{ "aboutHtml": "

Nova-3 — audioni matnga aylantirish uchun Deepgram’ning umumiy maqsadli nutqni tanish modeli. Ishlab chiqaruvchi uni yig‘ilishlar, tadbir subtitrlari, ko‘p so‘zlovchili yozuvlar va shovqin yoki uzoq mikrofon kabi murakkab sharoitlar uchun tavsiya qiladi; oldindan yozilgan yoki oqimli transkripsiyadan foydalaniladi. Foydali natija — manba audioga bog‘liq qolgan vaqt va ishonch ma’lumotli tanilgan nutq.

Til jarayonini tanlang

Hujjatlashtirilgan odatiy til ingliz tili. Bir tilli so‘rov aytilgan til yoki qo‘llanadigan locale’ni tanlaydi. Joriy umumiy model jadvalida ingliz tilining hududiy variantlari, ispan, fransuz, nemis, rus, portugal, yapon, italyan, niderland, arab tillari, xitoy yozuvlari va ko‘plab boshqa tillar, jumladan qozoq tili bor. Har qanday locale nomi qabul qilinadi deb o‘ylash o‘rniga ishlab chiqaruvchi qo‘llaydigan kodlardan tanlang.

Ko‘p tilli sozlama tillar almashishi uchun alohida jarayondir. Joriy Nova-3 jadvali shu rejim uchun o‘nta tilni ko‘rsatadi: ingliz, ispan, fransuz, nemis, hind, rus, portugal, yapon, italyan va niderland. Bu to‘plam kattaroq bir tilli ro‘yxat bilan bir xil emas. Qo‘llanadigan tillar almashadigan yozuvda butun suhbatni aloqasiz bitta til sozlamasiga majburlash o‘rniga ko‘p tilli rejimni tayyorlang. Tarjima yoki xulosa versiyasini tayyorlashdan oldin aytilgan nutqni saqlang.

Yozilgan audio va transkriptni tayyorlash

Deepgram fayl jarayoni yuklangan audio baytlarini yoki audio fayliga havolani qabul qiladi. So‘rov tugaganda qaytgan transkriptni saqlang; ishlab chiqaruvchi transkriptlarni keyin olish uchun saqlamaydi. Hujjatlashtirilgan odatiy kirish formatlari va kodlashlari MP3, MP4, MP2, AAC, WAV, FLAC, PCM, M4A, Ogg, Opus va WebM’ni o‘z ichiga oladi. Yozuv bilan haqiqiy format va kanal ma’lumotini saqlang. Yozuvga barqaror identifikator bering va natijani to‘g‘ri manba hamda kanal ma’lumotiga bog‘lang. Yig‘ilishda asl tovushni tinglab ishtirokchilar nomlari va texnik atamalarni tekshiring. Ma’ruza yoki tadbirda keyingi subtitr yoki qidiruv natijasi tegishli parchani topishi uchun audio ketma-ketligini saqlang.

Ishlab chiqaruvchining oldindan yozilgan audio qo‘llanmasi 2 GB maksimal fayl hajmini ko‘rsatadi va katta video faylidan audio oqimini ajratishni tavsiya qiladi. Nova so‘rovlari uchun o‘n daqiqali qayta ishlash taymauti ham hujjatlashtirilgan. Bu yozuv davomiyligining o‘n daqiqali maksimumi emas, so‘rov qancha vaqt qayta ishlanishiga tegishli. Foydali natija mo‘ljallangan yozuvning oxirini ham o‘z ichiga oladi; faqat qisman saqlangan transkriptni to‘liq matn deb bilmaslik kerak.

So‘zlar, vaqtlar va ishonchni o‘qing

Hujjatlashtirilgan JSON javobida transkript muqobillari va tanilgan so‘zlar bor; har bir so‘zning audio boshidan soniyalardagi boshlanish va tugash vaqti hamda ishonch qiymati beriladi. Ko‘p so‘zlovchili transkriptda ishlab chiqaruvchining ixtiyoriy so‘zlovchilarga ajratishi har bir so‘zga so‘zlovchi yorlig‘ini tayinlaydi. Oldindan yozilgan audio uchun so‘zlovchi bo‘yicha ishonch qiymati ham qaytadi; oqimli jarayonda so‘zlovchi yorlig‘i qaytadi. Shu yorliqlarni yozuvdagi ovozlar bilan tekshiring. Umumiy transkript ishonchi ham 0–1 shkalada beriladi. Aqlli formatlash so‘ralsa, natija tinish belgilari va bosh harflarni tinish belgili so‘zlar sifatida, o‘qiladigan paragraf ma’lumoti bilan berishi mumkin.

Maydonlarni ma’nosiga ko‘ra ishlating. So‘z vaqti tanilgan nutq joyini ko‘rsatadi; ishonch modelning ishonchlilik ko‘rsatkichi, qiyin nom yoki miqdor to‘g‘ri eshitilganining isboti emas. Subtitr tayyorlashda vaqtni tekshirilgan ifoda bilan saqlang va chegaralarni tovush bo‘yicha tekshiring. O‘qiladigan tahririy versiyada noaniq so‘zlarni sezdirmay mantiqli hikoyaga almashtirish o‘rniga, o‘zgarishlarni tanilgan transkriptdan farqlanadigan saqlang.

Oqimli tanish va yakuniy segmentlar

Nova oqimli jarayoni audio kelishi bilan vaqtinchalik va yakuniy matnni qaytaradi. is_final ko‘rsatkichi qayta tuzatilishi mumkin bo‘lgan matnni yakunlangan segmentdan ajratadi. speech_final ko‘rsatkichi nutq segmenti tugashini aniqlashga tegishli. Shu signallarni shunchaki bo‘sh bo‘lmagan transkript olishdan ajrating va to‘liq yozuv tayyorlashda yakuniy segmentlarni audio tartibida saqlang.

Nova-3 umumiy ASR modeli, modelning o‘zida suhbat navbatini aniqlashga ega alohida Flux suhbat modeli emas. Nova transkript yakuniyligini va nutq tugash nuqtalarini belgilaydi; Flux o‘z suhbat navbati holati hodisalarini beradi. Audio oldindan yozilganmi yoki jonli kelayaptimi — shunga qarab transkripsiya jarayonini tanlang; saqlanadigan artefakt sifatida haqiqiy yakuniy chiqishdan foydalaning.

Muhim lug‘at uchun keyterm

Nova-3’ning hujjatlashtirilgan Keyterm Prompting imkoniyati bir tilli va ko‘p tilli transkripsiyani qo‘llaydi, modelni qayta o‘qitmasdan tanishni muhim atamalarga yo‘naltiradi. Haqiqatan aytilishi mumkin bo‘lgan tegishli nomlar, mahsulot atamalari, qisqartmalar yoki ko‘p so‘zli iboralarni bering. Qo‘llanma jami keyterm kirishini 500 token bilan cheklaydi va oddiy so‘zlarni tanlamasdan qo‘shish o‘rniga eng muhim lug‘atga e’tibor qaratishni tavsiya qiladi.

Ishlab chiqaruvchi sintaksisi oddiy atamalar va har atama uchun alohida keyterm yozuvidan foydalanadi. Ko‘p so‘zli ibora bitta ibora bo‘lib qoladi. Eski keyword vaznlari yoki kuchaytirgichlar, alohida atamalarni vergul, nuqtali vergul yoki yangi qator bilan birlashtirish teng usul emas: interfeys ularni bitta literal qiymat sifatida qabul qilib, mo‘ljallangan kuchaytirishni bermasligi mumkin. Nomlarning bosh harflarini to‘g‘ri yozing, keyin transkriptni tekshiring; audio konteksti va aqlli formatlash yakuniy yozma shaklni baribir o‘zgartirishi mumkin.

Model oilasi chegaralari va foydali natijalar

Umumiy Nova-3 profili alohida nomlangan Medical va Pharma variantlaridan farq qiladi. Lug‘at bilan yo‘naltirish uni boshqa nashrga aylantirmaydi; maxsus modellarning til qamrovi yoki xulqini umumiy model uchun taxmin qilmaslik kerak. Qo‘shimcha transkript qayta ishlash imkoniyatlari ishlab chiqaruvchining nutq jarayonidagi tanlovlardir; tanish so‘ralmagan xulosa, tarjima yoki boshqa artefaktni yaratganining dalili emas.

Foydali Nova-3 natijasi qidiriladigan yig‘ilish transkripti, so‘z vaqtlari bilan subtitrga tayyor matn yoki ko‘p tilli suhbat yozuvi bo‘lishi mumkin. Audio identifikatori, tanlangan til jarayoni, yakuniy matn va foydali ishonch yoki vaqt maydonlarini saqlang. Noaniq nomlar, sonlar, ustma-ust ovozlar va til almashishlarini asl yozuv bo‘yicha tekshiring; keyingi mazmunni qayta ishlash bosqichi uchun haqiqatan tanilgan nutqni mavjud qoldiring.

", "aboutText": "Nova-3 — audioni matnga aylantirish uchun Deepgram’ning umumiy maqsadli nutqni tanish modeli. Ishlab chiqaruvchi uni yig‘ilishlar, tadbir subtitrlari, ko‘p so‘zlovchili yozuvlar va shovqin yoki uzoq mikrofon kabi murakkab sharoitlar uchun tavsiya qiladi; oldindan yozilgan yoki oqimli transkripsiyadan foydalaniladi. Foydali natija — manba audioga bog‘liq qolgan vaqt va ishonch ma’lumotli tanilgan nutq.\n\n### Til jarayonini tanlang\n\nHujjatlashtirilgan odatiy til ingliz tili. Bir tilli so‘rov aytilgan til yoki qo‘llanadigan locale’ni tanlaydi. Joriy umumiy model jadvalida ingliz tilining hududiy variantlari, ispan, fransuz, nemis, rus, portugal, yapon, italyan, niderland, arab tillari, xitoy yozuvlari va ko‘plab boshqa tillar, jumladan qozoq tili bor. Har qanday locale nomi qabul qilinadi deb o‘ylash o‘rniga ishlab chiqaruvchi qo‘llaydigan kodlardan tanlang.\n\nKo‘p tilli sozlama tillar almashishi uchun alohida jarayondir. Joriy Nova-3 jadvali shu rejim uchun o‘nta tilni ko‘rsatadi: ingliz, ispan, fransuz, nemis, hind, rus, portugal, yapon, italyan va niderland. Bu to‘plam kattaroq bir tilli ro‘yxat bilan bir xil emas. Qo‘llanadigan tillar almashadigan yozuvda butun suhbatni aloqasiz bitta til sozlamasiga majburlash o‘rniga ko‘p tilli rejimni tayyorlang. Tarjima yoki xulosa versiyasini tayyorlashdan oldin aytilgan nutqni saqlang.\n\n### Yozilgan audio va transkriptni tayyorlash\n\nDeepgram fayl jarayoni yuklangan audio baytlarini yoki audio fayliga havolani qabul qiladi. So‘rov tugaganda qaytgan transkriptni saqlang; ishlab chiqaruvchi transkriptlarni keyin olish uchun saqlamaydi. Hujjatlashtirilgan odatiy kirish formatlari va kodlashlari MP3, MP4, MP2, AAC, WAV, FLAC, PCM, M4A, Ogg, Opus va WebM’ni o‘z ichiga oladi. Yozuv bilan haqiqiy format va kanal ma’lumotini saqlang. Yozuvga barqaror identifikator bering va natijani to‘g‘ri manba hamda kanal ma’lumotiga bog‘lang. Yig‘ilishda asl tovushni tinglab ishtirokchilar nomlari va texnik atamalarni tekshiring. Ma’ruza yoki tadbirda keyingi subtitr yoki qidiruv natijasi tegishli parchani topishi uchun audio ketma-ketligini saqlang.\n\nIshlab chiqaruvchining oldindan yozilgan audio qo‘llanmasi 2 GB maksimal fayl hajmini ko‘rsatadi va katta video faylidan audio oqimini ajratishni tavsiya qiladi. Nova so‘rovlari uchun o‘n daqiqali qayta ishlash taymauti ham hujjatlashtirilgan. Bu yozuv davomiyligining o‘n daqiqali maksimumi emas, so‘rov qancha vaqt qayta ishlanishiga tegishli. Foydali natija mo‘ljallangan yozuvning oxirini ham o‘z ichiga oladi; faqat qisman saqlangan transkriptni to‘liq matn deb bilmaslik kerak.\n\n### So‘zlar, vaqtlar va ishonchni o‘qing\n\nHujjatlashtirilgan JSON javobida transkript muqobillari va tanilgan so‘zlar bor; har bir so‘zning audio boshidan soniyalardagi boshlanish va tugash vaqti hamda ishonch qiymati beriladi. Ko‘p so‘zlovchili transkriptda ishlab chiqaruvchining ixtiyoriy so‘zlovchilarga ajratishi har bir so‘zga so‘zlovchi yorlig‘ini tayinlaydi. Oldindan yozilgan audio uchun so‘zlovchi bo‘yicha ishonch qiymati ham qaytadi; oqimli jarayonda so‘zlovchi yorlig‘i qaytadi. Shu yorliqlarni yozuvdagi ovozlar bilan tekshiring. Umumiy transkript ishonchi ham 0–1 shkalada beriladi. Aqlli formatlash so‘ralsa, natija tinish belgilari va bosh harflarni tinish belgili so‘zlar sifatida, o‘qiladigan paragraf ma’lumoti bilan berishi mumkin.\n\nMaydonlarni ma’nosiga ko‘ra ishlating. So‘z vaqti tanilgan nutq joyini ko‘rsatadi; ishonch modelning ishonchlilik ko‘rsatkichi, qiyin nom yoki miqdor to‘g‘ri eshitilganining isboti emas. Subtitr tayyorlashda vaqtni tekshirilgan ifoda bilan saqlang va chegaralarni tovush bo‘yicha tekshiring. O‘qiladigan tahririy versiyada noaniq so‘zlarni sezdirmay mantiqli hikoyaga almashtirish o‘rniga, o‘zgarishlarni tanilgan transkriptdan farqlanadigan saqlang.\n\n### Oqimli tanish va yakuniy segmentlar\n\nNova oqimli jarayoni audio kelishi bilan vaqtinchalik va yakuniy matnni qaytaradi. is_final ko‘rsatkichi qayta tuzatilishi mumkin bo‘lgan matnni yakunlangan segmentdan ajratadi. speech_final ko‘rsatkichi nutq segmenti tugashini aniqlashga tegishli. Shu signallarni shunchaki bo‘sh bo‘lmagan transkript olishdan ajrating va to‘liq yozuv tayyorlashda yakuniy segmentlarni audio tartibida saqlang.\n\nNova-3 umumiy ASR modeli, modelning o‘zida suhbat navbatini aniqlashga ega alohida Flux suhbat modeli emas. Nova transkript yakuniyligini va nutq tugash nuqtalarini belgilaydi; Flux o‘z suhbat navbati holati hodisalarini beradi. Audio oldindan yozilganmi yoki jonli kelayaptimi — shunga qarab transkripsiya jarayonini tanlang; saqlanadigan artefakt sifatida haqiqiy yakuniy chiqishdan foydalaning.\n\n### Muhim lug‘at uchun keyterm\n\nNova-3’ning hujjatlashtirilgan Keyterm Prompting imkoniyati bir tilli va ko‘p tilli transkripsiyani qo‘llaydi, modelni qayta o‘qitmasdan tanishni muhim atamalarga yo‘naltiradi. Haqiqatan aytilishi mumkin bo‘lgan tegishli nomlar, mahsulot atamalari, qisqartmalar yoki ko‘p so‘zli iboralarni bering. Qo‘llanma jami keyterm kirishini 500 token bilan cheklaydi va oddiy so‘zlarni tanlamasdan qo‘shish o‘rniga eng muhim lug‘atga e’tibor qaratishni tavsiya qiladi.\n\nIshlab chiqaruvchi sintaksisi oddiy atamalar va har atama uchun alohida keyterm yozuvidan foydalanadi. Ko‘p so‘zli ibora bitta ibora bo‘lib qoladi. Eski keyword vaznlari yoki kuchaytirgichlar, alohida atamalarni vergul, nuqtali vergul yoki yangi qator bilan birlashtirish teng usul emas: interfeys ularni bitta literal qiymat sifatida qabul qilib, mo‘ljallangan kuchaytirishni bermasligi mumkin. Nomlarning bosh harflarini to‘g‘ri yozing, keyin transkriptni tekshiring; audio konteksti va aqlli formatlash yakuniy yozma shaklni baribir o‘zgartirishi mumkin.\n\n### Model oilasi chegaralari va foydali natijalar\n\nUmumiy Nova-3 profili alohida nomlangan Medical va Pharma variantlaridan farq qiladi. Lug‘at bilan yo‘naltirish uni boshqa nashrga aylantirmaydi; maxsus modellarning til qamrovi yoki xulqini umumiy model uchun taxmin qilmaslik kerak. Qo‘shimcha transkript qayta ishlash imkoniyatlari ishlab chiqaruvchining nutq jarayonidagi tanlovlardir; tanish so‘ralmagan xulosa, tarjima yoki boshqa artefaktni yaratganining dalili emas.\n\nFoydali Nova-3 natijasi qidiriladigan yig‘ilish transkripti, so‘z vaqtlari bilan subtitrga tayyor matn yoki ko‘p tilli suhbat yozuvi bo‘lishi mumkin. Audio identifikatori, tanlangan til jarayoni, yakuniy matn va foydali ishonch yoki vaqt maydonlarini saqlang. Noaniq nomlar, sonlar, ustma-ust ovozlar va til almashishlarini asl yozuv bo‘yicha tekshiring; keyingi mazmunni qayta ishlash bosqichi uchun haqiqatan tanilgan nutqni mavjud qoldiring.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "98770900661eb3ae5df6f90aea1aea2a811b75fae504a947429d3e096a87a81d", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "uz", "methods": [ { "html": "
•

Deepgram: Nova-3

Deepgram /deepgram/nova-3

Boshlash

Nova-3 — yozilgan va oqimda kelayotgan audioni matnga aylantirish uchun Deepgram’ning umumiy maqsadli modeli. U bir tilli nutqni tanish, tillar almashadigan belgilangan ko‘p tilli rejim va keyterm orqali yo‘naltirishni qo‘llab, so‘z vaqtlari hamda ishonch ma’lumotlari bilan transkript qaytaradi.

Qabul qilinadigan kirish ma’lumotlari
Audio
Natijalar
transcription
Model haqida

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

Nova-3 — audioni matnga aylantirish uchun Deepgram’ning umumiy maqsadli nutqni tanish modeli. Ishlab chiqaruvchi uni yig‘ilishlar, tadbir subtitrlari, ko‘p so‘zlovchili yozuvlar va shovqin yoki uzoq mikrofon kabi murakkab sharoitlar uchun tavsiya qiladi; oldindan yozilgan yoki oqimli transkripsiyadan foydalaniladi. Foydali natija — manba audioga bog‘liq qolgan vaqt va ishonch ma’lumotli tanilgan nutq.

Til jarayonini tanlang

Hujjatlashtirilgan odatiy til ingliz tili. Bir tilli so‘rov aytilgan til yoki qo‘llanadigan locale’ni tanlaydi. Joriy umumiy model jadvalida ingliz tilining hududiy variantlari, ispan, fransuz, nemis, rus, portugal, yapon, italyan, niderland, arab tillari, xitoy yozuvlari va ko‘plab boshqa tillar, jumladan qozoq tili bor. Har qanday locale nomi qabul qilinadi deb o‘ylash o‘rniga ishlab chiqaruvchi qo‘llaydigan kodlardan tanlang.

Ko‘p tilli sozlama tillar almashishi uchun alohida jarayondir. Joriy Nova-3 jadvali shu rejim uchun o‘nta tilni ko‘rsatadi: ingliz, ispan, fransuz, nemis, hind, rus, portugal, yapon, italyan va niderland. Bu to‘plam kattaroq bir tilli ro‘yxat bilan bir xil emas. Qo‘llanadigan tillar almashadigan yozuvda butun suhbatni aloqasiz bitta til sozlamasiga majburlash o‘rniga ko‘p tilli rejimni tayyorlang. Tarjima yoki xulosa versiyasini tayyorlashdan oldin aytilgan nutqni saqlang.

Yozilgan audio va transkriptni tayyorlash

Deepgram fayl jarayoni yuklangan audio baytlarini yoki audio fayliga havolani qabul qiladi. So‘rov tugaganda qaytgan transkriptni saqlang; ishlab chiqaruvchi transkriptlarni keyin olish uchun saqlamaydi. Hujjatlashtirilgan odatiy kirish formatlari va kodlashlari MP3, MP4, MP2, AAC, WAV, FLAC, PCM, M4A, Ogg, Opus va WebM’ni o‘z ichiga oladi. Yozuv bilan haqiqiy format va kanal ma’lumotini saqlang. Yozuvga barqaror identifikator bering va natijani to‘g‘ri manba hamda kanal ma’lumotiga bog‘lang. Yig‘ilishda asl tovushni tinglab ishtirokchilar nomlari va texnik atamalarni tekshiring. Ma’ruza yoki tadbirda keyingi subtitr yoki qidiruv natijasi tegishli parchani topishi uchun audio ketma-ketligini saqlang.

Ishlab chiqaruvchining oldindan yozilgan audio qo‘llanmasi 2 GB maksimal fayl hajmini ko‘rsatadi va katta video faylidan audio oqimini ajratishni tavsiya qiladi. Nova so‘rovlari uchun o‘n daqiqali qayta ishlash taymauti ham hujjatlashtirilgan. Bu yozuv davomiyligining o‘n daqiqali maksimumi emas, so‘rov qancha vaqt qayta ishlanishiga tegishli. Foydali natija mo‘ljallangan yozuvning oxirini ham o‘z ichiga oladi; faqat qisman saqlangan transkriptni to‘liq matn deb bilmaslik kerak.

So‘zlar, vaqtlar va ishonchni o‘qing

Hujjatlashtirilgan JSON javobida transkript muqobillari va tanilgan so‘zlar bor; har bir so‘zning audio boshidan soniyalardagi boshlanish va tugash vaqti hamda ishonch qiymati beriladi. Ko‘p so‘zlovchili transkriptda ishlab chiqaruvchining ixtiyoriy so‘zlovchilarga ajratishi har bir so‘zga so‘zlovchi yorlig‘ini tayinlaydi. Oldindan yozilgan audio uchun so‘zlovchi bo‘yicha ishonch qiymati ham qaytadi; oqimli jarayonda so‘zlovchi yorlig‘i qaytadi. Shu yorliqlarni yozuvdagi ovozlar bilan tekshiring. Umumiy transkript ishonchi ham 0–1 shkalada beriladi. Aqlli formatlash so‘ralsa, natija tinish belgilari va bosh harflarni tinish belgili so‘zlar sifatida, o‘qiladigan paragraf ma’lumoti bilan berishi mumkin.

Maydonlarni ma’nosiga ko‘ra ishlating. So‘z vaqti tanilgan nutq joyini ko‘rsatadi; ishonch modelning ishonchlilik ko‘rsatkichi, qiyin nom yoki miqdor to‘g‘ri eshitilganining isboti emas. Subtitr tayyorlashda vaqtni tekshirilgan ifoda bilan saqlang va chegaralarni tovush bo‘yicha tekshiring. O‘qiladigan tahririy versiyada noaniq so‘zlarni sezdirmay mantiqli hikoyaga almashtirish o‘rniga, o‘zgarishlarni tanilgan transkriptdan farqlanadigan saqlang.

Oqimli tanish va yakuniy segmentlar

Nova oqimli jarayoni audio kelishi bilan vaqtinchalik va yakuniy matnni qaytaradi. is_final ko‘rsatkichi qayta tuzatilishi mumkin bo‘lgan matnni yakunlangan segmentdan ajratadi. speech_final ko‘rsatkichi nutq segmenti tugashini aniqlashga tegishli. Shu signallarni shunchaki bo‘sh bo‘lmagan transkript olishdan ajrating va to‘liq yozuv tayyorlashda yakuniy segmentlarni audio tartibida saqlang.

Nova-3 umumiy ASR modeli, modelning o‘zida suhbat navbatini aniqlashga ega alohida Flux suhbat modeli emas. Nova transkript yakuniyligini va nutq tugash nuqtalarini belgilaydi; Flux o‘z suhbat navbati holati hodisalarini beradi. Audio oldindan yozilganmi yoki jonli kelayaptimi — shunga qarab transkripsiya jarayonini tanlang; saqlanadigan artefakt sifatida haqiqiy yakuniy chiqishdan foydalaning.

Muhim lug‘at uchun keyterm

Nova-3’ning hujjatlashtirilgan Keyterm Prompting imkoniyati bir tilli va ko‘p tilli transkripsiyani qo‘llaydi, modelni qayta o‘qitmasdan tanishni muhim atamalarga yo‘naltiradi. Haqiqatan aytilishi mumkin bo‘lgan tegishli nomlar, mahsulot atamalari, qisqartmalar yoki ko‘p so‘zli iboralarni bering. Qo‘llanma jami keyterm kirishini 500 token bilan cheklaydi va oddiy so‘zlarni tanlamasdan qo‘shish o‘rniga eng muhim lug‘atga e’tibor qaratishni tavsiya qiladi.

Ishlab chiqaruvchi sintaksisi oddiy atamalar va har atama uchun alohida keyterm yozuvidan foydalanadi. Ko‘p so‘zli ibora bitta ibora bo‘lib qoladi. Eski keyword vaznlari yoki kuchaytirgichlar, alohida atamalarni vergul, nuqtali vergul yoki yangi qator bilan birlashtirish teng usul emas: interfeys ularni bitta literal qiymat sifatida qabul qilib, mo‘ljallangan kuchaytirishni bermasligi mumkin. Nomlarning bosh harflarini to‘g‘ri yozing, keyin transkriptni tekshiring; audio konteksti va aqlli formatlash yakuniy yozma shaklni baribir o‘zgartirishi mumkin.

Model oilasi chegaralari va foydali natijalar

Umumiy Nova-3 profili alohida nomlangan Medical va Pharma variantlaridan farq qiladi. Lug‘at bilan yo‘naltirish uni boshqa nashrga aylantirmaydi; maxsus modellarning til qamrovi yoki xulqini umumiy model uchun taxmin qilmaslik kerak. Qo‘shimcha transkript qayta ishlash imkoniyatlari ishlab chiqaruvchining nutq jarayonidagi tanlovlardir; tanish so‘ralmagan xulosa, tarjima yoki boshqa artefaktni yaratganining dalili emas.

Foydali Nova-3 natijasi qidiriladigan yig‘ilish transkripti, so‘z vaqtlari bilan subtitrga tayyor matn yoki ko‘p tilli suhbat yozuvi bo‘lishi mumkin. Audio identifikatori, tanlangan til jarayoni, yakuniy matn va foydali ishonch yoki vaqt maydonlarini saqlang. Noaniq nomlar, sonlar, ustma-ust ovozlar va til almashishlarini asl yozuv bo‘yicha tekshiring; keyingi mazmunni qayta ishlash bosqichi uchun haqiqatan tanilgan nutqni mavjud qoldiring.

Ailoot da mavjud · kirish ma’lumotlari va usullar

Ailoot Ultra · Nutqni tanish POST /v1/audio/transcriptions
Kirish
audio
Chiqish
transcription
Chiqish formati
json
MaydonTurTalabQiymatlar va cheklovlarStandart
MaydonmodelTurstringTalabMajburiyQiymatlar va cheklovlar
deepgram/nova-3
Standart—
Maydoninput_audioTurobjectTalabMajburiyQiymatlar va cheklovlarStandart—
MaydonlanguageTurstringTalabIxtiyoriyQiymatlar va cheklovlarStandart—
MaydontemperatureTurnumberTalabIxtiyoriyQiymatlar va cheklovlar
Eng kam: 0
Eng ko‘p: 1
Standart—
Maydonresponse_formatTurstringTalabIxtiyoriyQiymatlar va cheklovlar
json, verbose_json
Standartjson
Maydontimestamp_granularitiesTurarrayTalabIxtiyoriyQiymatlar va cheklovlarStandart—
MaydonproviderTurobjectTalabIxtiyoriyQiymatlar va cheklovlarStandart—
Kirish materiallari birikmalari

speech_to_text · Majburiy: actual matching-format audio file

Usul parametrlari va hayot sikli
ParametrParametr talablari
Parametrcontent_typesParametr talablariapplication/json, multipart/form-data
ParametrrequiredParametr talablarimodel, input_audio
Parametrmaterial_typesParametr talablariaudio
ParametrJSON_audioParametr talablarihaqiqiy xom audio baytlari base64 ko‘rinishida va mos format
Parametrmultipart_requiredParametr talablarimodel, file
Parametrmultipart_cap_bytesParametr talablari26214400
Parametroptional_controlsParametr talablarilanguage, temperature, response_format, timestamp_granularities, provider
Parametrdefault_response_formatParametr talablarijson
Parametroptional_featuresParametr talablariBatafsil chiqish, diarize/keyterms va URL/kattaroq ichki audio uchun aynan shu model/provayder imkoniyati va tarifi zarur.

Hayot sikli: synchronous_result_then_owned_library

GET /v1/media/tasks/{task_id} · Amalda qaytarilgan task_id yoki media kutubxonasidagi yozuv

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

GET /v1/media/assets

GET /v1/media/assets/{asset_id}

Aniq model va hujjatdagi kirish maydonlaridan foydalaning.

To‘liq javobni, har bir haqiqiy chiqish natijasini va dastlab qaytarilgan ID larni saqlang.

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
SozlamaUltraTariflar jadvali—Hisob birligikirish audiosining soniyasi uchunTo‘lov
Kirish · Kirish audiosi soniyasi $0.0001433333333334 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 →

Ma’lumot uchun tarif tafsilotlari

Modelning ma’lumot jadvallari usul tanlash, narx hisobi yoki to‘lovlarni o‘zgartirmaydi. Amaldagi to‘lovlar tanlangan Ailoot usuli tariflari bo‘yicha hisoblanadi.

Deepgram: Nova-3

Sozlamalar bo‘yicha narxlar

SozlamaTo‘lovni hisoblash shartlariTo‘lov
SozlamaDeepgram: Nova-3 · Standart sozlamaTo‘lovni hisoblash shartlariStandart konfiguratsiyaTo‘lov
Kirish · Kirish audiosi soniyalari ≈0,000143 US$ kirish audiosining soniyasi uchun

So‘rov namunalari

Ailoot Ultra · Nutqni tanish

set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_AUDIO_FILE:?Set the path to your actual WAV recording}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\nimport base64\naudio=Path(os.environ['AILOOT_AUDIO_FILE']).read_bytes()\nif not (audio[:4]==b'RIFF' and audio[8:12]==b'WAVE'): raise SystemExit('Supply an actual WAV audio file')\nif len(audio)>26214400: raise SystemExit('Use a documented supported large-file flow')\nrequest={'model': 'deepgram/nova-3', 'input_audio': {'data': '${BASE64_ACTUAL_WAV_BYTES}', 'format': 'wav'}}\nrequest['input_audio']['data']=base64.b64encode(audio).decode('ascii')\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# Keep the complete original response and headers. Read every returned segment, word and usage field.\n# Preserve actual operation/task/asset IDs; continue reads of the original result without resubmitting.\n

Natijalarni olish va saqlash

Ailoot Ultra · Nutqni tanish

json

Barcha tayyor natijalarni saqlash

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

To‘liq dastlabki JSON, mavjud barcha matn/segmentlar/so‘zlar/so‘zlovchilar/vaqt belgilari va foydalanish ma’lumoti.

Asl javobni tekshirish kerak bo‘lsa

Dastlabki operation_id/X-Client-Request-ID va dastlabki javobni saqlang. Qayta yubormasdan haqiqiy, egalik qilinadigan vazifa/aktiv yozuvlarini o‘qing; audio holatini so‘rash uchun maxsus URL tuzilmaydi.

Javob maydonlari
MaydonTur
MaydontextTurstring
MaydonusageTurobject
Maydonsegments[]Turobject
Maydonwords[]Turobject

Taxalluslar

Model taxalluslari

Ailoot Ultra deepgram/nova-3

Usul yo‘llari taxalluslari

Yuqorida ko‘rsatilgan usul yo‘llaridan foydalaning.

Chaqirish uchun tegishli ID lar

deepgram/nova-3

", "method_identity": { "effective_request_model_id": "deepgram/nova-3", "fmt": "transcriptions", "http": "POST", "path": "/v1/audio/transcriptions", "request_model_id": "deepgram/nova-3", "route_label": "Ultra" }, "method_key": "Ultra|transcriptions|/v1/audio/transcriptions|deepgram%2Fnova-3", "ordinal": 0, "rawMethod": { "available": null, "cache_read": null, "cache_write": null, "cache_write_1h": null, "contract": { "data": { "all_results": "Complete original JSON, all available text/segments/words/speakers/timestamps and usage.", "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": "actual returned task_id or media library record", "path": "/v1/media/tasks/{task_id}" } ], "unknown": "Dastlabki operation_id/X-Client-Request-ID va dastlabki javobni saqlang. Qayta yubormasdan haqiqiy, egalik qilinadigan vazifa/aktiv yozuvlarini o‘qing; audio holatini so‘rash uchun maxsus URL tuzilmaydi." }, "material_combinations": [ { "content_types": [ "application/json", "multipart/form-data" ], "mode": "speech_to_text", "required": [ "actual matching-format audio file" ] } ], "outputs": { "all_results": "To‘liq dastlabki JSON, mavjud barcha matn/segmentlar/so‘zlar/so‘zlovchilar/vaqt belgilari va foydalanish ma’lumoti.", "family": "transcription", "fields": [ { "name": "text", "type": "string" }, { "name": "usage", "type": "object" }, { "name": "segments[]", "optional": true, "type": "object" }, { "name": "words[]", "optional": true, "type": "object" } ], "format": "json" }, "parameters": [ { "availability": "source_interface", "enum": [ "deepgram/nova-3" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "availability": "source_interface", "data_encoding": "base64 raw actual audio bytes, not data URI", "fields": [ "data", "format" ], "name": "input_audio", "required": true, "type": "object" }, { "availability": "retained_official_STTRequest", "description": "ISO-639-1 code; omitted means auto-detection", "name": "language", "required": false, "type": "string" }, { "availability": "retained_official_STTRequest", "maximum": 1, "minimum": 0, "name": "temperature", "required": false, "type": "number" }, { "availability": "retained_official_STTRequest", "default": "json", "default_known": true, "description": "verbose_json requires exact model/provider support", "enum": [ "json", "verbose_json" ], "enum_known": true, "name": "response_format", "required": false, "type": "string" }, { "availability": "retained_official_STTRequest", "description": "Only used with supported verbose_json", "items": { "enum": [ "segment", "word" ], "type": "string" }, "name": "timestamp_granularities", "required": false, "type": "array" }, { "availability": "retained_official_STTRequest", "description": "Data policy and exact provider options; order/only/ignore are not applied to STT", "name": "provider", "required": false, "type": "object" } ], "request_schema": { "properties": { "input_audio": { "properties": { "data": { "contentEncoding": "base64", "type": "string" }, "format": { "enum": [ "wav", "mp3", "flac", "m4a", "ogg", "webm", "aac" ], "type": "string" } }, "required": [ "data", "format" ], "type": "object" }, "language": { "description": "ISO-639-1 code; omitted means auto-detection", "type": "string" }, "model": { "enum": [ "deepgram/nova-3" ], "type": "string" }, "provider": { "description": "Data policy and exact provider options; order/only/ignore are not applied to STT", "properties": { "data_collection": { "enum": [ "allow", "deny", null ], "type": [ "string", "null" ] }, "options": { "type": "object" }, "zdr": { "type": [ "boolean", "null" ] } }, "type": "object" }, "response_format": { "default": "json", "description": "verbose_json requires exact model/provider support", "enum": [ "json", "verbose_json" ], "type": "string" }, "temperature": { "maximum": 1, "minimum": 0, "type": "number" }, "timestamp_granularities": { "description": "Only used with supported verbose_json", "items": { "enum": [ "segment", "word" ], "type": "string" }, "type": "array" } }, "required": [ "model", "input_audio" ], "type": "object" }, "schema_template": { "actual_file_preparation_required": true, "body": { "input_audio": { "data": "${BASE64_ACTUAL_WAV_BYTES}", "format": "wav" }, "model": "deepgram/nova-3" }, "content_type": "application/json" } }, "hints": [ "Aniq model va hujjatdagi kirish maydonlaridan foydalaning.", "To‘liq javobni, har bir haqiqiy chiqish natijasini va dastlab qaytarilgan ID larni saqlang." ], "input": { "JSON_audio": "haqiqiy xom audio baytlari base64 ko‘rinishida va mos format", "content_types": [ "application/json", "multipart/form-data" ], "default_response_format": "json", "material_types": [ "audio" ], "multipart_cap_bytes": 26214400, "multipart_required": [ "model", "file" ], "optional_controls": [ "language", "temperature", "response_format", "timestamp_granularities", "provider" ], "optional_features": "Batafsil chiqish, diarize/keyterms va URL/kattaroq ichki audio uchun aynan shu model/provayder imkoniyati va tarifi zarur.", "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 URL; never construct token" } ], "mode": "synchronous_result_then_owned_library", "operation_id_is_not_task_id": true, "status": [ { "http": "GET", "id_source": "Amalda qaytarilgan task_id yoki media kutubxonasidagi yozuv", "path": "/v1/media/tasks/{task_id}" } ], "unknown": "Retain original operation_id/X-Client-Request-ID and original response. Read actual owned task/asset records without resubmitting; no dedicated audio poll URL is constructed." }, "method": { "http": "POST", "path": "/v1/audio/transcriptions" }, "method_aliases": [], "operation_modes": [ "speech_to_text" ], "output": { "all_results": "Complete original JSON, all available text/segments/words/speakers/timestamps and usage.", "family": "transcription", "format": "json" } }, "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_basis": "actual physical units", "quoted_unit": "per audio input second" }, "label": "Ultra", "units": [ { "amount": "0.0001433333333334", "amount_unit": "usd_per_audio_input_second", "billing_input": true, "estimate_only": false, "key": "audio_input_second", "label": "audio input second", "native_amount_usd_per_unit": "0.0001433333333334", "native_quantity": 1, "public_unit_label": "per audio input 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: \"${AILOOT_AUDIO_FILE:?Set the path to your actual WAV recording}\"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\nimport base64\naudio=Path(os.environ['AILOOT_AUDIO_FILE']).read_bytes()\nif not (audio[:4]==b'RIFF' and audio[8:12]==b'WAVE'): raise SystemExit('Supply an actual WAV audio file')\nif len(audio)>26214400: raise SystemExit('Use a documented supported large-file flow')\nrequest={'model': 'deepgram/nova-3', 'input_audio': {'data': '${BASE64_ACTUAL_WAV_BYTES}', 'format': 'wav'}}\nrequest['input_audio']['data']=base64.b64encode(audio).decode('ascii')\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# Keep the complete original response and headers. Read every returned segment, word and usage field.\n# Preserve actual operation/task/asset IDs; continue reads of the original result without resubmitting.\n", "label": "curl · exact native body and complete result", "language": "bash" } ], "family": "openai", "fast_multiplier": null, "flex_multiplier": null, "fmt": "transcriptions", "hints": [ "Use the exact model and documented input fields.", "Keep the complete response, every actual output and original returned IDs." ], "http": "POST", "in": null, "input": [ "audio" ], "label": "Распознавание речи", "max_out": null, "max_reasoning_effort_multiplier": null, "method_aliases": [], "out": null, "output": [ "transcription" ], "path": "/v1/audio/transcriptions", "price_conditions": [ { "label": "Fast mode", "value": "Not specified", "when": "When fast mode is selected" }, { "label": "Flex mode", "value": "Not specified", "when": "When flex mode is selected" }, { "label": "Maximum reasoning effort", "value": "Not specified", "when": "When maximum reasoning effort uses the default adjustment" } ], "pricing": { "billing_mode": "per_request", "image_input_price": null, "image_output_price": null, "per_request_price": null, "unit_prices": { "audio_input_second": 0.0001433333333334 } }, "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_basis": "actual physical units", "quoted_unit": "per audio input second" }, "label": "Ultra", "units": [ { "amount": "0.0001433333333334", "amount_unit": "usd_per_audio_input_second", "billing_input": true, "estimate_only": false, "key": "audio_input_second", "label": "audio input second", "native_amount_usd_per_unit": "0.0001433333333334", "native_quantity": 1, "public_unit_label": "per audio input second", "quantity": "1", "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "audio_input_second" } ] } ], "request_model_id": "deepgram/nova-3", "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": "0.0001433333333334", "amount_unit": "usd_per_audio_input_second", "billing_input": true, "estimate_only": false, "key": "audio_input_second", "label": "audio input second", "native_amount_usd_per_unit": "0.0001433333333334", "native_quantity": 1, "public_unit_label": "per audio input second", "quantity": "1", "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "audio_input_second" } ] } } ], "model_id": "deepgram/nova-3", "nativeProvenance": { "input_facts_canonical_sha256": "aa58097e0c85a5f349b2be13cdd69941388028f3c53be79a0e5b86776d51e7dc", "input_html_sha256": "79ef5e8cae6ea9e54010d7a04322e6e5eea071bba0431c649e90091478bb38e1", "private_audit_sha256": "a98717ad5c6227f066f09acdb55d60da2eaa48c3284a8f33028f1d67d557da07", "role": "historical-normalized-input-audit-hashes", "schema": "ailoot-native-model-provenance-v2" }, "page": { "canonical": "https://ailoot.ai/models/uz/deepgram-nova-3/", "description": "Nova-3 — yozilgan va oqimda kelayotgan audioni matnga aylantirish uchun Deepgram’ning umumiy maqsadli modeli. U bir tilli nutqni tanish, tillar almashadigan belgilangan ko‘p tilli rejim va keyterm orqali yo‘naltirishni qo‘llab, so‘z vaqtlari hamda ishonch ma’lumotlari bilan transkript qaytaradi.", "locale": "uz", "md_url": "https://ailoot.ai/models/uz/deepgram-nova-3/index.md", "title": "Deepgram: Nova-3 — Ailoot", "url": "https://ailoot.ai/models/uz/deepgram-nova-3/" }, "rawModel": { "about": "Nova-3 — audioni matnga aylantirish uchun Deepgram’ning umumiy maqsadli nutqni tanish modeli. Ishlab chiqaruvchi uni yig‘ilishlar, tadbir subtitrlari, ko‘p so‘zlovchili yozuvlar va shovqin yoki uzoq mikrofon kabi murakkab sharoitlar uchun tavsiya qiladi; oldindan yozilgan yoki oqimli transkripsiyadan foydalaniladi. Foydali natija — manba audioga bog‘liq qolgan vaqt va ishonch ma’lumotli tanilgan nutq.\n\n### Til jarayonini tanlang\n\nHujjatlashtirilgan odatiy til ingliz tili. Bir tilli so‘rov aytilgan til yoki qo‘llanadigan locale’ni tanlaydi. Joriy umumiy model jadvalida ingliz tilining hududiy variantlari, ispan, fransuz, nemis, rus, portugal, yapon, italyan, niderland, arab tillari, xitoy yozuvlari va ko‘plab boshqa tillar, jumladan qozoq tili bor. Har qanday locale nomi qabul qilinadi deb o‘ylash o‘rniga ishlab chiqaruvchi qo‘llaydigan kodlardan tanlang.\n\nKo‘p tilli sozlama tillar almashishi uchun alohida jarayondir. Joriy Nova-3 jadvali shu rejim uchun o‘nta tilni ko‘rsatadi: ingliz, ispan, fransuz, nemis, hind, rus, portugal, yapon, italyan va niderland. Bu to‘plam kattaroq bir tilli ro‘yxat bilan bir xil emas. Qo‘llanadigan tillar almashadigan yozuvda butun suhbatni aloqasiz bitta til sozlamasiga majburlash o‘rniga ko‘p tilli rejimni tayyorlang. Tarjima yoki xulosa versiyasini tayyorlashdan oldin aytilgan nutqni saqlang.\n\n### Yozilgan audio va transkriptni tayyorlash\n\nDeepgram fayl jarayoni yuklangan audio baytlarini yoki audio fayliga havolani qabul qiladi. So‘rov tugaganda qaytgan transkriptni saqlang; ishlab chiqaruvchi transkriptlarni keyin olish uchun saqlamaydi. Hujjatlashtirilgan odatiy kirish formatlari va kodlashlari MP3, MP4, MP2, AAC, WAV, FLAC, PCM, M4A, Ogg, Opus va WebM’ni o‘z ichiga oladi. Yozuv bilan haqiqiy format va kanal ma’lumotini saqlang. Yozuvga barqaror identifikator bering va natijani to‘g‘ri manba hamda kanal ma’lumotiga bog‘lang. Yig‘ilishda asl tovushni tinglab ishtirokchilar nomlari va texnik atamalarni tekshiring. Ma’ruza yoki tadbirda keyingi subtitr yoki qidiruv natijasi tegishli parchani topishi uchun audio ketma-ketligini saqlang.\n\nIshlab chiqaruvchining oldindan yozilgan audio qo‘llanmasi 2 GB maksimal fayl hajmini ko‘rsatadi va katta video faylidan audio oqimini ajratishni tavsiya qiladi. Nova so‘rovlari uchun o‘n daqiqali qayta ishlash taymauti ham hujjatlashtirilgan. Bu yozuv davomiyligining o‘n daqiqali maksimumi emas, so‘rov qancha vaqt qayta ishlanishiga tegishli. Foydali natija mo‘ljallangan yozuvning oxirini ham o‘z ichiga oladi; faqat qisman saqlangan transkriptni to‘liq matn deb bilmaslik kerak.\n\n### So‘zlar, vaqtlar va ishonchni o‘qing\n\nHujjatlashtirilgan JSON javobida transkript muqobillari va tanilgan so‘zlar bor; har bir so‘zning audio boshidan soniyalardagi boshlanish va tugash vaqti hamda ishonch qiymati beriladi. Ko‘p so‘zlovchili transkriptda ishlab chiqaruvchining ixtiyoriy so‘zlovchilarga ajratishi har bir so‘zga so‘zlovchi yorlig‘ini tayinlaydi. Oldindan yozilgan audio uchun so‘zlovchi bo‘yicha ishonch qiymati ham qaytadi; oqimli jarayonda so‘zlovchi yorlig‘i qaytadi. Shu yorliqlarni yozuvdagi ovozlar bilan tekshiring. Umumiy transkript ishonchi ham 0–1 shkalada beriladi. Aqlli formatlash so‘ralsa, natija tinish belgilari va bosh harflarni tinish belgili so‘zlar sifatida, o‘qiladigan paragraf ma’lumoti bilan berishi mumkin.\n\nMaydonlarni ma’nosiga ko‘ra ishlating. So‘z vaqti tanilgan nutq joyini ko‘rsatadi; ishonch modelning ishonchlilik ko‘rsatkichi, qiyin nom yoki miqdor to‘g‘ri eshitilganining isboti emas. Subtitr tayyorlashda vaqtni tekshirilgan ifoda bilan saqlang va chegaralarni tovush bo‘yicha tekshiring. O‘qiladigan tahririy versiyada noaniq so‘zlarni sezdirmay mantiqli hikoyaga almashtirish o‘rniga, o‘zgarishlarni tanilgan transkriptdan farqlanadigan saqlang.\n\n### Oqimli tanish va yakuniy segmentlar\n\nNova oqimli jarayoni audio kelishi bilan vaqtinchalik va yakuniy matnni qaytaradi. is_final ko‘rsatkichi qayta tuzatilishi mumkin bo‘lgan matnni yakunlangan segmentdan ajratadi. speech_final ko‘rsatkichi nutq segmenti tugashini aniqlashga tegishli. Shu signallarni shunchaki bo‘sh bo‘lmagan transkript olishdan ajrating va to‘liq yozuv tayyorlashda yakuniy segmentlarni audio tartibida saqlang.\n\nNova-3 umumiy ASR modeli, modelning o‘zida suhbat navbatini aniqlashga ega alohida Flux suhbat modeli emas. Nova transkript yakuniyligini va nutq tugash nuqtalarini belgilaydi; Flux o‘z suhbat navbati holati hodisalarini beradi. Audio oldindan yozilganmi yoki jonli kelayaptimi — shunga qarab transkripsiya jarayonini tanlang; saqlanadigan artefakt sifatida haqiqiy yakuniy chiqishdan foydalaning.\n\n### Muhim lug‘at uchun keyterm\n\nNova-3’ning hujjatlashtirilgan Keyterm Prompting imkoniyati bir tilli va ko‘p tilli transkripsiyani qo‘llaydi, modelni qayta o‘qitmasdan tanishni muhim atamalarga yo‘naltiradi. Haqiqatan aytilishi mumkin bo‘lgan tegishli nomlar, mahsulot atamalari, qisqartmalar yoki ko‘p so‘zli iboralarni bering. Qo‘llanma jami keyterm kirishini 500 token bilan cheklaydi va oddiy so‘zlarni tanlamasdan qo‘shish o‘rniga eng muhim lug‘atga e’tibor qaratishni tavsiya qiladi.\n\nIshlab chiqaruvchi sintaksisi oddiy atamalar va har atama uchun alohida keyterm yozuvidan foydalanadi. Ko‘p so‘zli ibora bitta ibora bo‘lib qoladi. Eski keyword vaznlari yoki kuchaytirgichlar, alohida atamalarni vergul, nuqtali vergul yoki yangi qator bilan birlashtirish teng usul emas: interfeys ularni bitta literal qiymat sifatida qabul qilib, mo‘ljallangan kuchaytirishni bermasligi mumkin. Nomlarning bosh harflarini to‘g‘ri yozing, keyin transkriptni tekshiring; audio konteksti va aqlli formatlash yakuniy yozma shaklni baribir o‘zgartirishi mumkin.\n\n### Model oilasi chegaralari va foydali natijalar\n\nUmumiy Nova-3 profili alohida nomlangan Medical va Pharma variantlaridan farq qiladi. Lug‘at bilan yo‘naltirish uni boshqa nashrga aylantirmaydi; maxsus modellarning til qamrovi yoki xulqini umumiy model uchun taxmin qilmaslik kerak. Qo‘shimcha transkript qayta ishlash imkoniyatlari ishlab chiqaruvchining nutq jarayonidagi tanlovlardir; tanish so‘ralmagan xulosa, tarjima yoki boshqa artefaktni yaratganining dalili emas.\n\nFoydali Nova-3 natijasi qidiriladigan yig‘ilish transkripti, so‘z vaqtlari bilan subtitrga tayyor matn yoki ko‘p tilli suhbat yozuvi bo‘lishi mumkin. Audio identifikatori, tanlangan til jarayoni, yakuniy matn va foydali ishonch yoki vaqt maydonlarini saqlang. Noaniq nomlar, sonlar, ustma-ust ovozlar va til almashishlarini asl yozuv bo‘yicha tekshiring; keyingi mazmunni qayta ishlash bosqichi uchun haqiqatan tanilgan nutqni mavjud qoldiring.", "alias_of": null, "aliases": [], "author": "Deepgram", "available": null, "canonical_model": "deepgram/nova-3", "capabilities": { "context_length": 0, "manufacturer_input": [ "audio" ], "manufacturer_output": [ "transcription" ] }, "card_routes": [ { "label": "Ultra", "rates": [ { "amount": "0.0001433333333334", "amount_unit": "usd_per_audio_input_second", "billing_input": true, "estimate_only": false, "key": "audio_input_second", "label": "audio input second", "native_amount_usd_per_unit": "0.0001433333333334", "native_quantity": 1, "public_unit_label": "per audio input 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, "declared_tariff_references": [ { "client_selectable": false, "key": "c81fd216735cb75857ec", "label": "Deepgram: Nova-3", "profiles": [ { "basis": "", "dimensions": { "conditions": "Standart konfiguratsiya" }, "label": "Deepgram: Nova-3 · Standart sozlama", "units": [ { "amount": "0.0001433333333334", "amount_unit": "usd_per_exact_physical_unit", "billing_input": false, "key": "ce3ba3a9b22ee118a269edd4", "label": "Input audio seconds", "public_unit_label": "per input audio second", "quantity": "1", "rate_role": "declared_tariff_rate", "side": "in", "unit": "input_audio_second" } ] } ] } ], "entity_type": "model", "formats": [ "transcriptions" ], "id": "deepgram/nova-3", "input": [ "audio" ], "kind": "transcription", "max_out": null, "methods": [ { "available": null, "cache_read": null, "cache_write": null, "cache_write_1h": null, "contract": { "data": { "all_results": "Complete original JSON, all available text/segments/words/speakers/timestamps and usage.", "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": "actual returned task_id or media library record", "path": "/v1/media/tasks/{task_id}" } ], "unknown": "Dastlabki operation_id/X-Client-Request-ID va dastlabki javobni saqlang. Qayta yubormasdan haqiqiy, egalik qilinadigan vazifa/aktiv yozuvlarini o‘qing; audio holatini so‘rash uchun maxsus URL tuzilmaydi." }, "material_combinations": [ { "content_types": [ "application/json", "multipart/form-data" ], "mode": "speech_to_text", "required": [ "actual matching-format audio file" ] } ], "outputs": { "all_results": "To‘liq dastlabki JSON, mavjud barcha matn/segmentlar/so‘zlar/so‘zlovchilar/vaqt belgilari va foydalanish ma’lumoti.", "family": "transcription", "fields": [ { "name": "text", "type": "string" }, { "name": "usage", "type": "object" }, { "name": "segments[]", "optional": true, "type": "object" }, { "name": "words[]", "optional": true, "type": "object" } ], "format": "json" }, "parameters": [ { "availability": "source_interface", "enum": [ "deepgram/nova-3" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "availability": "source_interface", "data_encoding": "base64 raw actual audio bytes, not data URI", "fields": [ "data", "format" ], "name": "input_audio", "required": true, "type": "object" }, { "availability": "retained_official_STTRequest", "description": "ISO-639-1 code; omitted means auto-detection", "name": "language", "required": false, "type": "string" }, { "availability": "retained_official_STTRequest", "maximum": 1, "minimum": 0, "name": "temperature", "required": false, "type": "number" }, { "availability": "retained_official_STTRequest", "default": "json", "default_known": true, "description": "verbose_json requires exact model/provider support", "enum": [ "json", "verbose_json" ], "enum_known": true, "name": "response_format", "required": false, "type": "string" }, { "availability": "retained_official_STTRequest", "description": "Only used with supported verbose_json", "items": { "enum": [ "segment", "word" ], "type": "string" }, "name": "timestamp_granularities", "required": false, "type": "array" }, { "availability": "retained_official_STTRequest", "description": "Data policy and exact provider options; order/only/ignore are not applied to STT", "name": "provider", "required": false, "type": "object" } ], "request_schema": { "properties": { "input_audio": { "properties": { "data": { "contentEncoding": "base64", "type": "string" }, "format": { "enum": [ "wav", "mp3", "flac", "m4a", "ogg", "webm", "aac" ], "type": "string" } }, "required": [ "data", "format" ], "type": "object" }, "language": { "description": "ISO-639-1 code; omitted means auto-detection", "type": "string" }, "model": { "enum": [ "deepgram/nova-3" ], "type": "string" }, "provider": { "description": "Data policy and exact provider options; order/only/ignore are not applied to STT", "properties": { "data_collection": { "enum": [ "allow", "deny", null ], "type": [ "string", "null" ] }, "options": { "type": "object" }, "zdr": { "type": [ "boolean", "null" ] } }, "type": "object" }, "response_format": { "default": "json", "description": "verbose_json requires exact model/provider support", "enum": [ "json", "verbose_json" ], "type": "string" }, "temperature": { "maximum": 1, "minimum": 0, "type": "number" }, "timestamp_granularities": { "description": "Only used with supported verbose_json", "items": { "enum": [ "segment", "word" ], "type": "string" }, "type": "array" } }, "required": [ "model", "input_audio" ], "type": "object" }, "schema_template": { "actual_file_preparation_required": true, "body": { "input_audio": { "data": "${BASE64_ACTUAL_WAV_BYTES}", "format": "wav" }, "model": "deepgram/nova-3" }, "content_type": "application/json" } }, "hints": [ "Aniq model va hujjatdagi kirish maydonlaridan foydalaning.", "To‘liq javobni, har bir haqiqiy chiqish natijasini va dastlab qaytarilgan ID larni saqlang." ], "input": { "JSON_audio": "haqiqiy xom audio baytlari base64 ko‘rinishida va mos format", "content_types": [ "application/json", "multipart/form-data" ], "default_response_format": "json", "material_types": [ "audio" ], "multipart_cap_bytes": 26214400, "multipart_required": [ "model", "file" ], "optional_controls": [ "language", "temperature", "response_format", "timestamp_granularities", "provider" ], "optional_features": "Batafsil chiqish, diarize/keyterms va URL/kattaroq ichki audio uchun aynan shu model/provayder imkoniyati va tarifi zarur.", "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 URL; never construct token" } ], "mode": "synchronous_result_then_owned_library", "operation_id_is_not_task_id": true, "status": [ { "http": "GET", "id_source": "Amalda qaytarilgan task_id yoki media kutubxonasidagi yozuv", "path": "/v1/media/tasks/{task_id}" } ], "unknown": "Retain original operation_id/X-Client-Request-ID and original response. Read actual owned task/asset records without resubmitting; no dedicated audio poll URL is constructed." }, "method": { "http": "POST", "path": "/v1/audio/transcriptions" }, "method_aliases": [], "operation_modes": [ "speech_to_text" ], "output": { "all_results": "Complete original JSON, all available text/segments/words/speakers/timestamps and usage.", "family": "transcription", "format": "json" } }, "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_basis": "actual physical units", "quoted_unit": "per audio input second" }, "label": "Ultra", "units": [ { "amount": "0.0001433333333334", "amount_unit": "usd_per_audio_input_second", "billing_input": true, "estimate_only": false, "key": "audio_input_second", "label": "audio input second", "native_amount_usd_per_unit": "0.0001433333333334", "native_quantity": 1, "public_unit_label": "per audio input 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 WAV recording}\"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\nimport base64\naudio=Path(os.environ['AILOOT_AUDIO_FILE']).read_bytes()\nif not (audio[:4]==b'RIFF' and audio[8:12]==b'WAVE'): raise SystemExit('Supply an actual WAV audio file')\nif len(audio)>26214400: raise SystemExit('Use a documented supported large-file flow')\nrequest={'model': 'deepgram/nova-3', 'input_audio': {'data': '${BASE64_ACTUAL_WAV_BYTES}', 'format': 'wav'}}\nrequest['input_audio']['data']=base64.b64encode(audio).decode('ascii')\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# Keep the complete original response and headers. Read every returned segment, word and usage field.\n# Preserve actual operation/task/asset IDs; continue reads of the original result without resubmitting.\n", "label": "curl · exact native body and complete result", "language": "bash" } ], "family": "openai", "fast_multiplier": null, "flex_multiplier": null, "fmt": "transcriptions", "hints": [ "Use the exact model and documented input fields.", "Keep the complete response, every actual output and original returned IDs." ], "http": "POST", "in": null, "input": [ "audio" ], "label": "Распознавание речи", "max_out": null, "max_reasoning_effort_multiplier": null, "method_aliases": [], "out": null, "output": [ "transcription" ], "path": "/v1/audio/transcriptions", "price_conditions": [ { "label": "Fast mode", "value": "Not specified", "when": "When fast mode is selected" }, { "label": "Flex mode", "value": "Not specified", "when": "When flex mode is selected" }, { "label": "Maximum reasoning effort", "value": "Not specified", "when": "When maximum reasoning effort uses the default adjustment" } ], "pricing": { "billing_mode": "per_request", "image_input_price": null, "image_output_price": null, "per_request_price": null, "unit_prices": { "audio_input_second": 0.0001433333333334 } }, "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_basis": "actual physical units", "quoted_unit": "per audio input second" }, "label": "Ultra", "units": [ { "amount": "0.0001433333333334", "amount_unit": "usd_per_audio_input_second", "billing_input": true, "estimate_only": false, "key": "audio_input_second", "label": "audio input second", "native_amount_usd_per_unit": "0.0001433333333334", "native_quantity": 1, "public_unit_label": "per audio input second", "quantity": "1", "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "audio_input_second" } ] } ], "request_model_id": "deepgram/nova-3", "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": "0.0001433333333334", "amount_unit": "usd_per_audio_input_second", "billing_input": true, "estimate_only": false, "key": "audio_input_second", "label": "audio input second", "native_amount_usd_per_unit": "0.0001433333333334", "native_quantity": 1, "public_unit_label": "per audio input second", "quantity": "1", "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "audio_input_second" } ] } ], "model_aliases": [ { "canonical_model_id": "deepgram/nova-3", "request_model_id": "deepgram/nova-3", "route_label": "Ultra" } ], "name": "Deepgram: Nova-3", "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": { "language_variant": "monolingual", "multichannel_billing": "requires channel quantity; not implied by one file", "payg": true }, "label": "Ultra", "units": [ { "amount": "0.0086", "amount_unit": "usd_per_audio_input_minute", "conditions": { "language_variant": "monolingual", "multichannel_billing": "requires channel quantity; not implied by one file", "payg": true }, "key": "base", "label": "base", "profile_index": 0, "quantity": "1", "rate_role": "binding_component_rate", "side": "out", "unit": "audio_input_minute" } ] }, { "applicability": { "client_selectable": false, "native_profile_selection_pending": true, "scope": "manufacturer_reference" }, "dimensions": { "language_variant": "multilingual", "multichannel_billing": "requires channel quantity; not implied by one file", "payg": true }, "label": "Ultra", "units": [ { "amount": "0.0104", "amount_unit": "usd_per_audio_input_minute", "conditions": { "language_variant": "multilingual", "multichannel_billing": "requires channel quantity; not implied by one file", "payg": true }, "key": "base", "label": "base", "profile_index": 1, "quantity": "1", "rate_role": "binding_component_rate", "side": "out", "unit": "audio_input_minute" } ] }, { "applicability": { "client_selectable": false, "native_profile_selection_pending": true, "scope": "manufacturer_reference" }, "dimensions": { "adds_to_base": true, "feature_enabled": "redaction" }, "label": "Ultra", "units": [ { "amount": "0.0040", "amount_unit": "usd_per_audio_input_minute", "conditions": { "adds_to_base": true, "feature_enabled": "redaction" }, "key": "redaction", "label": "redaction", "profile_index": 2, "quantity": "1", "rate_role": "binding_component_rate", "side": "out", "unit": "audio_input_minute" } ] }, { "applicability": { "client_selectable": false, "native_profile_selection_pending": true, "scope": "manufacturer_reference" }, "dimensions": { "adds_to_base": true, "feature_enabled": "keyterm_prompting" }, "label": "Ultra", "units": [ { "amount": "0.0026", "amount_unit": "usd_per_audio_input_minute", "conditions": { "adds_to_base": true, "feature_enabled": "keyterm_prompting" }, "key": "keyterm_prompting", "label": "keyterm prompting", "profile_index": 3, "quantity": "1", "rate_role": "binding_component_rate", "side": "in", "unit": "audio_input_minute" } ] }, { "applicability": { "client_selectable": false, "native_profile_selection_pending": true, "scope": "manufacturer_reference" }, "dimensions": { "adds_to_base": true, "feature_enabled": "entity_detection" }, "label": "Ultra", "units": [ { "amount": "0.0034", "amount_unit": "usd_per_audio_input_minute", "conditions": { "adds_to_base": true, "feature_enabled": "entity_detection" }, "key": "entity_detection", "label": "entity detection", "profile_index": 4, "quantity": "1", "rate_role": "binding_component_rate", "side": "out", "unit": "audio_input_minute" } ] }, { "applicability": { "client_selectable": false, "native_profile_selection_pending": true, "scope": "manufacturer_reference" }, "dimensions": { "language_variant": "monolingual", "multichannel_billing": "requires channel quantity; not implied by one file", "payg": true }, "label": "Ultra", "units": [ { "amount": "0.0154", "amount_unit": "usd_per_audio_input_minute", "conditions": { "language_variant": "monolingual", "multichannel_billing": "requires channel quantity; not implied by one file", "payg": true }, "key": "base", "label": "base", "profile_index": 5, "quantity": "1", "rate_role": "binding_component_rate", "side": "out", "unit": "audio_input_minute" } ] }, { "applicability": { "client_selectable": false, "native_profile_selection_pending": true, "scope": "manufacturer_reference" }, "dimensions": { "language_variant": "multilingual", "multichannel_billing": "requires channel quantity; not implied by one file", "payg": true }, "label": "Ultra", "units": [ { "amount": "0.0184", "amount_unit": "usd_per_audio_input_minute", "conditions": { "language_variant": "multilingual", "multichannel_billing": "requires channel quantity; not implied by one file", "payg": true }, "key": "base", "label": "base", "profile_index": 6, "quantity": "1", "rate_role": "binding_component_rate", "side": "out", "unit": "audio_input_minute" } ] }, { "applicability": { "client_selectable": false, "native_profile_selection_pending": true, "scope": "manufacturer_reference" }, "dimensions": { "adds_to_base": true, "feature_enabled": "redaction" }, "label": "Ultra", "units": [ { "amount": "0.0040", "amount_unit": "usd_per_audio_input_minute", "conditions": { "adds_to_base": true, "feature_enabled": "redaction" }, "key": "redaction", "label": "redaction", "profile_index": 7, "quantity": "1", "rate_role": "binding_component_rate", "side": "out", "unit": "audio_input_minute" } ] }, { "applicability": { "client_selectable": false, "native_profile_selection_pending": true, "scope": "manufacturer_reference" }, "dimensions": { "adds_to_base": true, "feature_enabled": "keyterm_prompting" }, "label": "Ultra", "units": [ { "amount": "0.0026", "amount_unit": "usd_per_audio_input_minute", "conditions": { "adds_to_base": true, "feature_enabled": "keyterm_prompting" }, "key": "keyterm_prompting", "label": "keyterm prompting", "profile_index": 8, "quantity": "1", "rate_role": "binding_component_rate", "side": "in", "unit": "audio_input_minute" } ] }, { "applicability": { "client_selectable": false, "native_profile_selection_pending": true, "scope": "manufacturer_reference" }, "dimensions": { "adds_to_base": true, "feature_enabled": "entity_detection" }, "label": "Ultra", "units": [ { "amount": "0.0034", "amount_unit": "usd_per_audio_input_minute", "conditions": { "adds_to_base": true, "feature_enabled": "entity_detection" }, "key": "entity_detection", "label": "entity detection", "profile_index": 9, "quantity": "1", "rate_role": "binding_component_rate", "side": "out", "unit": "audio_input_minute" } ] }, { "applicability": { "client_selectable": false, "native_profile_selection_pending": true, "scope": "manufacturer_reference" }, "dimensions": { "adds_to_base": true, "feature_enabled": "speaker_diarization" }, "label": "Ultra", "units": [ { "amount": "0.0040", "amount_unit": "usd_per_audio_input_minute", "conditions": { "adds_to_base": true, "feature_enabled": "speaker_diarization" }, "key": "speaker_diarization", "label": "speaker diarization", "profile_index": 10, "quantity": "1", "rate_role": "binding_component_rate", "side": "out", "unit": "audio_input_minute" } ] } ], "public_id": "deepgram/nova-3", "short": "Nova-3 — yozilgan va oqimda kelayotgan audioni matnga aylantirish uchun Deepgram’ning umumiy maqsadli modeli. U bir tilli nutqni tanish, tillar almashadigan belgilangan ko‘p tilli rejim va keyterm orqali yo‘naltirishni qo‘llab, so‘z vaqtlari hamda ishonch ma’lumotlari bilan transkript qaytaradi." }, "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": "Nova-3 — yozilgan va oqimda kelayotgan audioni matnga aylantirish uchun Deepgram’ning umumiy maqsadli modeli. U bir tilli nutqni tanish, tillar almashadigan belgilangan ko‘p tilli rejim va keyterm orqali yo‘naltirishni qo‘llab, so‘z vaqtlari hamda ishonch ma’lumotlari bilan transkript qaytaradi.", "source": { "audit_sha256": "2e00086bcbfc28e64d0cebe97aa47c17d8d5618963027f8ffb9dc6123d7d25b1", "bridge_map_sha256": "1125275768b9636fc8461bc7da5061239a81ddfe508e2557843ca42c58ab0036", "raw_model_json_sha256": "c80736ea61cd58973a25de3b99eaf8d138ff72a913a7b2e8ff58aae1b254bf24", "renderer_sha256": "aa8a0fca1bd770c042b64987512b6187fca2067aea3ddc877f68b163d80e7df6" }, "sourceRevision": "8fa97b108616af3dc75e79750fdb57e4925a2134246dcf643e17a329c28db752" }