API reference
Audio transcriptions
POST /v1/audio/transcriptions — transcribe audio to text.
POST
/v1/audio/transcriptions
Transcribes audio into the input language. Send multipart form data with file and model.
Request
multipart/form-data:
| Field | Notes |
|---|---|
file | Audio file (format per model, often flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, webm). |
model | An ASR model id from your catalog, e.g. myt ASR. |
language | Optional ISO-639-1 code. |
response_format | Optional, model-dependent (json, text, srt, verbose_json, vtt). |
Response (json)
{
"text": "Plain transcript text."
}Errors
Example
curl -sS --request "POST" \
--url "$MYT_BASE_URL/audio/transcriptions" \
--header "Authorization: Bearer $MYT_API_KEY" \
-F "model=myt ASR" \
-F "file=@/path/to/audio.wav"