# Scribe v2 Medical

By Steven Van · 2026-09-11

Scribe v2 Medical is a batch speech-to-text model for clinical audio, priced the same as Scribe v2 and set via the model\_id parameter.

[ElevenLabs](<https://creatorstoolbox.com/tools/elevenlabs>) has made Scribe v2 Medical generally available, a batch speech recognition model built for medical and clinical audio. It's billed at the same rate as Scribe v2: pass *scribe\_v2\_medical* as the model\_id on [Create transcript](<https://elevenlabs.io/docs/api-reference/speech-to-text/convert>). Keyterm prompting, entity detection, speaker diarization and no-verbatim mode all work the same way they do in Scribe v2.

[![](<https://elevenlabs.io/docs/api/fern-docs/og?slug=docs%2Fapi-reference%2Fspeech-to-text%2Fconvert>)](<https://elevenlabs.io/docs/api-reference/speech-to-text/convert>)

![ElevenLabs](<https://elevenlabs.io/android-chrome-512x512.png>)

ElevenLabs

AI audio platform for text to speech, voice cloning, and video dubbing across dozens of languages while preserving the original tone and emotion.

[View ElevenLabs →](<https://creatorstoolbox.com/tools/elevenlabs>)

Sources

[Original source](<https://elevenlabs.io/docs/api-reference/speech-to-text/convert>)

[Read Scribe v2 Medical on Creators Toolbox](<https://creatorstoolbox.com/blog/elevenlabs-scribe-v2-medical>)

---
Canonical source: https://creatorstoolbox.com/blog/elevenlabs-scribe-v2-medical