Fact · Speech recognition
ElevenLabs' speech to text API has a model_id field that names the transcription model, and its examples set it to scribe_v2.
Checked against its source on October 17, 2026
In the source's own words
“The ID of the model to use for transcription”
Create transcript (ElevenLabs API reference, Speech to Text), ElevenLabs, 2026, Request body: model_id.
Open the original- What it measures
- The convert endpoint takes a multipart form with the audio file and fields such as model_id. The API reference lists the model_id as required and the example requests send scribe_v2.
- What it does not show
- Describes the request format only. It does not say which model gives the best accuracy for your audio.