All tasks / Models
Nova-3
Deepgram's speech-to-text models for production transcription; Flux is its separate conversational line.
- Deepgram
- Closed
- Released 12 Feb 2025
Where it ranks
- BTranscriptionModels · Cloud · 4.8% on Artificial Analysis Speech to Text: AA-WER v2 (non-streaming)
Facts
- Vendor
- Deepgram
- Family
- Nova
- Released
- 12 Feb 2025
- Weights
- Closed: API and apps only
- License
- proprietary
- API price
- $0.0043 per minute of audio (Artificial Analysis lists $4.3 per 1,000 minutes (Nova-3, provider Deepgram); divided by 1,000.)
- Last verified
- 18 Oct 2026
Price from artificialanalysis.ai, 18 Oct 2026.
Benchmark results
| Benchmark | Result | Entry on the leaderboard | As of | Source |
|---|---|---|---|---|
| Artificial Analysis Speech to Text: AA-WER Streaming | 6.6% | Deepgram Nova-3 RealtimeAA-WER Streaming index (final transcripts), provider Deepgram; embedded value 0.065859 converted to percent and rounded; page shows no last-updated date. | 19 Oct 2026 | artificialanalysis.ai |
| Artificial Analysis Speech to Text: AA-WER v2 (non-streaming) | 4.8% | Nova-3, TelnyxAA-WER v2 (non-streaming), provider Telnyx; embedded value 0.0482 converted to percent and rounded; page shows no last-updated date. | 18 Oct 2026 | artificialanalysis.ai |
| Coval Benchmarks: Speech-to-Text WER (24h window) | 5.3% | deepgram / nova-3Coval STT benchmark, mean WER over the trailing 24h window (snapshot generation 2610, as_of 2026-10-19T09:38Z), n=912 clips; rank 20 of 31; read from the public API that feeds https://benchmarks.coval.ai. | 19 Oct 2026 | benchmarks-api-6wxgp27p2a-ue.a.run.app |
Where you can use it
No tracked tool lists this model yet.
Earlier versions
- Nova-2 · 19 Sep 2023