Scribe v1
Scribe v1 was ElevenLabs’ first speech-recognition release. Its launch combined transcription in 99 languages with word timestamps, speaker separation and labels for events such as laughter.
Deprecated API; check access details
First recognition release
The launch credits Flavio Schneider with architecture and training, and Tim von Känel with project leadership and pretraining and fine-tuning data. The first release returned structured transcripts through the API; realtime recognition was still planned.ElevenLabs: first Scribe model
Practical guidance. Keep this identifier in an existing integration’s migration record. Scribe v2 Realtime is a different streaming branch, so it should not be treated as a direct rename of the batch endpoint.ElevenLabs: first Scribe model
Specifications & access
| Detail | Value and conditions |
|---|---|
| Status | Deprecated API; check access details |
| Launch date | |
| Access | API |
| Model identifiers | scribe_v1 |
| API status | Deprecated; Scribe v2 recommendedElevenLabs model catalog and deprecations |
Related models
- Scribe v2
ElevenLabs · Scribe
Batch speech-recognition model for long recordings, structured transcripts and multilingual audio.
Launch date API · Provider product - Scribe v2 Realtime
ElevenLabs · Scribe
Streaming recognition model with partial and committed transcripts.
Launch date API · Provider product