As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/elevenlabs-scribe-v2/

# Scribe v2 / Scribe v2 Medical

ElevenLabs, Scribe family. Status: current. Type: speech and audio. Released: 2026-01-09.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| ElevenLabs API | `scribe_v2` | https://api.elevenlabs.io/v1/speech-to-text | https://elevenlabs.io/docs/overview/capabilities/speech-to-text |
| ElevenLabs API | `scribe_v2_medical` | https://api.elevenlabs.io/v1/speech-to-text | https://elevenlabs.io/docs/models |

## Pricing

- Per hour: $0.22
- Unit as published: per hour of audio (Scribe v2 and v2 Medical, API)
- Source: https://elevenlabs.io/pricing/api
- Last checked: 2026-09-29

## Specs

- Input: audio, video
- Output: text
- Context window: not published
- Max output: not published
- Open weights: no
- Licence: proprietary

## Where it stands

- Newer speech and audio models in the registry since its release: 73. The 5 newest:
  - NVIDIA Nemotron 3.5 Transcribe (30B-A4B) (2026-10-28) https://postcutoff.com/m/nemotron-3-5-transcribe/
  - Hy-SimulMT-30B-A3B (2026-10-22) https://postcutoff.com/m/hy-simulmt-30b-a3b/
  - Eleven Realtime v1 Max / Mini (2026-10-20) https://postcutoff.com/m/eleven-realtime-v1-max/
  - Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3) (2026-10-20) https://postcutoff.com/m/voxtral-mini-transcribe-3/
  - Voxtral Small Transcribe 3 (2026-10-20) https://postcutoff.com/m/voxtral-small-transcribe-3/
- Before it from ElevenLabs: Scribe v2 Realtime (2025-11-11) https://postcutoff.com/m/elevenlabs-scribe-v2-realtime/
- After it from ElevenLabs: Eleven Dubbing v2 (2026-05-28) https://postcutoff.com/m/elevenlabs-dubbing-v2/
- Closed weights; access is hosted only.

## What stands out

- Entity detection with timestamps: Native detection of PII, health and payment entities (56 categories at launch, 65 types per current docs) with exact timestamps. Source: https://elevenlabs.io/blog/introducing-scribe-v2
- Keyterm prompting, 32-speaker diarization: Keyterm prompting (100 terms at launch, now up to 1,000), speaker diarization up to 32 speakers, word timestamps, dynamic audio-event tagging, multi-language audio in one file; 90+ languages. Source: https://elevenlabs.io/docs/models
- Clinical variant (found after launch): scribe_v2_medical fine-tuned for clinical audio, HIPAA with BAA; generally available 2026-09-14. Source: https://elevenlabs.io/docs/changelog

## Notes

Launched 2026-01-09; ElevenLabs claims 'the lowest word error rate recorded on industry-standard benchmarks' (FLEURS chart; company claim). Realtime variant in its own file. scribe_v1 (launched 2025-02-26, $0.40/h at launch) is deprecated ('outclassed by v2').

```bash
curl -X POST https://api.elevenlabs.io/v1/speech-to-text -H "xi-api-key: $ELEVENLABS_API_KEY" \
  -F model_id=scribe_v2 -F file=@audio.mp3
```

Sources: https://elevenlabs.io/docs/models , https://elevenlabs.io/pricing/api , https://elevenlabs.io/blog/introducing-scribe-v2 , https://elevenlabs.io/blog/scribe-v2-medical-is-now-available-to-everyone

Model page: https://postcutoff.com/m/elevenlabs-scribe-v2/