Medical Dictation
Medical transcription built for live calls and recorded audio
Two Speech to Text models for clinical language: Scribe v3 Live Medical for ElevenAgents, and Scribe v2 Medical for batch transcription.
- AstraZeneca
- Banner Health
- OpenEvidence
- Clover Health
- Pfizer grey
Power healthcare conversational agents with Scribe v3 Live Medical
Real-time Speech to Text for ElevenAgents, built on Scribe v3 Live and optimized for clinical language like medication names, dosages and diagnoses.
Lowest error rate on PriMock57
On PriMock57, a public benchmark of mock primary care consultations, Scribe v3 Live Medical had the lowest word error rate of the real-time models we tested.

Up to 10,000 custom terms
Add your formulary, provider and clinic names, or a specialty dictionary. The model applies a term only when the audio is a likely match, so one list can cover every call your agent takes.

Turn detection
Waits for callers to finish a member ID, date of birth or phone number before the agent replies.
90+ languages
Supports 90+ languages. Multilingual mode keeps up with callers who switch languages mid-call.
Speed and everyday accuracy
Matches the latency of Scribe v3 Live and performs the same on everyday speech, so you gain medical accuracy without sacrifices.
Real-time medical transcription for patient, member and HCP calls
Patient access
Book visits and take refill requests with medication names, provider names, and dates of birth captured right.
Patient outreach
Run reminders and post-discharge check-ins, and capture what patients report for your care team.
Member services
Answer benefits and claim status calls with member IDs, procedure names and plan details captured right.
Medical information
Transcribe brand and generic drug names correctly when patients and HCPs call in with questions.
Transcribe clinical audio with Scribe v2 Medical
A Speech to Text model for recorded audio, optimized for medical transcription and clinical workflows.
Transcribe clinical speech
Convert clinician-patient conversations, doctor dictation, and patient intake into precise text, ready for clinician review and use in notes, coding, and downstream documentation workflows.

Fewer errors on medical terms
On term-WER, Scribe v2 Medical makes 15% fewer errors than Scribe v2 on the Eka Medical ASR test split, with improved medical voice recognition across clinical vocabulary.
Prompt with key terms
Add the drug names and clinical phrases your team uses to bias the model toward them.
Smart speaker diarization
Automatically identify and label up to 32 speakers. Clear attribution of who said what, organized into readable transcripts.
Entity detection
Automatically identify and tag 56 entity types including names, dates, locations, and organizations within your transcripts.
Medical transcription for recorded speech
Dictated notes
Transcribe dictated notes full of drug names, dosages and units, so they are ready for clinician review.
Visit recordings
Turn recorded patient visits into transcripts that clinicians review before notes are finalized.
Care management
Transcribe care calls so coordinators spend less time fixing notes for patients on complicated regimens.
Medical conferences
Transcribe recorded meetings at medical conferences so teams can engage instead of taking notes.

