Deepgram Nova-3 (incl. Medical / Pharma)
Release date 2025-02-12 from Deepgram's Nova-3 launch (not re-checked today). Previous gen nova-2 and variants still served. Deepgram also hosts Whisper (whisper-large, $0.0048/min).
- Input
- audio
- Output
- text
- License
- proprietary
- Pricing
- per minute: $0.0048 (per minute streaming monolingual PAYG; multilingual $0.0058; pre-recorded $0.0043 mono / $0.0052 multi) source
- Verified
- 2026-09-29
How to call it
| Provider | Model id | Endpoint / URL | Docs |
|---|---|---|---|
| Deepgram API | nova-3 | https://api.deepgram.com/v1/listen (REST) / wss://api.deepgram.com/v1/listen | docs |
| Deepgram API | nova-3-medical | — | — |
| Deepgram API | nova-3-pharma | — | — |
Notable capabilities (2)
- Keyterm prompting, 90+ languages (found after launch): Nova-3 general supports 90+ languages incl. multilingual code-switching mode; languages added continuously through 2026 (e.g. Kazakh 2026-09-03, Assamese/Mongolian/Pashto 2026-08-27). source
- Domain variants (found after launch): nova-3-medical (upgraded batch model May 2026) and nova-3-pharma (English pharmaceutical model, 2026-09-17). source
Deepgram's general-purpose transcription model (batch + streaming).
Sources: https://developers.deepgram.com/docs/models-languages-overview , https://deepgram.com/pricing , https://developers.deepgram.com/changelog
Other Deepgram models
Deepgram Flux TTS · Deepgram Flux (conversational STT, English + Multilingual) · Deepgram Aura-2