{ "aboutHtml": "

Nemotron 3.5 ASR Streaming Multilingual 0.6B — NVIDIA’ning jonli transkripsiya va yozib olingan audio vazifalari uchun mo‘ljallangan 600 million parametrli nutqni tanish modeli. U til identifikatoriga asoslangan yo‘naltirish orqali ingliz tilidagi oqimli modellar yo‘nalishini kengaytiradi. Nutq kirish tilidagi matnga aylanadi; tinish belgilari va bosh harflar chiqishning o‘zida shakllanadi.

Ishlab chiqaruvchining til qamrovi uch darajadan iborat. Transkripsiyaga tayyor o‘n to‘qqizta lokal variant AQSh va Buyuk Britaniya inglizchasi, AQSh va Ispaniya ispanchasi, Fransiya va Kanada fransuzchasi, italyan tili, Braziliya va Portugaliya portugalchasi, niderland, nemis, turk, rus, arab, hind, yapon, koreys, vetnam va ukrain tillarini qamrab oladi. Keng qamrovli o‘n uchta lokal variant polyak, shved, chex, norveg bokmol, daniya, bolgar, fin, xorvat, slovak, mandarin, venger, rumin va eston tillarini qo‘shadi. Ushbu 32 ta lokal variant birgalikda qo‘shimcha o‘qitishsiz transkripsiya yaratadi.

Moslashtirishga tayyor sakkizta lokal variant — yunon, litva, latish, malta, sloven, ivrit, tay va norveg nyunorsk — tokenizer tomonidan taniladi, lekin to‘liq transkripsiyani yoqish uchun tegishli soha ma’lumotlarida qo‘shimcha o‘qitishni talab qiladi. Demak, ishlab chiqaruvchining 40 ta lokal variant haqidagi soni qirqalasining ham tayyor holatdagi imkoniyati bir xil degani emas. Moslashtirilgan nazorat nuqtasi asosiy modeldan alohida materialdir.

Arxitektura 24 qatlamli, keshni hisobga oluvchi FastConformer enkoderini RNN-T dekoderi bilan birlashtiradi. U oldingi kadrlardagi enkoder attention va konvolyutsiya holatlarini saqlaydi va har bir yangi audio bo‘lagini ustma-ust oynalarni qayta-qayta hisoblamasdan qayta ishlaydi. Transkriptni kerakli tilga yo‘naltirish yoki modelga tilni o‘zi aniqlashga imkon berish uchun akustik ifoda bilan birga til identifikatori signali beriladi.

NVIDIA’ning NeMo sozlamalarida 80, 160, 320, 560 va 1120 millisekundlik bo‘lak o‘lchamlari hujjatlashtirilgan. Attention sozlamasi matn chiqarilishidan oldin bo‘lak qancha kelgusi audio olishini boshqaradi; bu vazifada kutish vaqti bilan akustik kontekst o‘rtasida muvozanat tanlashga imkon beradi. Bular butun jarayon bo‘yicha kafolatlangan javob vaqtlari emas, ishlab chiqaruvchining oqimli sozlamalaridir; amalga oshirilgan yechim ulardan o‘ziga mos kichikroq to‘plamni taqdim etishi mumkin.

Ishlab chiqaruvchi protsessorining 16 kHz diskretlash chastotasida mono WAV audio tayyorlang. Til ma’lum bo‘lsa, tegishli lokal variantni belgilab yo‘naltiring; avtomatik rejim gapirilayotgan tilni aniqlaydi. Asosiy jarayon misoli standart holatda AQSh inglizchasi ko‘rsatmasidan foydalanadi; shu sababli ko‘p tilli ishlashni o‘sha misoldan kelib chiqib taxmin qilish o‘rniga ataylab sozlash kerak.

Avtomatik rejimda ishlab chiqaruvchining ish jarayoni transkriptning oxirgi tinish belgisidan keyin til tegini qo‘shishi mumkin. Tegni saqlash turli tillardagi oqimni boshqaradigan ilovaga tilni bilish imkonini beradi; uni olib tashlash esa toza transkript matnini qaytaradi. Natijani ko‘rsatish yoki qayta ishlashda tanilgan so‘zlar, ularning tinish belgilari va ushbu til metama’lumoti o‘rtasidagi farqni saqlang.

Subtitr ilovasi audioni tartib bilan uzatishi, transkriptni yig‘ishi va tugallangan matndan ekranda ko‘rsatish yoki keyingi qayta ishlash uchun foydalanishi mumkin. Ovozli ilova tanilgan nutqni keyingi tilni tushunish bosqichiga uzatishi mumkin. Qo‘ng‘iroqlar tahlilida ismlar, sonlar va notanish atamalarni tekshirish mumkin bo‘lib qolishi uchun asl yozuv va transkript birga saqlanishi mumkin. ASR modeli transkript beradi; umumlashtirish, amallar va nutq yaratish ilovaning alohida bosqichlaridir.

NVIDIA modelni ochiq va xususiy nutq ma’lumotlari aralashmasida, tinish belgilari va harf registri to‘g‘ri qo‘yilgan matnga me’yorlashtirilgan inson hamda sintetik yorliqlar bilan o‘qitadi. Uning moslashtirish yo‘riqnomasi til yorliqlari va matn uslubini mos keltirishga, keyin o‘qitishga kiritilmagan audioni foydalanish ko‘zlangan oqimli sozlamada baholashga urg‘u beradi. Unda til, aksent va sohaga moslashtirish tasvirlanadi, ammo bunday moslashtirilgan natijalar asl nazorat nuqtasining xususiyatlari deb ko‘rsatilmaydi.

Model kartasi barcha holatlar uchun yagona davomiylik chegarasini e’lon qilish o‘rniga amaldagi yozuv uzunligini mavjud xotiraga bog‘laydi. Ko‘p tilli nashrni faqat ingliz tilidagi modeldan ajrating va tanlangan til hamda oqimli sozlamani transkripsiya natijasi bilan saqlang. Chiqish materiali umumiy suhbat javobi emas, balki ixtiyoriy ishlab chiqaruvchi til metama’lumoti qo‘shilgan tanilgan matndir.

", "aboutText": "Nemotron 3.5 ASR Streaming Multilingual 0.6B — NVIDIA’ning jonli transkripsiya va yozib olingan audio vazifalari uchun mo‘ljallangan 600 million parametrli nutqni tanish modeli. U til identifikatoriga asoslangan yo‘naltirish orqali ingliz tilidagi oqimli modellar yo‘nalishini kengaytiradi. Nutq kirish tilidagi matnga aylanadi; tinish belgilari va bosh harflar chiqishning o‘zida shakllanadi.\n\nIshlab chiqaruvchining til qamrovi uch darajadan iborat. Transkripsiyaga tayyor o‘n to‘qqizta lokal variant AQSh va Buyuk Britaniya inglizchasi, AQSh va Ispaniya ispanchasi, Fransiya va Kanada fransuzchasi, italyan tili, Braziliya va Portugaliya portugalchasi, niderland, nemis, turk, rus, arab, hind, yapon, koreys, vetnam va ukrain tillarini qamrab oladi. Keng qamrovli o‘n uchta lokal variant polyak, shved, chex, norveg bokmol, daniya, bolgar, fin, xorvat, slovak, mandarin, venger, rumin va eston tillarini qo‘shadi. Ushbu 32 ta lokal variant birgalikda qo‘shimcha o‘qitishsiz transkripsiya yaratadi.\n\nMoslashtirishga tayyor sakkizta lokal variant — yunon, litva, latish, malta, sloven, ivrit, tay va norveg nyunorsk — tokenizer tomonidan taniladi, lekin to‘liq transkripsiyani yoqish uchun tegishli soha ma’lumotlarida qo‘shimcha o‘qitishni talab qiladi. Demak, ishlab chiqaruvchining 40 ta lokal variant haqidagi soni qirqalasining ham tayyor holatdagi imkoniyati bir xil degani emas. Moslashtirilgan nazorat nuqtasi asosiy modeldan alohida materialdir.\n\nArxitektura 24 qatlamli, keshni hisobga oluvchi FastConformer enkoderini RNN-T dekoderi bilan birlashtiradi. U oldingi kadrlardagi enkoder attention va konvolyutsiya holatlarini saqlaydi va har bir yangi audio bo‘lagini ustma-ust oynalarni qayta-qayta hisoblamasdan qayta ishlaydi. Transkriptni kerakli tilga yo‘naltirish yoki modelga tilni o‘zi aniqlashga imkon berish uchun akustik ifoda bilan birga til identifikatori signali beriladi.\n\nNVIDIA’ning NeMo sozlamalarida 80, 160, 320, 560 va 1120 millisekundlik bo‘lak o‘lchamlari hujjatlashtirilgan. Attention sozlamasi matn chiqarilishidan oldin bo‘lak qancha kelgusi audio olishini boshqaradi; bu vazifada kutish vaqti bilan akustik kontekst o‘rtasida muvozanat tanlashga imkon beradi. Bular butun jarayon bo‘yicha kafolatlangan javob vaqtlari emas, ishlab chiqaruvchining oqimli sozlamalaridir; amalga oshirilgan yechim ulardan o‘ziga mos kichikroq to‘plamni taqdim etishi mumkin.\n\nIshlab chiqaruvchi protsessorining 16 kHz diskretlash chastotasida mono WAV audio tayyorlang. Til ma’lum bo‘lsa, tegishli lokal variantni belgilab yo‘naltiring; avtomatik rejim gapirilayotgan tilni aniqlaydi. Asosiy jarayon misoli standart holatda AQSh inglizchasi ko‘rsatmasidan foydalanadi; shu sababli ko‘p tilli ishlashni o‘sha misoldan kelib chiqib taxmin qilish o‘rniga ataylab sozlash kerak.\n\nAvtomatik rejimda ishlab chiqaruvchining ish jarayoni transkriptning oxirgi tinish belgisidan keyin til tegini qo‘shishi mumkin. Tegni saqlash turli tillardagi oqimni boshqaradigan ilovaga tilni bilish imkonini beradi; uni olib tashlash esa toza transkript matnini qaytaradi. Natijani ko‘rsatish yoki qayta ishlashda tanilgan so‘zlar, ularning tinish belgilari va ushbu til metama’lumoti o‘rtasidagi farqni saqlang.\n\nSubtitr ilovasi audioni tartib bilan uzatishi, transkriptni yig‘ishi va tugallangan matndan ekranda ko‘rsatish yoki keyingi qayta ishlash uchun foydalanishi mumkin. Ovozli ilova tanilgan nutqni keyingi tilni tushunish bosqichiga uzatishi mumkin. Qo‘ng‘iroqlar tahlilida ismlar, sonlar va notanish atamalarni tekshirish mumkin bo‘lib qolishi uchun asl yozuv va transkript birga saqlanishi mumkin. ASR modeli transkript beradi; umumlashtirish, amallar va nutq yaratish ilovaning alohida bosqichlaridir.\n\nNVIDIA modelni ochiq va xususiy nutq ma’lumotlari aralashmasida, tinish belgilari va harf registri to‘g‘ri qo‘yilgan matnga me’yorlashtirilgan inson hamda sintetik yorliqlar bilan o‘qitadi. Uning moslashtirish yo‘riqnomasi til yorliqlari va matn uslubini mos keltirishga, keyin o‘qitishga kiritilmagan audioni foydalanish ko‘zlangan oqimli sozlamada baholashga urg‘u beradi. Unda til, aksent va sohaga moslashtirish tasvirlanadi, ammo bunday moslashtirilgan natijalar asl nazorat nuqtasining xususiyatlari deb ko‘rsatilmaydi.\n\nModel kartasi barcha holatlar uchun yagona davomiylik chegarasini e’lon qilish o‘rniga amaldagi yozuv uzunligini mavjud xotiraga bog‘laydi. Ko‘p tilli nashrni faqat ingliz tilidagi modeldan ajrating va tanlangan til hamda oqimli sozlamani transkripsiya natijasi bilan saqlang. Chiqish materiali umumiy suhbat javobi emas, balki ixtiyoriy ishlab chiqaruvchi til metama’lumoti qo‘shilgan tanilgan matndir.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "4ab7a44b725ad975d697b5b179137650122306e73f560d088a5264b71bec6a4c", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "uz", "methods": [ { "html": "
NV

NVIDIA: Nemotron 3.5 ASR Streaming Multilingual 0.6B

NVIDIA /nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b

Boshlash

NVIDIA’ning Nemotron 3.5 ASR Streaming Multilingual 0.6B modeli keshni hisobga oluvchi oqimli enkoder yordamida nutqni tinish belgilari qo‘yilgan matnga aylantiradi. U tilni aniq ko‘rsatish yoki avtomatik aniqlashni qo‘llab-quvvatlaydi; 32 ta lokal variant transkripsiyaga tayyor, sakkiztasi esa moslashtirishni talab qiladi.

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.

Nemotron 3.5 ASR Streaming Multilingual 0.6B — NVIDIA’ning jonli transkripsiya va yozib olingan audio vazifalari uchun mo‘ljallangan 600 million parametrli nutqni tanish modeli. U til identifikatoriga asoslangan yo‘naltirish orqali ingliz tilidagi oqimli modellar yo‘nalishini kengaytiradi. Nutq kirish tilidagi matnga aylanadi; tinish belgilari va bosh harflar chiqishning o‘zida shakllanadi.

Ishlab chiqaruvchining til qamrovi uch darajadan iborat. Transkripsiyaga tayyor o‘n to‘qqizta lokal variant AQSh va Buyuk Britaniya inglizchasi, AQSh va Ispaniya ispanchasi, Fransiya va Kanada fransuzchasi, italyan tili, Braziliya va Portugaliya portugalchasi, niderland, nemis, turk, rus, arab, hind, yapon, koreys, vetnam va ukrain tillarini qamrab oladi. Keng qamrovli o‘n uchta lokal variant polyak, shved, chex, norveg bokmol, daniya, bolgar, fin, xorvat, slovak, mandarin, venger, rumin va eston tillarini qo‘shadi. Ushbu 32 ta lokal variant birgalikda qo‘shimcha o‘qitishsiz transkripsiya yaratadi.

Moslashtirishga tayyor sakkizta lokal variant — yunon, litva, latish, malta, sloven, ivrit, tay va norveg nyunorsk — tokenizer tomonidan taniladi, lekin to‘liq transkripsiyani yoqish uchun tegishli soha ma’lumotlarida qo‘shimcha o‘qitishni talab qiladi. Demak, ishlab chiqaruvchining 40 ta lokal variant haqidagi soni qirqalasining ham tayyor holatdagi imkoniyati bir xil degani emas. Moslashtirilgan nazorat nuqtasi asosiy modeldan alohida materialdir.

Arxitektura 24 qatlamli, keshni hisobga oluvchi FastConformer enkoderini RNN-T dekoderi bilan birlashtiradi. U oldingi kadrlardagi enkoder attention va konvolyutsiya holatlarini saqlaydi va har bir yangi audio bo‘lagini ustma-ust oynalarni qayta-qayta hisoblamasdan qayta ishlaydi. Transkriptni kerakli tilga yo‘naltirish yoki modelga tilni o‘zi aniqlashga imkon berish uchun akustik ifoda bilan birga til identifikatori signali beriladi.

NVIDIA’ning NeMo sozlamalarida 80, 160, 320, 560 va 1120 millisekundlik bo‘lak o‘lchamlari hujjatlashtirilgan. Attention sozlamasi matn chiqarilishidan oldin bo‘lak qancha kelgusi audio olishini boshqaradi; bu vazifada kutish vaqti bilan akustik kontekst o‘rtasida muvozanat tanlashga imkon beradi. Bular butun jarayon bo‘yicha kafolatlangan javob vaqtlari emas, ishlab chiqaruvchining oqimli sozlamalaridir; amalga oshirilgan yechim ulardan o‘ziga mos kichikroq to‘plamni taqdim etishi mumkin.

Ishlab chiqaruvchi protsessorining 16 kHz diskretlash chastotasida mono WAV audio tayyorlang. Til ma’lum bo‘lsa, tegishli lokal variantni belgilab yo‘naltiring; avtomatik rejim gapirilayotgan tilni aniqlaydi. Asosiy jarayon misoli standart holatda AQSh inglizchasi ko‘rsatmasidan foydalanadi; shu sababli ko‘p tilli ishlashni o‘sha misoldan kelib chiqib taxmin qilish o‘rniga ataylab sozlash kerak.

Avtomatik rejimda ishlab chiqaruvchining ish jarayoni transkriptning oxirgi tinish belgisidan keyin til tegini qo‘shishi mumkin. Tegni saqlash turli tillardagi oqimni boshqaradigan ilovaga tilni bilish imkonini beradi; uni olib tashlash esa toza transkript matnini qaytaradi. Natijani ko‘rsatish yoki qayta ishlashda tanilgan so‘zlar, ularning tinish belgilari va ushbu til metama’lumoti o‘rtasidagi farqni saqlang.

Subtitr ilovasi audioni tartib bilan uzatishi, transkriptni yig‘ishi va tugallangan matndan ekranda ko‘rsatish yoki keyingi qayta ishlash uchun foydalanishi mumkin. Ovozli ilova tanilgan nutqni keyingi tilni tushunish bosqichiga uzatishi mumkin. Qo‘ng‘iroqlar tahlilida ismlar, sonlar va notanish atamalarni tekshirish mumkin bo‘lib qolishi uchun asl yozuv va transkript birga saqlanishi mumkin. ASR modeli transkript beradi; umumlashtirish, amallar va nutq yaratish ilovaning alohida bosqichlaridir.

NVIDIA modelni ochiq va xususiy nutq ma’lumotlari aralashmasida, tinish belgilari va harf registri to‘g‘ri qo‘yilgan matnga me’yorlashtirilgan inson hamda sintetik yorliqlar bilan o‘qitadi. Uning moslashtirish yo‘riqnomasi til yorliqlari va matn uslubini mos keltirishga, keyin o‘qitishga kiritilmagan audioni foydalanish ko‘zlangan oqimli sozlamada baholashga urg‘u beradi. Unda til, aksent va sohaga moslashtirish tasvirlanadi, ammo bunday moslashtirilgan natijalar asl nazorat nuqtasining xususiyatlari deb ko‘rsatilmaydi.

Model kartasi barcha holatlar uchun yagona davomiylik chegarasini e’lon qilish o‘rniga amaldagi yozuv uzunligini mavjud xotiraga bog‘laydi. Ko‘p tilli nashrni faqat ingliz tilidagi modeldan ajrating va tanlangan til hamda oqimli sozlamani transkripsiya natijasi bilan saqlang. Chiqish materiali umumiy suhbat javobi emas, balki ixtiyoriy ishlab chiqaruvchi til metama’lumoti qo‘shilgan tanilgan matndir.

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
nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b
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—
Usul parametrlari va hayot sikli
ParametrParametr talablari
Parametrcontent_typeParametr talablariapplication/json
ParametrrequiredParametr talablarimodel, input_audio
Parametrmaterial_typesParametr talablariaudio
Parametrmaterial_conditionsParametr talablariHaqiqiy WAV faylini o‘qing va e’lon qilingan JSON input_audio uchun uning haqiqiy baytlarini kodlang; faqat JSON uchun berilgan aynan shu deklaratsiyada multipart yo‘nalishi taklif qilinmaydi.

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}

Tariflar

Yakuniy to‘lov qanday hisoblanadi

Ko‘rsatilgan tariflar xarajatni generatsiyadan oldin taxminiy hisoblash uchun xizmat qiladi. Yakuniy to‘lov dastlabki generatsiya uchun qayd etilgan xarajat asosida hisoblanadi. Natijaning o‘lchangan davomiyligi va oldindan taxmin qilingan miqdorlar haq undiriladigan yakuniy miqdor hisoblanmaydi.

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

Taqqoslash uchun taxminiy tariflar

Sozlamalar bo‘yicha narxlar

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

SozlamaTariflar jadvaliPrognoz miqdoriHisob birligiTo‘lov
SozlamaTokenlar uchun bazaviy tariflarTariflar jadvaliAsosiy tarifPrognoz miqdori—Hisob birligi—To‘lov
Kirish · Kirish tokenlari · Faqat taqqoslash uchun taxmin — / 1K token
Chiqish · Chiqish tokenlari · Faqat taqqoslash uchun taxmin — / 1K token
Kirish · Keshdan o‘qish · Faqat taqqoslash uchun taxmin — / 1K token
Kirish · Keshga yozish · Faqat taqqoslash uchun taxmin — / 1K token
Kirish · Keshga yozish, 1 soat · Faqat taqqoslash uchun taxmin — / 1K token
SozlamaKirish audiosi soniyasiTariflar jadvali—Prognoz miqdori—Hisob birligikirish audiosining soniyasi uchunTo‘lov
Kirish · Kirish audiosi soniyasi · Faqat taqqoslash uchun taxmin $0.00000666 kirish audiosining soniyasi uchun
SozlamaYaratishning taxminiy qiymatiTariflar jadvali—Prognoz miqdoribir generatsiya uchun taxminHisob birligi—To‘lov
Chiqish · Yaratishning taxminiy narxi · Faqat taqqoslash uchun taxmin $0.00000666 yaratishdan oldingi taxmin

Bu taxmin qo‘shimcha to‘lov ham, tugallangan generatsiya uchun qat’iy tarif ham emas.

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 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': 'nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b', '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 · Transkripsiya

Boshqa kontentni o‘qish
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/media/assets \\\n  -H "Authorization: Bearer $AILOOT_API_KEY" -o owned-assets.json\n# Preserve every returned asset and follow its exact signed content URL. Do not construct a signed token.\n
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

Qaytarilgan X-Client-Request-ID ni ma’lumotlarni solishtirib tekshirish uchun saqlang. Faqat amalda qaytarilgan task_id/asset_id qiymatlari bo‘yicha yoki o‘zingizga tegishli media kutubxonasidan ma’lumot o‘qing; operatsiya ID sidan vazifa URL manzilini hech qachon tuzmang va yaratish so‘rovini qayta yubormang.

Javob maydonlari
MaydonTur
MaydontextTur
MaydonusageTur
Maydonsegments[]Tur
Maydonwords[]Tur
Maydonspeaker fieldsTur
MaydontimestampsTur

Taxalluslar

Model taxalluslari

Ailoot Ultra nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b

Usul yo‘llari taxalluslari

Yuqorida ko‘rsatilgan usul yo‘llaridan foydalaning.

Chaqirish uchun tegishli ID lar

nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b

", "method_identity": { "effective_request_model_id": "nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b", "fmt": "transcriptions", "http": "POST", "path": "/v1/audio/transcriptions", "request_model_id": "nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b", "route_label": "Ultra" }, "method_key": "Ultra|transcriptions|/v1/audio/transcriptions|nvidia%2Fnemotron-3.5-asr-streaming-multilingual-0.6b", "ordinal": 0, "rawMethod": { "available": null, "billing_basis": { "basis": "original_invoice_usd", "description": "Ko‘rsatilgan tariflar xarajatni generatsiyadan oldin taxminiy hisoblash uchun xizmat qiladi. Yakuniy to‘lov dastlabki generatsiya uchun qayd etilgan xarajat asosida hisoblanadi. Natijaning o‘lchangan davomiyligi va oldindan taxmin qilingan miqdorlar haq undiriladigan yakuniy miqdor hisoblanmaydi.", "forecast_quantity_is_estimate": true, "physical_output_is_billable_quantity": false, "version": "original_invoice_usd_v1" }, "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.", "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": "Qaytarilgan X-Client-Request-ID ni ma’lumotlarni solishtirib tekshirish uchun saqlang. Faqat amalda qaytarilgan task_id/asset_id qiymatlari bo‘yicha yoki o‘zingizga tegishli media kutubxonasidan ma’lumot o‘qing; operatsiya ID sidan vazifa URL manzilini hech qachon tuzmang va yaratish so‘rovini 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", "type": null }, { "description": null, "name": "usage", "type": null }, { "description": null, "name": "segments[]", "type": null }, { "description": null, "name": "words[]", "type": null }, { "description": null, "name": "speaker fields", "type": null }, { "description": null, "name": "timestamps", "type": null } ] }, "parameters": [ { "enum": [ "nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "name": "input_audio", "required": true, "type": "object" }, { "name": "language", "required": false, "type": "string" }, { "maximum": 1, "minimum": 0, "name": "temperature", "required": false, "type": "number" }, { "default": "json", "default_known": true, "enum": [ "json", "verbose_json" ], "enum_known": true, "name": "response_format", "required": false, "type": "string" }, { "items": { "enum": [ "segment", "word" ], "type": "string" }, "name": "timestamp_granularities", "required": false, "type": "array" }, { "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": [ "nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b" ], "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": "nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b" }, "content_type": "application/json" } }, "input": { "content_type": "application/json", "material_conditions": [ "Haqiqiy WAV faylini o‘qing va e’lon qilingan JSON input_audio uchun uning haqiqiy baytlarini kodlang; faqat JSON uchun berilgan aynan shu deklaratsiyada multipart yo‘nalishi taklif qilinmaydi." ], "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 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": "Keep the returned X-Client-Request-ID for reconciliation. Read only actual returned task_id/asset_id values or the owned media library; never build a task URL from the operation ID and never resubmit 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", "type": null }, { "description": null, "name": "usage", "type": null }, { "description": null, "name": "segments[]", "type": null }, { "description": null, "name": "words[]", "type": null }, { "description": null, "name": "speaker fields", "type": null }, { "description": null, "name": "timestamps", "type": null } ] } }, "ctx": null, "declared_pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "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": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "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": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "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": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "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": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "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": true, "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": "0.00000666", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "audio_input_second", "label": "input audio second", "native_amount_usd_per_unit": "0.00000666", "native_quantity": 1, "public_unit_label": "per input audio second", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "audio_input_second" } ] }, { "basis": "Bu taxmin qo‘shimcha to‘lov ham, tugallangan generatsiya uchun qat’iy tarif ham emas.", "dimensions": { "forecast_quantity": "one generation estimate" }, "label": "Yaratishning taxminiy qiymati", "units": [ { "amount": "0.00000666", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "forecast_usd", "label": "Estimated generation cost", "native_amount_usd_per_unit": "0.00000666", "native_quantity": 1, "public_unit_label": "estimate before generation", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "request_estimate" } ] } ], "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_AUDIO_FILE:?Set the path to your actual WAV recording}\"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\nimport base64\naudio=Path(os.environ['AILOOT_AUDIO_FILE']).read_bytes()\nif not (audio[:4]==b'RIFF' and audio[8:12]==b'WAVE'): raise SystemExit('Supply an actual WAV audio file')\nif len(audio)>26214400: raise SystemExit('Use a documented supported large-file flow')\nrequest={'model': 'nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b', 'input_audio': {'data': '${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 $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o response.bin\n# Keep the complete original response and headers. Read every returned segment, word and usage field.\n# Preserve actual operation/task/asset IDs; continue reads of the original result without resubmitting.\n", "label": "curl · exact native body and complete result", "language": "bash" }, { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/media/assets \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" -o owned-assets.json\n# Preserve every returned asset and follow its exact signed content URL. Do not construct a signed token.\n", "label": "Read existing owned assets", "language": "bash" } ], "family": "openai", "fast_multiplier": null, "flex_multiplier": null, "fmt": "transcriptions", "hints": [ "Use the exact caller model ID and documented input representation.", "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": "original_invoice_usd", "image_input_price": null, "image_output_price": null }, "pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "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": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "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": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "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": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "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": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "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": true, "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": "0.00000666", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "audio_input_second", "label": "input audio second", "native_amount_usd_per_unit": "0.00000666", "native_quantity": 1, "public_unit_label": "per input audio second", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "audio_input_second" } ] }, { "basis": "This estimate is not an additional charge or a fixed rate for the completed generation.", "dimensions": { "forecast_quantity": "one generation estimate" }, "label": "Estimated generation cost", "units": [ { "amount": "0.00000666", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "forecast_usd", "label": "Estimated generation cost", "native_amount_usd_per_unit": "0.00000666", "native_quantity": 1, "public_unit_label": "estimate before generation", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "request_estimate" } ] } ], "request_model_id": "nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b", "route_label": "Ultra", "status_reads": [ "GET /v1/media/tasks/{task_id}" ], "tiers": [], "units": [ { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "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": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "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": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "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": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "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": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "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": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" }, { "amount": "0.00000666", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "audio_input_second", "label": "input audio second", "native_amount_usd_per_unit": "0.00000666", "native_quantity": 1, "public_unit_label": "per input audio second", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "audio_input_second" }, { "amount": "0.00000666", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "forecast_usd", "label": "Estimated generation cost", "native_amount_usd_per_unit": "0.00000666", "native_quantity": 1, "public_unit_label": "estimate before generation", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "request_estimate" } ] } } ], "model_id": "nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b", "nativeProvenance": { "input_facts_canonical_sha256": "b62202490754999335aee38563af68cda6f486820abc72bbd4480eeed123ca24", "input_html_sha256": "f2811ce8f30ec63e7c84c065d343965be9929c46af53a2620dc65d4483757936", "private_audit_sha256": "dd01d3d0c6d3c0b66061ce32fddf53fad5c2c418e89d882e1dab8e3ed382056a", "role": "historical-normalized-input-audit-hashes", "schema": "ailoot-native-model-provenance-v2" }, "page": { "canonical": "https://ailoot.ai/models/uz/nvidia-nemotron-3-5-asr-streaming-multilingual-0-6b/", "description": "NVIDIA’ning Nemotron 3.5 ASR Streaming Multilingual 0.6B modeli keshni hisobga oluvchi oqimli enkoder yordamida nutqni tinish belgilari qo‘yilgan matnga aylantiradi. U tilni aniq ko‘rsatish yoki avtomatik aniqlashni qo‘llab-quvvatlaydi; 32 ta lokal variant transkripsiyaga tayyor, sakkiztasi esa moslashtirishni talab qiladi.", "locale": "uz", "md_url": "https://ailoot.ai/models/uz/nvidia-nemotron-3-5-asr-streaming-multilingual-0-6b/index.md", "title": "NVIDIA: Nemotron 3.5 ASR Streaming Multilingual 0.6B — Ailoot", "url": "https://ailoot.ai/models/uz/nvidia-nemotron-3-5-asr-streaming-multilingual-0-6b/" }, "rawModel": { "about": "Nemotron 3.5 ASR Streaming Multilingual 0.6B — NVIDIA’ning jonli transkripsiya va yozib olingan audio vazifalari uchun mo‘ljallangan 600 million parametrli nutqni tanish modeli. U til identifikatoriga asoslangan yo‘naltirish orqali ingliz tilidagi oqimli modellar yo‘nalishini kengaytiradi. Nutq kirish tilidagi matnga aylanadi; tinish belgilari va bosh harflar chiqishning o‘zida shakllanadi.\n\nIshlab chiqaruvchining til qamrovi uch darajadan iborat. Transkripsiyaga tayyor o‘n to‘qqizta lokal variant AQSh va Buyuk Britaniya inglizchasi, AQSh va Ispaniya ispanchasi, Fransiya va Kanada fransuzchasi, italyan tili, Braziliya va Portugaliya portugalchasi, niderland, nemis, turk, rus, arab, hind, yapon, koreys, vetnam va ukrain tillarini qamrab oladi. Keng qamrovli o‘n uchta lokal variant polyak, shved, chex, norveg bokmol, daniya, bolgar, fin, xorvat, slovak, mandarin, venger, rumin va eston tillarini qo‘shadi. Ushbu 32 ta lokal variant birgalikda qo‘shimcha o‘qitishsiz transkripsiya yaratadi.\n\nMoslashtirishga tayyor sakkizta lokal variant — yunon, litva, latish, malta, sloven, ivrit, tay va norveg nyunorsk — tokenizer tomonidan taniladi, lekin to‘liq transkripsiyani yoqish uchun tegishli soha ma’lumotlarida qo‘shimcha o‘qitishni talab qiladi. Demak, ishlab chiqaruvchining 40 ta lokal variant haqidagi soni qirqalasining ham tayyor holatdagi imkoniyati bir xil degani emas. Moslashtirilgan nazorat nuqtasi asosiy modeldan alohida materialdir.\n\nArxitektura 24 qatlamli, keshni hisobga oluvchi FastConformer enkoderini RNN-T dekoderi bilan birlashtiradi. U oldingi kadrlardagi enkoder attention va konvolyutsiya holatlarini saqlaydi va har bir yangi audio bo‘lagini ustma-ust oynalarni qayta-qayta hisoblamasdan qayta ishlaydi. Transkriptni kerakli tilga yo‘naltirish yoki modelga tilni o‘zi aniqlashga imkon berish uchun akustik ifoda bilan birga til identifikatori signali beriladi.\n\nNVIDIA’ning NeMo sozlamalarida 80, 160, 320, 560 va 1120 millisekundlik bo‘lak o‘lchamlari hujjatlashtirilgan. Attention sozlamasi matn chiqarilishidan oldin bo‘lak qancha kelgusi audio olishini boshqaradi; bu vazifada kutish vaqti bilan akustik kontekst o‘rtasida muvozanat tanlashga imkon beradi. Bular butun jarayon bo‘yicha kafolatlangan javob vaqtlari emas, ishlab chiqaruvchining oqimli sozlamalaridir; amalga oshirilgan yechim ulardan o‘ziga mos kichikroq to‘plamni taqdim etishi mumkin.\n\nIshlab chiqaruvchi protsessorining 16 kHz diskretlash chastotasida mono WAV audio tayyorlang. Til ma’lum bo‘lsa, tegishli lokal variantni belgilab yo‘naltiring; avtomatik rejim gapirilayotgan tilni aniqlaydi. Asosiy jarayon misoli standart holatda AQSh inglizchasi ko‘rsatmasidan foydalanadi; shu sababli ko‘p tilli ishlashni o‘sha misoldan kelib chiqib taxmin qilish o‘rniga ataylab sozlash kerak.\n\nAvtomatik rejimda ishlab chiqaruvchining ish jarayoni transkriptning oxirgi tinish belgisidan keyin til tegini qo‘shishi mumkin. Tegni saqlash turli tillardagi oqimni boshqaradigan ilovaga tilni bilish imkonini beradi; uni olib tashlash esa toza transkript matnini qaytaradi. Natijani ko‘rsatish yoki qayta ishlashda tanilgan so‘zlar, ularning tinish belgilari va ushbu til metama’lumoti o‘rtasidagi farqni saqlang.\n\nSubtitr ilovasi audioni tartib bilan uzatishi, transkriptni yig‘ishi va tugallangan matndan ekranda ko‘rsatish yoki keyingi qayta ishlash uchun foydalanishi mumkin. Ovozli ilova tanilgan nutqni keyingi tilni tushunish bosqichiga uzatishi mumkin. Qo‘ng‘iroqlar tahlilida ismlar, sonlar va notanish atamalarni tekshirish mumkin bo‘lib qolishi uchun asl yozuv va transkript birga saqlanishi mumkin. ASR modeli transkript beradi; umumlashtirish, amallar va nutq yaratish ilovaning alohida bosqichlaridir.\n\nNVIDIA modelni ochiq va xususiy nutq ma’lumotlari aralashmasida, tinish belgilari va harf registri to‘g‘ri qo‘yilgan matnga me’yorlashtirilgan inson hamda sintetik yorliqlar bilan o‘qitadi. Uning moslashtirish yo‘riqnomasi til yorliqlari va matn uslubini mos keltirishga, keyin o‘qitishga kiritilmagan audioni foydalanish ko‘zlangan oqimli sozlamada baholashga urg‘u beradi. Unda til, aksent va sohaga moslashtirish tasvirlanadi, ammo bunday moslashtirilgan natijalar asl nazorat nuqtasining xususiyatlari deb ko‘rsatilmaydi.\n\nModel kartasi barcha holatlar uchun yagona davomiylik chegarasini e’lon qilish o‘rniga amaldagi yozuv uzunligini mavjud xotiraga bog‘laydi. Ko‘p tilli nashrni faqat ingliz tilidagi modeldan ajrating va tanlangan til hamda oqimli sozlamani transkripsiya natijasi bilan saqlang. Chiqish materiali umumiy suhbat javobi emas, balki ixtiyoriy ishlab chiqaruvchi til metama’lumoti qo‘shilgan tanilgan matndir.", "alias_of": null, "aliases": [], "author": "NVIDIA", "capabilities": { "context_length": 0, "manufacturer_input": [ "audio" ], "manufacturer_output": [ "transcription" ] }, "card_routes": [ { "label": "Ultra", "rates": [ { "amount": "0.00000666", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "forecast_usd", "label": "Estimated generation cost", "native_amount_usd_per_unit": "0.00000666", "native_quantity": 1, "public_unit_label": "estimate before generation", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "request_estimate" } ], "summary": "Konfiguratsiya narxlari tafsilotlarda to‘liq ko‘rsatilgan." } ], "ctx": null, "formats": [ "transcriptions" ], "id": "nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b", "input": [ "audio" ], "kind": "audio", "max_out": null, "methods": [ { "available": null, "billing_basis": { "basis": "original_invoice_usd", "description": "Ko‘rsatilgan tariflar xarajatni generatsiyadan oldin taxminiy hisoblash uchun xizmat qiladi. Yakuniy to‘lov dastlabki generatsiya uchun qayd etilgan xarajat asosida hisoblanadi. Natijaning o‘lchangan davomiyligi va oldindan taxmin qilingan miqdorlar haq undiriladigan yakuniy miqdor hisoblanmaydi.", "forecast_quantity_is_estimate": true, "physical_output_is_billable_quantity": false, "version": "original_invoice_usd_v1" }, "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.", "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": "Qaytarilgan X-Client-Request-ID ni ma’lumotlarni solishtirib tekshirish uchun saqlang. Faqat amalda qaytarilgan task_id/asset_id qiymatlari bo‘yicha yoki o‘zingizga tegishli media kutubxonasidan ma’lumot o‘qing; operatsiya ID sidan vazifa URL manzilini hech qachon tuzmang va yaratish so‘rovini 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", "type": null }, { "description": null, "name": "usage", "type": null }, { "description": null, "name": "segments[]", "type": null }, { "description": null, "name": "words[]", "type": null }, { "description": null, "name": "speaker fields", "type": null }, { "description": null, "name": "timestamps", "type": null } ] }, "parameters": [ { "enum": [ "nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "name": "input_audio", "required": true, "type": "object" }, { "name": "language", "required": false, "type": "string" }, { "maximum": 1, "minimum": 0, "name": "temperature", "required": false, "type": "number" }, { "default": "json", "default_known": true, "enum": [ "json", "verbose_json" ], "enum_known": true, "name": "response_format", "required": false, "type": "string" }, { "items": { "enum": [ "segment", "word" ], "type": "string" }, "name": "timestamp_granularities", "required": false, "type": "array" }, { "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": [ "nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b" ], "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": "nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b" }, "content_type": "application/json" } }, "input": { "content_type": "application/json", "material_conditions": [ "Haqiqiy WAV faylini o‘qing va e’lon qilingan JSON input_audio uchun uning haqiqiy baytlarini kodlang; faqat JSON uchun berilgan aynan shu deklaratsiyada multipart yo‘nalishi taklif qilinmaydi." ], "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 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": "Keep the returned X-Client-Request-ID for reconciliation. Read only actual returned task_id/asset_id values or the owned media library; never build a task URL from the operation ID and never resubmit 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", "type": null }, { "description": null, "name": "usage", "type": null }, { "description": null, "name": "segments[]", "type": null }, { "description": null, "name": "words[]", "type": null }, { "description": null, "name": "speaker fields", "type": null }, { "description": null, "name": "timestamps", "type": null } ] } }, "ctx": null, "declared_pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "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": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "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": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "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": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "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": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "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": true, "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": "0.00000666", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "audio_input_second", "label": "input audio second", "native_amount_usd_per_unit": "0.00000666", "native_quantity": 1, "public_unit_label": "per input audio second", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "audio_input_second" } ] }, { "basis": "Bu taxmin qo‘shimcha to‘lov ham, tugallangan generatsiya uchun qat’iy tarif ham emas.", "dimensions": { "forecast_quantity": "one generation estimate" }, "label": "Yaratishning taxminiy qiymati", "units": [ { "amount": "0.00000666", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "forecast_usd", "label": "Estimated generation cost", "native_amount_usd_per_unit": "0.00000666", "native_quantity": 1, "public_unit_label": "estimate before generation", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "request_estimate" } ] } ], "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': 'nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b', '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 $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o response.bin\n# Keep the complete original response and headers. Read every returned segment, word and usage field.\n# Preserve actual operation/task/asset IDs; continue reads of the original result without resubmitting.\n", "label": "curl · exact native body and complete result", "language": "bash" }, { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/media/assets \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" -o owned-assets.json\n# Preserve every returned asset and follow its exact signed content URL. Do not construct a signed token.\n", "label": "Read existing owned assets", "language": "bash" } ], "family": "openai", "fast_multiplier": null, "flex_multiplier": null, "fmt": "transcriptions", "hints": [ "Use the exact caller model ID and documented input representation.", "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": "original_invoice_usd", "image_input_price": null, "image_output_price": null }, "pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "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": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "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": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "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": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "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": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "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": true, "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": "0.00000666", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "audio_input_second", "label": "input audio second", "native_amount_usd_per_unit": "0.00000666", "native_quantity": 1, "public_unit_label": "per input audio second", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "audio_input_second" } ] }, { "basis": "This estimate is not an additional charge or a fixed rate for the completed generation.", "dimensions": { "forecast_quantity": "one generation estimate" }, "label": "Estimated generation cost", "units": [ { "amount": "0.00000666", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "forecast_usd", "label": "Estimated generation cost", "native_amount_usd_per_unit": "0.00000666", "native_quantity": 1, "public_unit_label": "estimate before generation", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "request_estimate" } ] } ], "request_model_id": "nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b", "route_label": "Ultra", "status_reads": [ "GET /v1/media/tasks/{task_id}" ], "tiers": [], "units": [ { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "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": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "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": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "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": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "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": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "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": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" }, { "amount": "0.00000666", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "audio_input_second", "label": "input audio second", "native_amount_usd_per_unit": "0.00000666", "native_quantity": 1, "public_unit_label": "per input audio second", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "audio_input_second" }, { "amount": "0.00000666", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "forecast_usd", "label": "Estimated generation cost", "native_amount_usd_per_unit": "0.00000666", "native_quantity": 1, "public_unit_label": "estimate before generation", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "request_estimate" } ] } ], "model_aliases": [ { "canonical_model_id": "nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b", "request_model_id": "nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b", "route_label": "Ultra" } ], "name": "NVIDIA: Nemotron 3.5 ASR Streaming Multilingual 0.6B", "price": { "estimate_only": true, "in": null, "in_label": null, "out": 6.66e-06, "out_label": "estimate before generation", "scope_label": "Estimated generation cost", "sort_in": null, "sort_out": 6.66e-06, "varies": false }, "short": "NVIDIA’ning Nemotron 3.5 ASR Streaming Multilingual 0.6B modeli keshni hisobga oluvchi oqimli enkoder yordamida nutqni tinish belgilari qo‘yilgan matnga aylantiradi. U tilni aniq ko‘rsatish yoki avtomatik aniqlashni qo‘llab-quvvatlaydi; 32 ta lokal variant transkripsiyaga tayyor, sakkiztasi esa moslashtirishni talab qiladi." }, "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": "NVIDIA’ning Nemotron 3.5 ASR Streaming Multilingual 0.6B modeli keshni hisobga oluvchi oqimli enkoder yordamida nutqni tinish belgilari qo‘yilgan matnga aylantiradi. U tilni aniq ko‘rsatish yoki avtomatik aniqlashni qo‘llab-quvvatlaydi; 32 ta lokal variant transkripsiyaga tayyor, sakkiztasi esa moslashtirishni talab qiladi.", "source": { "audit_sha256": "2e00086bcbfc28e64d0cebe97aa47c17d8d5618963027f8ffb9dc6123d7d25b1", "bridge_map_sha256": "1125275768b9636fc8461bc7da5061239a81ddfe508e2557843ca42c58ab0036", "raw_model_json_sha256": "cd60c11b9d08577b4971fc0def19e815e1b7694014b4155fdee3155cbe58cded", "renderer_sha256": "aa8a0fca1bd770c042b64987512b6187fca2067aea3ddc877f68b163d80e7df6" }, "sourceRevision": "f868b0528441b157921189f632e90b53235e55e8f19782f2a0d7731f09d7f9d6" }