Skip to main content
POST
Speech-to-Text
STT uses a dedicated multipart endpoint POST /api/v2/stt, not the standard /generate endpoint.

Request

string
required
Authorization: Bearer nb_YOUR_API_KEY
file
required
Audio file. Supported formats: mp3, mp4, wav, m4a, ogg, flac, webm. Max size: 25 MB.
string
default:"whisper"
STT model slug. See table below.
string
Language code (e.g. en, ru, es). Optional — auto-detected if omitted.
boolean
default:"false"
Speaker diarization. Only supported by elevenlabs-scribe.

Models

Response

Diarization (who said what)

Available only with elevenlabs-scribe:
Response includes speaker labels in result_text:

Code Examples