice G.711 μ-law, mono ali stereo; razpoložljivi nabor formatov konkretne zahteve določajo sredstva Ailoot.\n\nTa kartica pretvarja besedilo v govorni zvok. Zmožnosti nastavljanja glasu opisujejo model MiniMax; ustvarjanje klona glasu, ločeni podnapisi in posebni načini povezovanja niso samodejno vključeni v zahtevo za govorno izvedbo.\n\nDodatne nastavitve zvoka vključujejo frekvence vzorčenja **8, 16, 22,05, 24, 32 in 44,1 kHz**. Za MP3 je predvidena bitna hitrost **32, 64, 128 ali 256 kbit/s**. Spreminjate lahko tudi barvo glasu in uporabite en učinek: prostoren odmev, odmev dvorane, telefonski zven ali robotski glas. Učinki spreminjanja glasu so pri pridobivanju zvoka v celoti podprti za MP3, WAV in FLAC, pri pretočnem izhodu pa samo za MP3. Formati G.711 μ-law uporabljajo frekvenco 8 kHz. Te zmožnosti veljajo za nastavitve sinteze MiniMax.\n\nProizvajalec predvideva sinhronizacijo govora z besedilom: časovne oznake po povedih, besedah ali besedah pri postopnem izhodu. Takšen rezultat pomaga uskladiti izgovarjavo s prikazom besedila. Ta dodatna zmožnost zahteva podporo ustreznemu formatu odgovora.", "alias_of": null, "aliases": [], "author": "MiniMax", "available": null, "canonical_model": "minimax/speech-2.8-hd", "capabilities": { "context_length": 0, "manufacturer_input": [ "text" ], "manufacturer_output": [ "speech" ] }, "card_routes": [ { "label": "Ultra", "rates": [ { "amount": "0.2000", "amount_unit": "usd_per_1000_characters", "billing_input": true, "estimate_only": false, "key": "audio_input_character", "label": "input character", "native_amount_usd_per_unit": "0.0002", "native_quantity": 1, "public_unit_label": "per 1000 input character", "quantity": "1000", "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_character" } ], "summary": "Celoten cenik konfiguracije je v podrobnostih." } ], "ctx": null, "entity_type": "model", "formats": [ "speech" ], "id": "minimax/speech-2.8-hd", "input": [ "text" ], "kind": "speech", "max_out": null, "methods": [ { "available": null, "cache_read": null, "cache_write": null, "cache_write_1h": null, "contract": { "data": { "all_results": "Keep the complete binary result and headers. If JSON/multiple outputs are returned, retain every data item and fetch each actual signed asset URL.", "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." }, "material_combinations": [ { "content_type": "application/json", "mode": "text_to_speech", "required": [ "input" ] } ], "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": [ "text_to_speech" ], "outputs": { "all_results": "Shranite celoten binarni rezultat in glave. Če so vrnjeni podatki JSON ali več izhodov, shranite vsak podatkovni element in pridobite vsebino z vsakega dejanskega podpisanega URL datoteke.", "family": "audio", "fields": [ { "description": null, "name": "binary audio", "type": "bytes" }, { "description": null, "name": "response headers", "type": "headers" } ], "format": "mp3", "http_success": 200 }, "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "minimax/speech-2.8-hd" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "limit_known": false, "maximum_length": null, "min_length": 1, "name": "input", "required": true, "type": "string", "unit": "znaki Unicode" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "English_expressive_narrator", "English_radiant_girl", "English_magnetic_voiced_man", "English_compelling_lady1", "English_Aussie_Bloke", "English_captivating_female1", "English_Upbeat_Woman", "English_Trustworth_Man", "English_CalmWoman", "English_UpsetGirl", "English_Gentle-voiced_man", "English_Whispering_girl", "English_Diligent_Man", "English_Graceful_Lady", "English_ReservedYoungMan", "English_PlayfulGirl", "English_ManWithDeepVoice", "English_MaturePartner", "English_FriendlyPerson", "English_MatureBoss", "English_Debator", "English_LovelyGirl", "English_Steadymentor", "English_Deep-VoicedGentleman", "English_Wiselady", "English_CaptivatingStoryteller", "English_DecentYoungMan", "English_SentimentalLady", "English_ImposingManner", "English_SadTeen", "English_PassionateWarrior", "English_WiseScholar", "English_Soft-spokenGirl", "English_SereneWoman", "English_ConfidentWoman", "English_PatientMan", "English_Comedian", "English_BossyLeader", "English_Strong-WilledBoy", "English_StressedLady", "English_AssertiveQueen", "English_AnimeCharacter", "English_Jovialman", "English_WhimsicalGirl", "English_Kind-heartedGirl" ], "enum_known": true, "name": "voice", "required": true, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "mp3" ], "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": [ "every field outside exactmodel,input,voice,response_format", "stream/speed/reference speech options" ] }, "hints": [ "Izberite natančen glas iz profila tega modela.", "Vhodni znaki in zvočne sekunde so različni merili porabe." ], "input": { "content_type": "application/json", "input": "natančno besedilo UTF-8; število znakov Unicode brez normalizacije", "material_types": [ "text" ], "max_input_characters": null, "other_options": false, "required": [ "model", "input", "voice", "response_format" ], "response_format": [ "mp3" ], "voice_ids": [ "English_expressive_narrator", "English_radiant_girl", "English_magnetic_voiced_man", "English_compelling_lady1", "English_Aussie_Bloke", "English_captivating_female1", "English_Upbeat_Woman", "English_Trustworth_Man", "English_CalmWoman", "English_UpsetGirl", "English_Gentle-voiced_man", "English_Whispering_girl", "English_Diligent_Man", "English_Graceful_Lady", "English_ReservedYoungMan", "English_PlayfulGirl", "English_ManWithDeepVoice", "English_MaturePartner", "English_FriendlyPerson", "English_MatureBoss", "English_Debator", "English_LovelyGirl", "English_Steadymentor", "English_Deep-VoicedGentleman", "English_Wiselady", "English_CaptivatingStoryteller", "English_DecentYoungMan", "English_SentimentalLady", "English_ImposingManner", "English_SadTeen", "English_PassionateWarrior", "English_WiseScholar", "English_Soft-spokenGirl", "English_SereneWoman", "English_ConfidentWoman", "English_PatientMan", "English_Comedian", "English_BossyLeader", "English_Strong-WilledBoy", "English_StressedLady", "English_AssertiveQueen", "English_AnimeCharacter", "English_Jovialman", "English_WhimsicalGirl", "English_Kind-heartedGirl" ] }, "lifecycle": { "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." }, "manufacturer_capability": null, "method": { "http": "POST", "path": "/v1/audio/speech" }, "method_aliases": [], "operation_modes": [ "text_to_speech" ], "output": { "family": "audio", "format": "mp3", "http_success": 200, "response": "full binary MP3 plus response headers", "result": "complete playable owned MP3" } }, "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": { "quantity_meter": "utf8.RuneCountInString(validUTF8): one Han codepoint=1; no Han weighting", "quoted_unit": "per 1000 input character" }, "label": "Ultra", "units": [ { "amount": "0.2000", "amount_unit": "usd_per_1000_characters", "billing_input": true, "estimate_only": false, "key": "audio_input_character", "label": "input character", "native_amount_usd_per_unit": "0.0002", "native_quantity": 1, "public_unit_label": "per 1000 input character", "quantity": "1000", "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_character" } ] } ], "declared_tariff_references": [ { "client_selectable": false, "key": "811df870581b3a6d28c7", "label": "MiniMax: Speech 2.8 HD", "profiles": [ { "basis": "", "dimensions": { "conditions": "Privzeta konfiguracija" }, "label": "MiniMax: Speech 2.8 HD · Privzeta konfiguracija", "units": [ { "amount": "0.0002", "amount_unit": "usd_per_exact_physical_unit", "billing_input": false, "key": "3075a39a90ece77c41dc1677", "label": "Input characters", "public_unit_label": "per input character", "quantity": "1", "rate_role": "declared_tariff_rate", "side": "in", "unit": "input_character" } ] } ] } ], "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_VOICE_ID:?Choose an accepted voice ID from this exact model profile}\"\nexport AILOOT_VOICE_ID\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"minimax/speech-2.8-hd\", \"input\": \"Good afternoon! This is a short voice take.\"}')\nvoice=os.environ[\"AILOOT_VOICE_ID\"]\nallowed=json.loads('[\"English_expressive_narrator\", \"English_radiant_girl\", \"English_magnetic_voiced_man\", \"English_compelling_lady1\", \"English_Aussie_Bloke\", \"English_captivating_female1\", \"English_Upbeat_Woman\", \"English_Trustworth_Man\", \"English_CalmWoman\", \"English_UpsetGirl\", \"English_Gentle-voiced_man\", \"English_Whispering_girl\", \"English_Diligent_Man\", \"English_Graceful_Lady\", \"English_ReservedYoungMan\", \"English_PlayfulGirl\", \"English_ManWithDeepVoice\", \"English_MaturePartner\", \"English_FriendlyPerson\", \"English_MatureBoss\", \"English_Debator\", \"English_LovelyGirl\", \"English_Steadymentor\", \"English_Deep-VoicedGentleman\", \"English_Wiselady\", \"English_CaptivatingStoryteller\", \"English_DecentYoungMan\", \"English_SentimentalLady\", \"English_ImposingManner\", \"English_SadTeen\", \"English_PassionateWarrior\", \"English_WiseScholar\", \"English_Soft-spokenGirl\", \"English_SereneWoman\", \"English_ConfidentWoman\", \"English_PatientMan\", \"English_Comedian\", \"English_BossyLeader\", \"English_Strong-WilledBoy\", \"English_StressedLady\", \"English_AssertiveQueen\", \"English_AnimeCharacter\", \"English_Jovialman\", \"English_WhimsicalGirl\", \"English_Kind-heartedGirl\"]')\nif voice not in allowed: raise SystemExit(\"Choose an accepted voice ID from this exact model profile\")\np[\"voice\"]=voice\np[\"response_format\"]=\"mp3\"\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/audio/speech \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o speech.mp3\n", "label": "curl", "language": "bash" }, { "code": "set -eu\n: \"${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": "speech", "hints": [ "Select exact voice from this model profile.", "Input characters and audio seconds are different meters." ], "http": "POST", "in": null, "input": [ "text" ], "label": "Озвучка текста", "max_out": null, "max_reasoning_effort_multiplier": null, "method_aliases": [], "out": null, "output": [ "audio" ], "path": "/v1/audio/speech", "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_character": 0.0002 } }, "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": { "quantity_meter": "utf8.RuneCountInString(validUTF8): one Han codepoint=1; no Han weighting", "quoted_unit": "per 1000 input character" }, "label": "Ultra", "units": [ { "amount": "0.2000", "amount_unit": "usd_per_1000_characters", "billing_input": true, "estimate_only": false, "key": "audio_input_character", "label": "input character", "native_amount_usd_per_unit": "0.0002", "native_quantity": 1, "public_unit_label": "per 1000 input character", "quantity": "1000", "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_character" } ] } ], "request_model_id": "minimax/speech-2.8-hd", "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": "0.2000", "amount_unit": "usd_per_1000_characters", "billing_input": true, "estimate_only": false, "key": "audio_input_character", "label": "input character", "native_amount_usd_per_unit": "0.0002", "native_quantity": 1, "public_unit_label": "per 1000 input character", "quantity": "1000", "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_character" } ] } ], "model_aliases": [ { "canonical_model_id": "minimax/speech-2.8-hd", "request_model_id": "minimax/speech-2.8-hd", "route_label": "Ultra" } ], "name": "MiniMax: Speech 2.8 HD", "price": { "in": null, "in_label": null, "out": null, "out_label": null, "sort_in": null, "sort_out": null, "varies": true }, "pricing_profiles": [ { "applicability": { "client_selectable": false, "native_profile_selection_pending": true, "scope": "manufacturer_reference" }, "dimensions": { "async_max_input_characters": null, "not_tokens": true, "quoted_denominator": "1000000_characters" }, "label": "Ultra", "units": [ { "amount": "0.0002", "amount_unit": "usd_per_input_character", "conditions": { "async_max_input_characters": null, "not_tokens": true, "quoted_denominator": "1000000_characters" }, "key": "base", "label": "base", "profile_index": 0, "quantity": "1", "rate_role": "binding_component_rate", "side": "in", "unit": "input_character" } ] }, { "applicability": { "client_selectable": false, "native_profile_selection_pending": true, "scope": "manufacturer_reference" }, "dimensions": { "async_max_input_characters": 1000000, "not_tokens": true, "quoted_denominator": "1000000_characters" }, "label": "Ultra", "units": [ { "amount": "0.0002", "amount_unit": "usd_per_input_character", "conditions": { "async_max_input_characters": 1000000, "not_tokens": true, "quoted_denominator": "1000000_characters" }, "key": "base", "label": "base", "profile_index": 1, "quantity": "1", "rate_role": "binding_component_rate", "side": "in", "unit": "input_character" } ] }, { "applicability": { "client_selectable": false, "native_profile_selection_pending": true, "scope": "manufacturer_reference" }, "dimensions": { "charge_at_design_or_clone_creation": false, "charge_at_first_synthesis": true, "charge_once_per_voice_across_synthesis_calls": true, "event": "designed_voice_first_synthesis", "plus_synthesis_characters": true }, "label": "Ultra", "units": [ { "amount": "6", "amount_unit": "usd_per_voice", "conditions": { "charge_at_design_or_clone_creation": false, "charge_at_first_synthesis": true, "charge_once_per_voice_across_synthesis_calls": true, "event": "designed_voice_first_synthesis", "plus_synthesis_characters": true }, "key": "designed_voice_first_synthesis", "label": "designed voice first synthesis", "profile_index": 2, "quantity": "1", "rate_role": "binding_component_rate", "side": "out", "unit": "voice" } ] }, { "applicability": { "client_selectable": false, "native_profile_selection_pending": true, "scope": "manufacturer_reference" }, "dimensions": { "charge_at_design_or_clone_creation": false, "charge_at_first_synthesis": true, "charge_once_per_voice_across_synthesis_calls": true, "event": "cloned_voice_first_synthesis", "plus_synthesis_characters": true }, "label": "Ultra", "units": [ { "amount": "3.0", "amount_unit": "usd_per_voice", "conditions": { "charge_at_design_or_clone_creation": false, "charge_at_first_synthesis": true, "charge_once_per_voice_across_synthesis_calls": true, "event": "cloned_voice_first_synthesis", "plus_synthesis_characters": true }, "key": "cloned_voice_first_synthesis", "label": "cloned voice first synthesis", "profile_index": 3, "quantity": "1", "rate_role": "binding_component_rate", "side": "out", "unit": "voice" } ] } ], "public_id": "minimax/speech-2.8-hd", "short": "Speech 2.8 HD sintetizira izrazen govor z upravljanjem čustev in zvočnimi podrobnostmi, kot sta dihanje in smeh." }, "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": "Speech 2.8 HD sintetizira izrazen govor z upravljanjem čustev in zvočnimi podrobnostmi, kot sta dihanje in smeh.", "source": { "audit_sha256": "2e00086bcbfc28e64d0cebe97aa47c17d8d5618963027f8ffb9dc6123d7d25b1", "bridge_map_sha256": "1125275768b9636fc8461bc7da5061239a81ddfe508e2557843ca42c58ab0036", "raw_model_json_sha256": "6649a30ef9a9299b0469d3215774dc187146c2e53ffbfd21927a8b481a028d1b", "renderer_sha256": "dcba2271c18b0f9570a8b166e8d1e3166f121e096a58609c3a46da31562a1bf2" }, "sourceRevision": "97106771f431f935a2cbab6e9e966e211ebdb53e3064189cad6f75210a6ffbaf" }