{ "aboutHtml": "

Voxtral Mini Transcribe 2 — Mistral AI kompaniyasining ishlab chiqaruvchi model kartasida voxtral-mini-2602 deb belgilangan, transkripsiyaga yo‘naltirilgan Voxtral nashri. U dastlabki Voxtral Mini 3B modelining kengroq savol-javob roli uchun emas, yozuvga asoslangan paketli transkripsiya uchun yaratilgan. Kirish audio, natija esa ixtiyoriy ravishda so‘zlovchi belgilari va vaqt ma’lumotlari bilan boyitilgan ko‘chirilgan matndir. Amaliy qo‘llanishlar yig‘ilish transkriptlari, intervyu tahlili, ko‘p tomonli qo‘ng‘iroq qaydlari va yozib olingan media bilan moslashtirilgan matnni o‘z ichiga oladi.

Ishlab chiqaruvchi transkript kim qachon gapirganini ko‘rsatishi uchun so‘zlovchilarni ajratish va boshlanish/tugash vaqtlarini hujjatlashtiradi. So‘z darajasidagi vaqt belgilari subtitrlar, audio qidiruv va matn parchasi bilan uning yozuvdagi o‘rnini moslashtirishni qo‘llaydi. Ishlab chiqaruvchi yo‘riqnomasi segment yoki so‘z darajasidagi vaqt belgilariga ruxsat beradi. Intervyu uchun foydali material — so‘zlovchiga biriktirilgan vaqtli parchalar ketma-ketligi; subtitr tayyorlashda esa so‘z yoki segment vaqti keyingi subtitrlash qadamiga yo‘l ko‘rsatishi mumkin, bu vaqtni oddiy transkript matnidan taxmin qilishga majbur qilmaydi.

Kontekst orqali yo‘naltirish nomlar, texnik atamalar va sohaga xos lug‘atning kerakli yozilishiga modelni yo‘naltiradigan 100 tagacha so‘z yoki iborani qabul qiladi. Mistral bu imkoniyat ingliz tili uchun optimallashtirilganini, boshqa tillardagi qo‘llov esa tajribaviy ekanini aytadi. Aloqasiz lug‘at o‘rniga yozuv mavzusidan aniq yo‘naltirilgan lug‘at ro‘yxatini tayyorlang. Mualliflik misolida texnik muhokamada uchrashi mumkin bo‘lgan loyiha nomlari va maxsus atamalar berilib, keyin tugallangan transkriptda ularning yozilishi tekshirilishi mumkin.

Ushbu nashr o‘n uch tilni qo‘llaydi: ingliz, xitoy, hind, ispan, arab, fransuz, portugal, rus, nemis, yapon, koreys, italyan va niderland. Ishlab chiqaruvchi shovqinga chidamlilik va bitta so‘rovda uch soatgacha yozuvlarni ham hujjatlashtiradi. Bular Mini Transcribe 2ning yozuv jarayoniga tegishli; dastlabki 2507 audioni tushunish modelining kontekst va davomiylik bayonotlari boshqa relizni ta’riflaydi. Tilni avtomatik aniqlash mavjud, yo‘riqnomada ma’lum audio tilini aniq berish transkripsiya aniqligini yaxshilashi mumkinligi aytiladi.

Hujjatlashtirilgan ishlab chiqaruvchi jarayonida audio yuklangan fayl, avval yuklangan fayl identifikatori yoki havola qilingan yozuv sifatida berilishi mumkin. Hamroh yuklash namoyishi MP3, WAV, M4A, FLAC va OGG yozuvlarini qabul qiladi; ko‘rsatilgan yuklash jarayoni uchun shu formatlardan birini tanlang. Yozuv dekodlanadigan bo‘lsin va tegishli nutqni o‘z ichiga olsin. Uzun materialda uning identifikatori va vaqt boshlanishini saqlang, shunda keyingi parchalar yoki tahrirlar ham manbaga kuzatib bog‘lanadi.

Transkripsiya ma’lumotnomasi matn va aniqlangan tilni, so‘ralganda segmentlarni qaytaradi hamda oqimli transkripsiya hodisalarini alohida hujjatlashtiradi. Diarizatsiya ixtiyoriy va standart qiymati false. Yo‘riqnomada timestamp_granularities va tilni aniq belgilash hozircha mos emasligi qayd etiladi; shuning uchun ularni birlashtirish o‘rniga kerakli vaqtli jarayonni yoki tilni qo‘lda ko‘rsatishni tanlang. So‘zlovchi belgilari bilan transkripsiya, lug‘atga yo‘naltirish va vaqt belgilarini oddiy so‘rovdan avtomatik deb hisoblamay, ko‘zlangan natijaga qarab tanlash kerak.

Bir vaqtda ustma-ust nutq muhim cheklovdir: Mistral so‘zlovchilar bir vaqtda gapirganda model odatda bitta so‘zlovchini ko‘chirib yozishini aytadi. Demak, belgilangan transkriptni bir vaqtdagi har bir gapning to‘liq qaydi deb qabul qilmaslik kerak. Yig‘ilish qaydida murakkab ustma-ust nutq va muhim nomlar yoki sonlarni yozuv bilan solishtirib ko‘ring. Modelning maqsadi transkripsiya; xulosa, tarjima yoki tahlil transkriptga asoslangan alohida vazifa bo‘lishi mumkin. Voxtral Realtime alohida jonli transkripsiya kechikishi variantiga ega, nutq yaratish esa boshqa modellarga tegishli.

Natijani keyingi qo‘llanishi uchun tayyorlang. Yig‘ilish jarayoni alohida bosqich qarorlarni ajratishidan oldin transkript, so‘zlovchi belgilari va vaqtni saqlashi mumkin; media jarayoni parchalarni topish va subtitr qoralamalarini yozish uchun vaqtdan foydalanishi mumkin; atamalarga boy yozuv esa aniq kontekst yo‘naltirish ro‘yxati va natijadagi yozilishlarni ko‘rib chiqishni o‘z ichiga olishi mumkin. Foydali yakuniy material — o‘z manba yozuvi va sozlangan metama’lumotlariga bog‘langan matn; bunda ushbu raqamlangan transkripsiya nashri dastlabki Mini modeli va yangilanib turadigan latest nomlaridan alohida saqlanadi.

", "aboutText": "Voxtral Mini Transcribe 2 — Mistral AI kompaniyasining ishlab chiqaruvchi model kartasida voxtral-mini-2602 deb belgilangan, transkripsiyaga yo‘naltirilgan Voxtral nashri. U dastlabki Voxtral Mini 3B modelining kengroq savol-javob roli uchun emas, yozuvga asoslangan paketli transkripsiya uchun yaratilgan. Kirish audio, natija esa ixtiyoriy ravishda so‘zlovchi belgilari va vaqt ma’lumotlari bilan boyitilgan ko‘chirilgan matndir. Amaliy qo‘llanishlar yig‘ilish transkriptlari, intervyu tahlili, ko‘p tomonli qo‘ng‘iroq qaydlari va yozib olingan media bilan moslashtirilgan matnni o‘z ichiga oladi.\n\nIshlab chiqaruvchi transkript kim qachon gapirganini ko‘rsatishi uchun so‘zlovchilarni ajratish va boshlanish/tugash vaqtlarini hujjatlashtiradi. So‘z darajasidagi vaqt belgilari subtitrlar, audio qidiruv va matn parchasi bilan uning yozuvdagi o‘rnini moslashtirishni qo‘llaydi. Ishlab chiqaruvchi yo‘riqnomasi segment yoki so‘z darajasidagi vaqt belgilariga ruxsat beradi. Intervyu uchun foydali material — so‘zlovchiga biriktirilgan vaqtli parchalar ketma-ketligi; subtitr tayyorlashda esa so‘z yoki segment vaqti keyingi subtitrlash qadamiga yo‘l ko‘rsatishi mumkin, bu vaqtni oddiy transkript matnidan taxmin qilishga majbur qilmaydi.\n\nKontekst orqali yo‘naltirish nomlar, texnik atamalar va sohaga xos lug‘atning kerakli yozilishiga modelni yo‘naltiradigan 100 tagacha so‘z yoki iborani qabul qiladi. Mistral bu imkoniyat ingliz tili uchun optimallashtirilganini, boshqa tillardagi qo‘llov esa tajribaviy ekanini aytadi. Aloqasiz lug‘at o‘rniga yozuv mavzusidan aniq yo‘naltirilgan lug‘at ro‘yxatini tayyorlang. Mualliflik misolida texnik muhokamada uchrashi mumkin bo‘lgan loyiha nomlari va maxsus atamalar berilib, keyin tugallangan transkriptda ularning yozilishi tekshirilishi mumkin.\n\nUshbu nashr o‘n uch tilni qo‘llaydi: ingliz, xitoy, hind, ispan, arab, fransuz, portugal, rus, nemis, yapon, koreys, italyan va niderland. Ishlab chiqaruvchi shovqinga chidamlilik va bitta so‘rovda uch soatgacha yozuvlarni ham hujjatlashtiradi. Bular Mini Transcribe 2ning yozuv jarayoniga tegishli; dastlabki 2507 audioni tushunish modelining kontekst va davomiylik bayonotlari boshqa relizni ta’riflaydi. Tilni avtomatik aniqlash mavjud, yo‘riqnomada ma’lum audio tilini aniq berish transkripsiya aniqligini yaxshilashi mumkinligi aytiladi.\n\nHujjatlashtirilgan ishlab chiqaruvchi jarayonida audio yuklangan fayl, avval yuklangan fayl identifikatori yoki havola qilingan yozuv sifatida berilishi mumkin. Hamroh yuklash namoyishi MP3, WAV, M4A, FLAC va OGG yozuvlarini qabul qiladi; ko‘rsatilgan yuklash jarayoni uchun shu formatlardan birini tanlang. Yozuv dekodlanadigan bo‘lsin va tegishli nutqni o‘z ichiga olsin. Uzun materialda uning identifikatori va vaqt boshlanishini saqlang, shunda keyingi parchalar yoki tahrirlar ham manbaga kuzatib bog‘lanadi.\n\nTranskripsiya ma’lumotnomasi matn va aniqlangan tilni, so‘ralganda segmentlarni qaytaradi hamda oqimli transkripsiya hodisalarini alohida hujjatlashtiradi. Diarizatsiya ixtiyoriy va standart qiymati false. Yo‘riqnomada timestamp_granularities va tilni aniq belgilash hozircha mos emasligi qayd etiladi; shuning uchun ularni birlashtirish o‘rniga kerakli vaqtli jarayonni yoki tilni qo‘lda ko‘rsatishni tanlang. So‘zlovchi belgilari bilan transkripsiya, lug‘atga yo‘naltirish va vaqt belgilarini oddiy so‘rovdan avtomatik deb hisoblamay, ko‘zlangan natijaga qarab tanlash kerak.\n\nBir vaqtda ustma-ust nutq muhim cheklovdir: Mistral so‘zlovchilar bir vaqtda gapirganda model odatda bitta so‘zlovchini ko‘chirib yozishini aytadi. Demak, belgilangan transkriptni bir vaqtdagi har bir gapning to‘liq qaydi deb qabul qilmaslik kerak. Yig‘ilish qaydida murakkab ustma-ust nutq va muhim nomlar yoki sonlarni yozuv bilan solishtirib ko‘ring. Modelning maqsadi transkripsiya; xulosa, tarjima yoki tahlil transkriptga asoslangan alohida vazifa bo‘lishi mumkin. Voxtral Realtime alohida jonli transkripsiya kechikishi variantiga ega, nutq yaratish esa boshqa modellarga tegishli.\n\nNatijani keyingi qo‘llanishi uchun tayyorlang. Yig‘ilish jarayoni alohida bosqich qarorlarni ajratishidan oldin transkript, so‘zlovchi belgilari va vaqtni saqlashi mumkin; media jarayoni parchalarni topish va subtitr qoralamalarini yozish uchun vaqtdan foydalanishi mumkin; atamalarga boy yozuv esa aniq kontekst yo‘naltirish ro‘yxati va natijadagi yozilishlarni ko‘rib chiqishni o‘z ichiga olishi mumkin. Foydali yakuniy material — o‘z manba yozuvi va sozlangan metama’lumotlariga bog‘langan matn; bunda ushbu raqamlangan transkripsiya nashri dastlabki Mini modeli va yangilanib turadigan latest nomlaridan alohida saqlanadi.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "6e6bdb5f7478008bdbd4dc0d8c04af94ba336714bbe67dfedf5280792231cee2", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "uz", "methods": [ { "html": "
•

Mistral: Voxtral Mini Transcribe

Mistral /mistralai/voxtral-mini-transcribe

Boshlash

Voxtral Mini Transcribe 2 yozuvlarni so‘zlovchilarni ajratish, so‘z darajasidagi vaqt belgilari va lug‘atga yo‘naltirish bilan matnga aylantiradi. Mistral transkripsiyaga yo‘naltirilgan ushbu nashr uchun 13 til va uch soatgacha yozuvlarni hujjatlashtiradi; u Voxtral Realtimedan alohida.

Qabul qilinadigan kirish ma’lumotlari
Audio
Natijalar
Matn
Model haqida

Bu tavsif model imkoniyatlarini yoritadi. Ailoot da tanlangan usul uchun mavjud kirish, chiqish va parametrlar quyida keltirilgan.

Voxtral Mini Transcribe 2 — Mistral AI kompaniyasining ishlab chiqaruvchi model kartasida voxtral-mini-2602 deb belgilangan, transkripsiyaga yo‘naltirilgan Voxtral nashri. U dastlabki Voxtral Mini 3B modelining kengroq savol-javob roli uchun emas, yozuvga asoslangan paketli transkripsiya uchun yaratilgan. Kirish audio, natija esa ixtiyoriy ravishda so‘zlovchi belgilari va vaqt ma’lumotlari bilan boyitilgan ko‘chirilgan matndir. Amaliy qo‘llanishlar yig‘ilish transkriptlari, intervyu tahlili, ko‘p tomonli qo‘ng‘iroq qaydlari va yozib olingan media bilan moslashtirilgan matnni o‘z ichiga oladi.

Ishlab chiqaruvchi transkript kim qachon gapirganini ko‘rsatishi uchun so‘zlovchilarni ajratish va boshlanish/tugash vaqtlarini hujjatlashtiradi. So‘z darajasidagi vaqt belgilari subtitrlar, audio qidiruv va matn parchasi bilan uning yozuvdagi o‘rnini moslashtirishni qo‘llaydi. Ishlab chiqaruvchi yo‘riqnomasi segment yoki so‘z darajasidagi vaqt belgilariga ruxsat beradi. Intervyu uchun foydali material — so‘zlovchiga biriktirilgan vaqtli parchalar ketma-ketligi; subtitr tayyorlashda esa so‘z yoki segment vaqti keyingi subtitrlash qadamiga yo‘l ko‘rsatishi mumkin, bu vaqtni oddiy transkript matnidan taxmin qilishga majbur qilmaydi.

Kontekst orqali yo‘naltirish nomlar, texnik atamalar va sohaga xos lug‘atning kerakli yozilishiga modelni yo‘naltiradigan 100 tagacha so‘z yoki iborani qabul qiladi. Mistral bu imkoniyat ingliz tili uchun optimallashtirilganini, boshqa tillardagi qo‘llov esa tajribaviy ekanini aytadi. Aloqasiz lug‘at o‘rniga yozuv mavzusidan aniq yo‘naltirilgan lug‘at ro‘yxatini tayyorlang. Mualliflik misolida texnik muhokamada uchrashi mumkin bo‘lgan loyiha nomlari va maxsus atamalar berilib, keyin tugallangan transkriptda ularning yozilishi tekshirilishi mumkin.

Ushbu nashr o‘n uch tilni qo‘llaydi: ingliz, xitoy, hind, ispan, arab, fransuz, portugal, rus, nemis, yapon, koreys, italyan va niderland. Ishlab chiqaruvchi shovqinga chidamlilik va bitta so‘rovda uch soatgacha yozuvlarni ham hujjatlashtiradi. Bular Mini Transcribe 2ning yozuv jarayoniga tegishli; dastlabki 2507 audioni tushunish modelining kontekst va davomiylik bayonotlari boshqa relizni ta’riflaydi. Tilni avtomatik aniqlash mavjud, yo‘riqnomada ma’lum audio tilini aniq berish transkripsiya aniqligini yaxshilashi mumkinligi aytiladi.

Hujjatlashtirilgan ishlab chiqaruvchi jarayonida audio yuklangan fayl, avval yuklangan fayl identifikatori yoki havola qilingan yozuv sifatida berilishi mumkin. Hamroh yuklash namoyishi MP3, WAV, M4A, FLAC va OGG yozuvlarini qabul qiladi; ko‘rsatilgan yuklash jarayoni uchun shu formatlardan birini tanlang. Yozuv dekodlanadigan bo‘lsin va tegishli nutqni o‘z ichiga olsin. Uzun materialda uning identifikatori va vaqt boshlanishini saqlang, shunda keyingi parchalar yoki tahrirlar ham manbaga kuzatib bog‘lanadi.

Transkripsiya ma’lumotnomasi matn va aniqlangan tilni, so‘ralganda segmentlarni qaytaradi hamda oqimli transkripsiya hodisalarini alohida hujjatlashtiradi. Diarizatsiya ixtiyoriy va standart qiymati false. Yo‘riqnomada timestamp_granularities va tilni aniq belgilash hozircha mos emasligi qayd etiladi; shuning uchun ularni birlashtirish o‘rniga kerakli vaqtli jarayonni yoki tilni qo‘lda ko‘rsatishni tanlang. So‘zlovchi belgilari bilan transkripsiya, lug‘atga yo‘naltirish va vaqt belgilarini oddiy so‘rovdan avtomatik deb hisoblamay, ko‘zlangan natijaga qarab tanlash kerak.

Bir vaqtda ustma-ust nutq muhim cheklovdir: Mistral so‘zlovchilar bir vaqtda gapirganda model odatda bitta so‘zlovchini ko‘chirib yozishini aytadi. Demak, belgilangan transkriptni bir vaqtdagi har bir gapning to‘liq qaydi deb qabul qilmaslik kerak. Yig‘ilish qaydida murakkab ustma-ust nutq va muhim nomlar yoki sonlarni yozuv bilan solishtirib ko‘ring. Modelning maqsadi transkripsiya; xulosa, tarjima yoki tahlil transkriptga asoslangan alohida vazifa bo‘lishi mumkin. Voxtral Realtime alohida jonli transkripsiya kechikishi variantiga ega, nutq yaratish esa boshqa modellarga tegishli.

Natijani keyingi qo‘llanishi uchun tayyorlang. Yig‘ilish jarayoni alohida bosqich qarorlarni ajratishidan oldin transkript, so‘zlovchi belgilari va vaqtni saqlashi mumkin; media jarayoni parchalarni topish va subtitr qoralamalarini yozish uchun vaqtdan foydalanishi mumkin; atamalarga boy yozuv esa aniq kontekst yo‘naltirish ro‘yxati va natijadagi yozilishlarni ko‘rib chiqishni o‘z ichiga olishi mumkin. Foydali yakuniy material — o‘z manba yozuvi va sozlangan metama’lumotlariga bog‘langan matn; bunda ushbu raqamlangan transkripsiya nashri dastlabki Mini modeli va yangilanib turadigan latest nomlaridan alohida saqlanadi.

Ailoot da mavjud · kirish ma’lumotlari va usullar

Ailoot Ultra · Transkripsiya POST /v1/audio/transcriptions
Kirish
audio
Chiqish
text
MaydonTurTalabQiymatlar va cheklovlarStandart
MaydonmodelTurstringTalabMajburiyQiymatlar va cheklovlar
mistralai/voxtral-mini-transcribe
Standart—
Maydoninput_audioTurobjectTalabMajburiyQiymatlar va cheklovlarStandart—
Usul parametrlari va hayot sikli
ParametrParametr talablari
Parametrcontent_typeParametr talablariapplication/json
ParametrrequiredParametr talablarimodel, input_audio
Parametrmaterial_typesParametr talablariaudio
Parametrmaterial_conditionsParametr talablariMisol haqiqiy, bo‘sh bo‘lmagan PCM WAV faylingizni o‘qiydi, faylning barcha baytlarini base64 ko‘rinishida kodlaydi va input_audio.format qiymatini wav qilib yuboradi.

Hayot sikli: synchronous_result_then_owned_library

GET /v1/media/tasks/{task_id} · mavjud, egalik qilinadigan media yozuvidan aniq task_id

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

GET /v1/media/assets

GET /v1/media/assets/{asset_id}

Tariflar

Tarif ma’lumotlari so‘rov imkoniyatlarini qo‘shmaydi. Qo‘llab-quvvatlanadigan parametrlar tanlangan usulda ko‘rsatilgan.

Tezkor rejim
Ko‘rsatilmagan Tezkor rejim tanlanganda
Flex rejimi
Ko‘rsatilmagan flex rejimi tanlanganda
Maksimal fikrlash darajasi
Ko‘rsatilmagan Maksimal fikrlash darajasi uchun standart (default) tuzatish qo‘llanganda

Ailoot tariflari

Sozlamalar bo‘yicha narxlar

Har bir to‘lovni ko‘rsatilgan shartlarga moslang. Har bir muqobil sozlamalar to‘plami uchun bitta tarifdan foydalaning.

SozlamaTariflar jadvaliHisob birligiTo‘lov
SozlamaTokenlar uchun bazaviy tariflarTariflar jadvaliAsosiy tarifHisob birligi—To‘lov
Kirish · Kirish tokenlari — / 1K token
Chiqish · Chiqish tokenlari — / 1K token
Kirish · Keshdan o‘qish — / 1K token
Kirish · Keshga yozish — / 1K token
Kirish · Keshga yozish, 1 soat — / 1K token
SozlamaKirish audiosi soniyasiTariflar jadvali—Hisob birligikirish audiosining soniyasi uchunTo‘lov
Kirish · Kirish audiosi soniyasi $0.0001 kirish audiosining soniyasi uchun

Ailoot so‘rovdan oldin taxminiy summani band qiladi. Natijadan keyin o‘lchangan sarf asosidagi yakuniy to‘lovni yechadi. Oqimli javob bo‘yicha yakuniy hisob-kitob yakuniy sarf yozuviga asoslanadi. Summani band qilish va to‘lovni hisoblash tartibi →

So‘rov namunalari

Ailoot Ultra · Transkripsiya

set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_AUDIO_FILE:?Set the path to your actual PCM WAV recording}"\nexport AILOOT_AUDIO_FILE\npython3 - <<'PY_REQUEST'\nimport base64, io, json, os, wave\nfrom pathlib import Path\naudio = Path(os.environ['AILOOT_AUDIO_FILE']).read_bytes()\nif not (audio[:4] == b'RIFF' and audio[8:12] == b'WAVE'):\n    raise SystemExit('Supply your actual PCM WAV audio file')\nwith wave.open(io.BytesIO(audio), 'rb') as recording:\n    if recording.getcomptype() != 'NONE' or recording.getnframes() <= 0:\n        raise SystemExit('Supply a nonempty PCM WAV recording')\nrequest = {'model': 'mistralai/voxtral-mini-transcribe', 'input_audio': {'data': base64.b64encode(audio).decode('ascii'), 'format': 'wav'}}\nPath('request.json').write_text(json.dumps(request, ensure_ascii=False), encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/audio/transcriptions \\\n  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o response.bin\n# Retain the complete original response, headers and actual X-Client-Request-ID.\n# Read existing owned records for recovery; do not resubmit an uncertain operation.\n

Natijalarni olish va saqlash

Ailoot Ultra · Transkripsiya

To‘liq dastlabki javob tanasi, holat va uzatilgan sarlavhalar. Bu ishlovchi universal JSON tuzilmasi, matn maydoni yoki vazifa o‘rovini qo‘shmaydi.

Barcha tayyor natijalarni saqlash

Qaytarilgan har bir to‘liq javob, fayl va kontent qismini saqlang.

To‘liq javob va sarlavhalarni, amalda qaytarilgan barcha natijalarni, dastlab qaytarilgan identifikatorlarni hamda barcha usage maydonlarini saqlang. Yaratish so‘rovini qayta yubormasdan dastlabki operatsiyani tiklang.

Asl javobni tekshirish kerak bo‘lsa

Haqiqiy X-Client-Request-ID va to‘liq javobni saqlang. Egalik qilinadigan dastlabki aktivlar va ularning aniq imzolangan mazmun URL larini o‘qing; natijasi noaniq yaratishni hech qachon qayta yubormang.

Javob maydonlari
MaydonTur
Maydontext (when present)Tur
Maydonusage (when present)Tur
Xatolar va keyingi qadamlar
JavobShartKeyingi qadam
Javob400 · invalid_request_errorShartJSON tanasi yoki ochiq ko‘rsatilgan kanonik model ID si yaroqsiz.Keyingi qadamJavobni saqlang va ko‘rsatilgan so‘rov maydonini tuzating.
Javob401 · authentication_errorShartAiloot API kaliti yaroqsiz.Keyingi qadamRuxsat berilgan Ailoot API kalitingizdan foydalaning.
Javob403 · permission_errorShartKalit guruhi bu usulga ruxsat bermaydi.Keyingi qadamQaytarilgan xato tafsilotlarini saqlang.
Javob404 · not_found_errorShartTanlangan usul uchun ruxsat etilgan yo‘nalish yo‘q.Keyingi qadamQaytarilgan xato tafsilotlarini saqlang.
Javob422 · price_unavailableShartQabul qilingan tarif zarur kirish miqdorini yoki chegarasini aniqlay olmaydi.Keyingi qadamJavobni saqlang; qabul qilingan tarif talab qiladigan kirish ko‘rinishidan foydalaning.
Javob503 · ShartZarur saqlov, yo‘nalish, usul narxi yoki mablag‘ni band qilish imkoniyati mavjud emas.Keyingi qadamTo‘liq dastlabki javobni saqlang. Noaniq mablag‘ band qilish qayta yuborishga ruxsat bermaydi.
Javob502 · server_errorShartDastlabki natija, foydalanish ma’lumoti yoki hisob-kitobni tekshirish talab qilinadi.Keyingi qadamHaqiqiy so‘rov ID si va dastlabki javobni saqlang. Mavjud, egalik qilinadigan yozuvni o‘qing; yaratishni qayta yubormang.

Taxalluslar

Model taxalluslari

Ailoot Ultra mistralai/voxtral-mini-transcribe

Usul yo‘llari taxalluslari

Yuqorida ko‘rsatilgan usul yo‘llaridan foydalaning.

Chaqirish uchun tegishli ID lar

mistralai/voxtral-mini-transcribe

", "method_identity": { "effective_request_model_id": "mistralai/voxtral-mini-transcribe", "fmt": "transcriptions", "http": "POST", "path": "/v1/audio/transcriptions", "request_model_id": "mistralai/voxtral-mini-transcribe", "route_label": "Ultra" }, "method_key": "Ultra|transcriptions|/v1/audio/transcriptions|mistralai%2Fvoxtral-mini-transcribe", "ordinal": 0, "rawMethod": { "available": null, "cache_read": null, "cache_write": null, "cache_write_1h": null, "contract": { "data": { "all_results": "Retain the complete response and headers, every actual output, original returned identifiers and all usage fields. Recover the original operation without submitting creation again.", "errors": [ { "code": null, "condition": "JSON tanasi yoki ochiq ko‘rsatilgan kanonik model ID si yaroqsiz.", "http_status": 400, "recovery": "Javobni saqlang va ko‘rsatilgan so‘rov maydonini tuzating.", "type": "invalid_request_error" }, { "code": null, "condition": "Ailoot API kaliti yaroqsiz.", "http_status": 401, "recovery": "Ruxsat berilgan Ailoot API kalitingizdan foydalaning.", "type": "authentication_error" }, { "code": null, "condition": "Kalit guruhi bu usulga ruxsat bermaydi.", "http_status": 403, "recovery": "Qaytarilgan xato tafsilotlarini saqlang.", "type": "permission_error" }, { "code": null, "condition": "Tanlangan usul uchun ruxsat etilgan yo‘nalish yo‘q.", "http_status": 404, "recovery": "Qaytarilgan xato tafsilotlarini saqlang.", "type": "not_found_error" }, { "code": null, "condition": "Qabul qilingan tarif zarur kirish miqdorini yoki chegarasini aniqlay olmaydi.", "http_status": 422, "recovery": "Javobni saqlang; qabul qilingan tarif talab qiladigan kirish ko‘rinishidan foydalaning.", "type": "price_unavailable" }, { "code": null, "condition": "Zarur saqlov, yo‘nalish, usul narxi yoki mablag‘ni band qilish imkoniyati mavjud emas.", "http_status": 503, "recovery": "To‘liq dastlabki javobni saqlang. Noaniq mablag‘ band qilish qayta yuborishga ruxsat bermaydi.", "type": null }, { "code": null, "condition": "Dastlabki natija, foydalanish ma’lumoti yoki hisob-kitobni tekshirish talab qilinadi.", "http_status": 502, "operation_id_source": "actual X-Client-Request-ID", "recovery": "Haqiqiy so‘rov ID si va dastlabki javobni saqlang. Mavjud, egalik qilinadigan yozuvni o‘qing; yaratishni qayta yubormang.", "response_headers": { "x-should-retry": "false" }, "type": "server_error" } ], "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 content URL" } ], "dedicated_method_polling_or_cancel": false, "mode": "synchronous_result_then_owned_library", "original_POST_adds_task_envelope": false, "status": [ { "http": "GET", "id_source": "exact task_id from an existing owned media record", "path": "/v1/media/tasks/{task_id}" } ], "unknown": "Haqiqiy X-Client-Request-ID va to‘liq javobni saqlang. Egalik qilinadigan dastlabki aktivlar va ularning aniq imzolangan mazmun URL larini o‘qing; natijasi noaniq yaratishni hech qachon qayta yubormang." }, "outputs": { "all_results": "To‘liq javob va sarlavhalarni, amalda qaytarilgan barcha natijalarni, dastlab qaytarilgan identifikatorlarni hamda barcha usage maydonlarini saqlang. Yaratish so‘rovini qayta yubormasdan dastlabki operatsiyani tiklang.", "family": "text", "fields": [ { "description": null, "name": "text (when present)", "type": null }, { "description": null, "name": "usage (when present)", "type": null } ], "result": "To‘liq dastlabki javob tanasi, holat va uzatilgan sarlavhalar. Bu ishlovchi universal JSON tuzilmasi, matn maydoni yoki vazifa o‘rovini qo‘shmaydi." }, "parameters": [ { "default_known": false, "enum": [ "mistralai/voxtral-mini-transcribe" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "default_known": false, "enum_known": false, "name": "input_audio", "required": true, "type": "object" } ], "request_schema": { "properties": { "input_audio": { "properties": { "data": { "contentEncoding": "base64", "type": "string" }, "format": { "type": "string" } }, "required": [ "data", "format" ], "type": "object" }, "model": { "enum": [ "mistralai/voxtral-mini-transcribe" ], "type": "string" } }, "required": [ "model", "input_audio" ], "type": "object" }, "schema_template": { "actual_file_preparation_required": true, "body": { "input_audio": { "data": "${BASE64_ACTUAL_WAV_BYTES}", "format": "wav" }, "model": "mistralai/voxtral-mini-transcribe" }, "content_type": "application/json" } }, "input": { "content_type": "application/json", "material_conditions": [ "Misol haqiqiy, bo‘sh bo‘lmagan PCM WAV faylingizni o‘qiydi, faylning barcha baytlarini base64 ko‘rinishida kodlaydi va input_audio.format qiymatini wav qilib yuboradi." ], "material_types": [ "audio" ], "required": [ "model", "input_audio" ] }, "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 content URL" } ], "dedicated_method_polling_or_cancel": false, "mode": "synchronous_result_then_owned_library", "original_POST_adds_task_envelope": false, "status": [ { "http": "GET", "id_source": "mavjud, egalik qilinadigan media yozuvidan aniq task_id", "path": "/v1/media/tasks/{task_id}" } ], "unknown": "Retain the actual X-Client-Request-ID and complete response. Read the original owned assets and their exact signed content URLs; never resubmit an uncertain creation." }, "method": { "http": "POST", "path": "/v1/audio/transcriptions" }, "output": { "all_results": "Retain the complete response and headers, every actual output, original returned identifiers and all usage fields. Recover the original operation without submitting creation again.", "family": "text", "fields": [ { "description": null, "name": "text (when present)", "type": null }, { "description": null, "name": "usage (when present)", "type": null } ], "result": "Complete original response body, status and forwarded headers. No universal JSON shape, text field or task envelope is added by this handler." } }, "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": "per input audio second" }, "label": "input audio second", "units": [ { "amount": "0.0001", "amount_unit": "usd_per_exact_native_unit", "billing_input": true, "estimate_only": false, "key": "audio_input_second", "label": "input audio second", "native_amount_usd_per_unit": "0.0001", "native_quantity": 1, "public_unit_label": "per input audio second", "quantity": 1, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "audio_input_second" } ] } ], "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_AUDIO_FILE:?Set the path to your actual PCM WAV recording}\"\nexport AILOOT_AUDIO_FILE\npython3 - <<'PY_REQUEST'\nimport base64, io, json, os, wave\nfrom pathlib import Path\naudio = Path(os.environ['AILOOT_AUDIO_FILE']).read_bytes()\nif not (audio[:4] == b'RIFF' and audio[8:12] == b'WAVE'):\n raise SystemExit('Supply your actual PCM WAV audio file')\nwith wave.open(io.BytesIO(audio), 'rb') as recording:\n if recording.getcomptype() != 'NONE' or recording.getnframes() <= 0:\n raise SystemExit('Supply a nonempty PCM WAV recording')\nrequest = {'model': 'mistralai/voxtral-mini-transcribe', 'input_audio': {'data': base64.b64encode(audio).decode('ascii'), 'format': 'wav'}}\nPath('request.json').write_text(json.dumps(request, ensure_ascii=False), encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/audio/transcriptions \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o response.bin\n# Retain the complete original response, headers and actual X-Client-Request-ID.\n# Read existing owned records for recovery; do not resubmit an uncertain operation.\n", "label": "curl · actual WAV file and complete original result", "language": "bash" } ], "family": "openai", "fast_multiplier": null, "flex_multiplier": null, "fmt": "transcriptions", "hints": [ "The example reads your actual nonempty PCM WAV file, encodes the complete file bytes as base64 and sends input_audio.format as wav.", "The format value in the example is the documented recipe; no model-specific format list, limit or default is asserted.", "Retain the complete response and headers, every actual output, original returned identifiers and all usage fields. Recover the original operation without submitting creation again." ], "http": "POST", "in": null, "input": [ "audio" ], "label": "Transkripsiya", "max_out": null, "max_reasoning_effort_multiplier": null, "method_aliases": [], "native_endpoint": "audio_transcriptions", "out": null, "output": [ "text" ], "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_second": 0.0001 } }, "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": "per input audio second" }, "label": "input audio second", "units": [ { "amount": "0.0001", "amount_unit": "usd_per_exact_native_unit", "billing_input": true, "estimate_only": false, "key": "audio_input_second", "label": "input audio second", "native_amount_usd_per_unit": "0.0001", "native_quantity": 1, "public_unit_label": "per input audio second", "quantity": 1, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "audio_input_second" } ] } ], "request_model_id": "mistralai/voxtral-mini-transcribe", "route_label": "Ultra", "status_reads": [ "GET /v1/media/tasks/{task_id}" ], "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": "0.0001", "amount_unit": "usd_per_exact_native_unit", "billing_input": true, "estimate_only": false, "key": "audio_input_second", "label": "input audio second", "native_amount_usd_per_unit": "0.0001", "native_quantity": 1, "public_unit_label": "per input audio second", "quantity": 1, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "audio_input_second" } ] } } ], "model_id": "mistralai/voxtral-mini-transcribe", "nativeProvenance": { "input_facts_canonical_sha256": "3db1a810737bac8c04a478b781dac1447830645caa9849f143bf64b3d045085d", "input_html_sha256": "108d5a2b81c87894e1bbd06814a04c7152dbc4e7651ee4a67a8f62625eacbca7", "private_audit_sha256": "5ce11e4c5a43017ed315825cb9d4cfa3fa503de9ca8315202aeaea5cab407ad3", "role": "historical-normalized-input-audit-hashes", "schema": "ailoot-native-model-provenance-v2" }, "page": { "canonical": "https://ailoot.ai/models/uz/mistralai-voxtral-mini-transcribe/", "description": "Voxtral Mini Transcribe 2 yozuvlarni so‘zlovchilarni ajratish, so‘z darajasidagi vaqt belgilari va lug‘atga yo‘naltirish bilan matnga aylantiradi. Mistral transkripsiyaga yo‘naltirilgan ushbu nashr uchun 13 til va uch soatgacha yozuvlarni hujjatlashtiradi; u Voxtral Realtimedan alohida.", "locale": "uz", "md_url": "https://ailoot.ai/models/uz/mistralai-voxtral-mini-transcribe/index.md", "title": "Mistral: Voxtral Mini Transcribe — Ailoot", "url": "https://ailoot.ai/models/uz/mistralai-voxtral-mini-transcribe/" }, "rawModel": { "about": "Voxtral Mini Transcribe 2 — Mistral AI kompaniyasining ishlab chiqaruvchi model kartasida voxtral-mini-2602 deb belgilangan, transkripsiyaga yo‘naltirilgan Voxtral nashri. U dastlabki Voxtral Mini 3B modelining kengroq savol-javob roli uchun emas, yozuvga asoslangan paketli transkripsiya uchun yaratilgan. Kirish audio, natija esa ixtiyoriy ravishda so‘zlovchi belgilari va vaqt ma’lumotlari bilan boyitilgan ko‘chirilgan matndir. Amaliy qo‘llanishlar yig‘ilish transkriptlari, intervyu tahlili, ko‘p tomonli qo‘ng‘iroq qaydlari va yozib olingan media bilan moslashtirilgan matnni o‘z ichiga oladi.\n\nIshlab chiqaruvchi transkript kim qachon gapirganini ko‘rsatishi uchun so‘zlovchilarni ajratish va boshlanish/tugash vaqtlarini hujjatlashtiradi. So‘z darajasidagi vaqt belgilari subtitrlar, audio qidiruv va matn parchasi bilan uning yozuvdagi o‘rnini moslashtirishni qo‘llaydi. Ishlab chiqaruvchi yo‘riqnomasi segment yoki so‘z darajasidagi vaqt belgilariga ruxsat beradi. Intervyu uchun foydali material — so‘zlovchiga biriktirilgan vaqtli parchalar ketma-ketligi; subtitr tayyorlashda esa so‘z yoki segment vaqti keyingi subtitrlash qadamiga yo‘l ko‘rsatishi mumkin, bu vaqtni oddiy transkript matnidan taxmin qilishga majbur qilmaydi.\n\nKontekst orqali yo‘naltirish nomlar, texnik atamalar va sohaga xos lug‘atning kerakli yozilishiga modelni yo‘naltiradigan 100 tagacha so‘z yoki iborani qabul qiladi. Mistral bu imkoniyat ingliz tili uchun optimallashtirilganini, boshqa tillardagi qo‘llov esa tajribaviy ekanini aytadi. Aloqasiz lug‘at o‘rniga yozuv mavzusidan aniq yo‘naltirilgan lug‘at ro‘yxatini tayyorlang. Mualliflik misolida texnik muhokamada uchrashi mumkin bo‘lgan loyiha nomlari va maxsus atamalar berilib, keyin tugallangan transkriptda ularning yozilishi tekshirilishi mumkin.\n\nUshbu nashr o‘n uch tilni qo‘llaydi: ingliz, xitoy, hind, ispan, arab, fransuz, portugal, rus, nemis, yapon, koreys, italyan va niderland. Ishlab chiqaruvchi shovqinga chidamlilik va bitta so‘rovda uch soatgacha yozuvlarni ham hujjatlashtiradi. Bular Mini Transcribe 2ning yozuv jarayoniga tegishli; dastlabki 2507 audioni tushunish modelining kontekst va davomiylik bayonotlari boshqa relizni ta’riflaydi. Tilni avtomatik aniqlash mavjud, yo‘riqnomada ma’lum audio tilini aniq berish transkripsiya aniqligini yaxshilashi mumkinligi aytiladi.\n\nHujjatlashtirilgan ishlab chiqaruvchi jarayonida audio yuklangan fayl, avval yuklangan fayl identifikatori yoki havola qilingan yozuv sifatida berilishi mumkin. Hamroh yuklash namoyishi MP3, WAV, M4A, FLAC va OGG yozuvlarini qabul qiladi; ko‘rsatilgan yuklash jarayoni uchun shu formatlardan birini tanlang. Yozuv dekodlanadigan bo‘lsin va tegishli nutqni o‘z ichiga olsin. Uzun materialda uning identifikatori va vaqt boshlanishini saqlang, shunda keyingi parchalar yoki tahrirlar ham manbaga kuzatib bog‘lanadi.\n\nTranskripsiya ma’lumotnomasi matn va aniqlangan tilni, so‘ralganda segmentlarni qaytaradi hamda oqimli transkripsiya hodisalarini alohida hujjatlashtiradi. Diarizatsiya ixtiyoriy va standart qiymati false. Yo‘riqnomada timestamp_granularities va tilni aniq belgilash hozircha mos emasligi qayd etiladi; shuning uchun ularni birlashtirish o‘rniga kerakli vaqtli jarayonni yoki tilni qo‘lda ko‘rsatishni tanlang. So‘zlovchi belgilari bilan transkripsiya, lug‘atga yo‘naltirish va vaqt belgilarini oddiy so‘rovdan avtomatik deb hisoblamay, ko‘zlangan natijaga qarab tanlash kerak.\n\nBir vaqtda ustma-ust nutq muhim cheklovdir: Mistral so‘zlovchilar bir vaqtda gapirganda model odatda bitta so‘zlovchini ko‘chirib yozishini aytadi. Demak, belgilangan transkriptni bir vaqtdagi har bir gapning to‘liq qaydi deb qabul qilmaslik kerak. Yig‘ilish qaydida murakkab ustma-ust nutq va muhim nomlar yoki sonlarni yozuv bilan solishtirib ko‘ring. Modelning maqsadi transkripsiya; xulosa, tarjima yoki tahlil transkriptga asoslangan alohida vazifa bo‘lishi mumkin. Voxtral Realtime alohida jonli transkripsiya kechikishi variantiga ega, nutq yaratish esa boshqa modellarga tegishli.\n\nNatijani keyingi qo‘llanishi uchun tayyorlang. Yig‘ilish jarayoni alohida bosqich qarorlarni ajratishidan oldin transkript, so‘zlovchi belgilari va vaqtni saqlashi mumkin; media jarayoni parchalarni topish va subtitr qoralamalarini yozish uchun vaqtdan foydalanishi mumkin; atamalarga boy yozuv esa aniq kontekst yo‘naltirish ro‘yxati va natijadagi yozilishlarni ko‘rib chiqishni o‘z ichiga olishi mumkin. Foydali yakuniy material — o‘z manba yozuvi va sozlangan metama’lumotlariga bog‘langan matn; bunda ushbu raqamlangan transkripsiya nashri dastlabki Mini modeli va yangilanib turadigan latest nomlaridan alohida saqlanadi.", "alias_of": null, "aliases": [], "author": "Mistral", "capabilities": { "context_length": 16384, "manufacturer_input": [ "audio" ], "manufacturer_output": [ "transcription" ] }, "card_routes": [ { "label": "Ultra", "rates": [ { "amount": "0.0001", "amount_unit": "usd_per_exact_native_unit", "billing_input": true, "estimate_only": false, "key": "audio_input_second", "label": "input audio second", "native_amount_usd_per_unit": "0.0001", "native_quantity": 1, "public_unit_label": "per input audio second", "quantity": 1, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "audio_input_second" } ], "summary": "Konfiguratsiya narxlari tafsilotlarda to‘liq ko‘rsatilgan." } ], "ctx": null, "formats": [ "transcriptions" ], "id": "mistralai/voxtral-mini-transcribe", "input": [ "audio" ], "kind": "audio", "max_out": null, "methods": [ { "available": null, "cache_read": null, "cache_write": null, "cache_write_1h": null, "contract": { "data": { "all_results": "Retain the complete response and headers, every actual output, original returned identifiers and all usage fields. Recover the original operation without submitting creation again.", "errors": [ { "code": null, "condition": "JSON tanasi yoki ochiq ko‘rsatilgan kanonik model ID si yaroqsiz.", "http_status": 400, "recovery": "Javobni saqlang va ko‘rsatilgan so‘rov maydonini tuzating.", "type": "invalid_request_error" }, { "code": null, "condition": "Ailoot API kaliti yaroqsiz.", "http_status": 401, "recovery": "Ruxsat berilgan Ailoot API kalitingizdan foydalaning.", "type": "authentication_error" }, { "code": null, "condition": "Kalit guruhi bu usulga ruxsat bermaydi.", "http_status": 403, "recovery": "Qaytarilgan xato tafsilotlarini saqlang.", "type": "permission_error" }, { "code": null, "condition": "Tanlangan usul uchun ruxsat etilgan yo‘nalish yo‘q.", "http_status": 404, "recovery": "Qaytarilgan xato tafsilotlarini saqlang.", "type": "not_found_error" }, { "code": null, "condition": "Qabul qilingan tarif zarur kirish miqdorini yoki chegarasini aniqlay olmaydi.", "http_status": 422, "recovery": "Javobni saqlang; qabul qilingan tarif talab qiladigan kirish ko‘rinishidan foydalaning.", "type": "price_unavailable" }, { "code": null, "condition": "Zarur saqlov, yo‘nalish, usul narxi yoki mablag‘ni band qilish imkoniyati mavjud emas.", "http_status": 503, "recovery": "To‘liq dastlabki javobni saqlang. Noaniq mablag‘ band qilish qayta yuborishga ruxsat bermaydi.", "type": null }, { "code": null, "condition": "Dastlabki natija, foydalanish ma’lumoti yoki hisob-kitobni tekshirish talab qilinadi.", "http_status": 502, "operation_id_source": "actual X-Client-Request-ID", "recovery": "Haqiqiy so‘rov ID si va dastlabki javobni saqlang. Mavjud, egalik qilinadigan yozuvni o‘qing; yaratishni qayta yubormang.", "response_headers": { "x-should-retry": "false" }, "type": "server_error" } ], "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 content URL" } ], "dedicated_method_polling_or_cancel": false, "mode": "synchronous_result_then_owned_library", "original_POST_adds_task_envelope": false, "status": [ { "http": "GET", "id_source": "exact task_id from an existing owned media record", "path": "/v1/media/tasks/{task_id}" } ], "unknown": "Haqiqiy X-Client-Request-ID va to‘liq javobni saqlang. Egalik qilinadigan dastlabki aktivlar va ularning aniq imzolangan mazmun URL larini o‘qing; natijasi noaniq yaratishni hech qachon qayta yubormang." }, "outputs": { "all_results": "To‘liq javob va sarlavhalarni, amalda qaytarilgan barcha natijalarni, dastlab qaytarilgan identifikatorlarni hamda barcha usage maydonlarini saqlang. Yaratish so‘rovini qayta yubormasdan dastlabki operatsiyani tiklang.", "family": "text", "fields": [ { "description": null, "name": "text (when present)", "type": null }, { "description": null, "name": "usage (when present)", "type": null } ], "result": "To‘liq dastlabki javob tanasi, holat va uzatilgan sarlavhalar. Bu ishlovchi universal JSON tuzilmasi, matn maydoni yoki vazifa o‘rovini qo‘shmaydi." }, "parameters": [ { "default_known": false, "enum": [ "mistralai/voxtral-mini-transcribe" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "default_known": false, "enum_known": false, "name": "input_audio", "required": true, "type": "object" } ], "request_schema": { "properties": { "input_audio": { "properties": { "data": { "contentEncoding": "base64", "type": "string" }, "format": { "type": "string" } }, "required": [ "data", "format" ], "type": "object" }, "model": { "enum": [ "mistralai/voxtral-mini-transcribe" ], "type": "string" } }, "required": [ "model", "input_audio" ], "type": "object" }, "schema_template": { "actual_file_preparation_required": true, "body": { "input_audio": { "data": "${BASE64_ACTUAL_WAV_BYTES}", "format": "wav" }, "model": "mistralai/voxtral-mini-transcribe" }, "content_type": "application/json" } }, "input": { "content_type": "application/json", "material_conditions": [ "Misol haqiqiy, bo‘sh bo‘lmagan PCM WAV faylingizni o‘qiydi, faylning barcha baytlarini base64 ko‘rinishida kodlaydi va input_audio.format qiymatini wav qilib yuboradi." ], "material_types": [ "audio" ], "required": [ "model", "input_audio" ] }, "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 content URL" } ], "dedicated_method_polling_or_cancel": false, "mode": "synchronous_result_then_owned_library", "original_POST_adds_task_envelope": false, "status": [ { "http": "GET", "id_source": "mavjud, egalik qilinadigan media yozuvidan aniq task_id", "path": "/v1/media/tasks/{task_id}" } ], "unknown": "Retain the actual X-Client-Request-ID and complete response. Read the original owned assets and their exact signed content URLs; never resubmit an uncertain creation." }, "method": { "http": "POST", "path": "/v1/audio/transcriptions" }, "output": { "all_results": "Retain the complete response and headers, every actual output, original returned identifiers and all usage fields. Recover the original operation without submitting creation again.", "family": "text", "fields": [ { "description": null, "name": "text (when present)", "type": null }, { "description": null, "name": "usage (when present)", "type": null } ], "result": "Complete original response body, status and forwarded headers. No universal JSON shape, text field or task envelope is added by this handler." } }, "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": "per input audio second" }, "label": "input audio second", "units": [ { "amount": "0.0001", "amount_unit": "usd_per_exact_native_unit", "billing_input": true, "estimate_only": false, "key": "audio_input_second", "label": "input audio second", "native_amount_usd_per_unit": "0.0001", "native_quantity": 1, "public_unit_label": "per input audio second", "quantity": 1, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "audio_input_second" } ] } ], "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_AUDIO_FILE:?Set the path to your actual PCM WAV recording}\"\nexport AILOOT_AUDIO_FILE\npython3 - <<'PY_REQUEST'\nimport base64, io, json, os, wave\nfrom pathlib import Path\naudio = Path(os.environ['AILOOT_AUDIO_FILE']).read_bytes()\nif not (audio[:4] == b'RIFF' and audio[8:12] == b'WAVE'):\n raise SystemExit('Supply your actual PCM WAV audio file')\nwith wave.open(io.BytesIO(audio), 'rb') as recording:\n if recording.getcomptype() != 'NONE' or recording.getnframes() <= 0:\n raise SystemExit('Supply a nonempty PCM WAV recording')\nrequest = {'model': 'mistralai/voxtral-mini-transcribe', 'input_audio': {'data': base64.b64encode(audio).decode('ascii'), 'format': 'wav'}}\nPath('request.json').write_text(json.dumps(request, ensure_ascii=False), encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/audio/transcriptions \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o response.bin\n# Retain the complete original response, headers and actual X-Client-Request-ID.\n# Read existing owned records for recovery; do not resubmit an uncertain operation.\n", "label": "curl · actual WAV file and complete original result", "language": "bash" } ], "family": "openai", "fast_multiplier": null, "flex_multiplier": null, "fmt": "transcriptions", "hints": [ "The example reads your actual nonempty PCM WAV file, encodes the complete file bytes as base64 and sends input_audio.format as wav.", "The format value in the example is the documented recipe; no model-specific format list, limit or default is asserted.", "Retain the complete response and headers, every actual output, original returned identifiers and all usage fields. Recover the original operation without submitting creation again." ], "http": "POST", "in": null, "input": [ "audio" ], "label": "Transkripsiya", "max_out": null, "max_reasoning_effort_multiplier": null, "method_aliases": [], "native_endpoint": "audio_transcriptions", "out": null, "output": [ "text" ], "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_second": 0.0001 } }, "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": "per input audio second" }, "label": "input audio second", "units": [ { "amount": "0.0001", "amount_unit": "usd_per_exact_native_unit", "billing_input": true, "estimate_only": false, "key": "audio_input_second", "label": "input audio second", "native_amount_usd_per_unit": "0.0001", "native_quantity": 1, "public_unit_label": "per input audio second", "quantity": 1, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "audio_input_second" } ] } ], "request_model_id": "mistralai/voxtral-mini-transcribe", "route_label": "Ultra", "status_reads": [ "GET /v1/media/tasks/{task_id}" ], "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": "0.0001", "amount_unit": "usd_per_exact_native_unit", "billing_input": true, "estimate_only": false, "key": "audio_input_second", "label": "input audio second", "native_amount_usd_per_unit": "0.0001", "native_quantity": 1, "public_unit_label": "per input audio second", "quantity": 1, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "audio_input_second" } ] } ], "model_aliases": [ { "canonical_model_id": "mistralai/voxtral-mini-transcribe", "request_model_id": "mistralai/voxtral-mini-transcribe", "route_label": "Ultra" } ], "name": "Mistral: Voxtral Mini Transcribe", "price": { "in": null, "in_label": null, "out": null, "out_label": null, "sort_in": null, "sort_out": null, "varies": true }, "short": "Voxtral Mini Transcribe 2 yozuvlarni so‘zlovchilarni ajratish, so‘z darajasidagi vaqt belgilari va lug‘atga yo‘naltirish bilan matnga aylantiradi. Mistral transkripsiyaga yo‘naltirilgan ushbu nashr uchun 13 til va uch soatgacha yozuvlarni hujjatlashtiradi; u Voxtral Realtimedan alohida." }, "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": "Voxtral Mini Transcribe 2 yozuvlarni so‘zlovchilarni ajratish, so‘z darajasidagi vaqt belgilari va lug‘atga yo‘naltirish bilan matnga aylantiradi. Mistral transkripsiyaga yo‘naltirilgan ushbu nashr uchun 13 til va uch soatgacha yozuvlarni hujjatlashtiradi; u Voxtral Realtimedan alohida.", "source": { "audit_sha256": "2e00086bcbfc28e64d0cebe97aa47c17d8d5618963027f8ffb9dc6123d7d25b1", "bridge_map_sha256": "1125275768b9636fc8461bc7da5061239a81ddfe508e2557843ca42c58ab0036", "raw_model_json_sha256": "921d93b87a1dfef5cd32c17301431a1aff8fc78e4e7c7b0fefe87f6e4c9670a5", "renderer_sha256": "aa8a0fca1bd770c042b64987512b6187fca2067aea3ddc877f68b163d80e7df6" }, "sourceRevision": "6b8d05ac1746a8e7d2bc7d7f092a55106d59f7cc04176258e2da0df181bf5a3e" }