Audio modelActive
Nova-3
Deepgram
- Released
- -
- Data date
- September 24, 2026
- Model class
- Access
Nova-3 is Deepgram’s general-purpose speech-to-text model for batch and streaming. Its multilingual option covers English, Spanish, French, German, Hindi, Russian, Portuguese, Japanese, Italian, and Dutch, with English as the default. Deepgram documents meetings, captions, multi-speaker recordings, and noisy or far-field audio for the profile.
Nova-3 transcribes speech but does not provide model-integrated turn detection. Flux adds that end-of-turn detection for English voice agents.
Specifications and access
| Specification | Value and source |
|---|---|
| Model class | Speech recognitionSource |
| Access | APISource |
| API model ID | nova-3Source |
| Input | Audio file or streamSource |
| Output | TextSource |
| Task | TranscriptionSource |
| Supported details | Multilingual, batch and streamingSource |
| Languages | Multilingual option for English, Spanish, French, German, Hindi, Russian, Portuguese, Japanese, Italian, and Dutch; English is the defaultSource |
| Intended use | General-purpose speech recognition without integrated turn detectionSource |
Popularity
51 / 100
Sources and data date
| Type | Evidence and data date |
|---|---|
| Additional source | Deepgram speech-to-text documentation (retrieved September 24, 2026) · Deepgram speech-to-text models and languages · Editorial description reviewed October 2, 2026 |
| Additional source | OpenRouter: Popularity index (derived), CC BY 4.0 |
| Additional source | Vercel AI Gateway: Popularity index (derived), CC BY 4.0 |
| Additional source | Creative Commons Attribution 4.0 |