ElevenLabs releases Scribe v2 Medical speech-to-text model

The model cuts clinical word error rates by 35% compared to base Scribe v2 and is available via API starting at $0.22 per hour.
Key points
- Achieved the lowest overall WER on the MedDictate clinical dictation benchmark across English, French, and German.
- Scored lower WER and CER than published leaderboard results on the 3,619-sample Eka Medical ASR benchmark.
- Maintains a 5.3% WER on 6,000 non-medical audio samples from Common Voice, matching base Scribe v2.
- Enterprise customers with a BAA can enable Zero Retention Mode to delete audio and transcripts immediately upon request completion for HIPAA compliance.
Why it matters
Clinical software developers can transcribe specialized medical speech with higher accuracy without retaining sensitive patient audio or sacrificing non-medical transcription performance.
Sources
- ElevenLabs releases Scribe v2 Medical speech-to-text model (ElevenLabs, Sep 23, 2026, 2:15 PM)