Audio modelActive
Nova-3
Deepgram
- Released
- -
- Data date
- September 22, 2026
- Model class
- Access
Profile
Specifications and access
Published information about this model. Existing estimates are explicitly labeled.
| 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 transcription; defaults to English unless a language is specifiedSource |
Evidence
Sources and data date
Every statement links to its underlying documentation or leaderboard.
| Type | Evidence and data date |
|---|---|
| Additional source | Deepgram speech-to-text documentation (retrieved September 22, 2026) |