Multi-Modal AI (Coming Soon)
Create Transcription
Start an asynchronous transcription job
POST
Start an asynchronous transcription job for a recording. The recording must be in
See the Auto-Processing Guide for full details.
uploaded status.
Use webhooks to receive real-time notifications when the transcription completes, or poll the Get Transcription endpoint.
Authentication
Requires an API key withtranscriptions:write scope.
Path Parameters
The recording’s unique identifier (e.g.,
rec_abc123).Request Body
Language code for the audio content. If not specified, the language is auto-detected.ISO 639-1 two-letter codes (e.g.,
en, es, zh) work across all providers. Some providers also accept regional variants — see Language Code Formats below.Enable speaker diarization to identify different speakers in the transcript.
ASR provider to use for transcription. If not specified, uses the system default.
Response
Returns the newly created transcription object withpending status.
Response Fields
Transcription Status
Polling for Results
After starting a transcription job, poll the Get Transcription endpoint:Transcription typically takes 10-30% of the audio duration. A 30-minute recording usually completes in 3-10 minutes.
Auto-Transcription
Instead of calling this endpoint manually, you can enable auto-transcription to automatically start a transcription job whenever a recording upload completes. Configure via the hierarchical config system:Webhooks (Recommended)
For production use, subscribe to webhook events instead of polling:transcription.started- Processing beginstranscription.completed- Transcription finished successfullytranscription.failed- Transcription failed
Language Code Formats
Each ASR provider accepts different language code formats. ISO 639-1 two-letter codes are recommended as they work across all providers.
If you need regional accuracy (e.g., US English vs British English), use the provider-specific format:
Supported Languages per Provider
Whisper — 99 languages (ISO 639-1)
Whisper — 99 languages (ISO 639-1)
af Afrikaans, am Amharic, ar Arabic, as Assamese, az Azerbaijani, ba Bashkir, be Belarusian, bg Bulgarian, bn Bengali, bo Tibetan, br Breton, bs Bosnian, ca Catalan, cs Czech, cy Welsh, da Danish, de German, el Greek, en English, es Spanish, et Estonian, eu Basque, fa Persian, fi Finnish, fo Faroese, fr French, gl Galician, gu Gujarati, ha Hausa, haw Hawaiian, he Hebrew, hi Hindi, hr Croatian, ht Haitian Creole, hu Hungarian, hy Armenian, id Indonesian, is Icelandic, it Italian, ja Japanese, jw Javanese, ka Georgian, kk Kazakh, km Khmer, kn Kannada, ko Korean, la Latin, lb Luxembourgish, ln Lingala, lo Lao, lt Lithuanian, lv Latvian, mg Malagasy, mi Maori, mk Macedonian, ml Malayalam, mn Mongolian, mr Marathi, ms Malay, mt Maltese, my Myanmar, ne Nepali, nl Dutch, nn Nynorsk, no Norwegian, oc Occitan, pa Punjabi, pl Polish, ps Pashto, pt Portuguese, ro Romanian, ru Russian, sa Sanskrit, sd Sindhi, si Sinhala, sk Slovak, sl Slovenian, sn Shona, so Somali, sq Albanian, sr Serbian, su Sundanese, sv Swedish, sw Swahili, ta Tamil, te Telugu, tg Tajik, th Thai, tk Turkmen, tl Tagalog, tr Turkish, tt Tatar, uk Ukrainian, ur Urdu, uz Uzbek, vi Vietnamese, yi Yiddish, yo Yoruba, zh ChineseDeepgram — 36+ languages (BCP-47)
Deepgram — 36+ languages (BCP-47)
AssemblyAI — 17+ languages (ISO 639-1 / underscore)
AssemblyAI — 17+ languages (ISO 639-1 / underscore)
ElevenLabs — 99 languages (ISO 639-1 / ISO 639-3)
ElevenLabs — 99 languages (ISO 639-1 / ISO 639-3)
Full list:
afr, amh, ara, asm, aze, bak, bel, bul, ben, bod, bre, bos, cat, ces, cym, dan, deu, ell, eng, spa, est, eus, fas, fin, fao, fra, glg, guj, hau, haw, heb, hin, hrv, hat, hun, hye, ind, isl, ita, jpn, jav, kat, kaz, khm, kan, kor, lat, ltz, lin, lao, lit, lav, mlg, mri, mkd, mal, mon, mar, msa, mlt, mya, nep, nld, nno, nor, oci, pan, pol, pus, por, ron, rus, san, snd, sin, slk, slv, sna, som, sqi, srp, sun, swe, swa, tam, tel, tgk, tha, tuk, tgl, tur, tat, ukr, urd, uzb, vie, yid, yor, zho
