Deepgram Nova-3
Available deepgram/nova-3 · by Deepgram · end-to-end-asr
Pricing — 1 offering(s)
Deepgram
Pre-recorded audio (batch)
- $0.0043 / minute Current 2025-01-01 → present
Streaming (real-time)
- $0.0077 / minute Current 2025-01-01 → present
Showing the active price and any recorded history. Full pricing history is available via the paid API — see API docs.
Capability profile
transcription accuracy strong
language support moderate
speaker diarisation strong
real time streaming strong
custom vocabulary strong
Benchmarks
| Benchmark | Score | Config | Source |
|---|---|---|---|
| Real-time streaming latency (vendor-reported) | 300 ms | Round-trip latency on Deepgram-hosted infrastructure. Vendor-reported, not independently verified. | source ↗ |
| WER (LibriSpeech) | — | Deepgram does not publish LibriSpeech WER. Nova-3 is positioned as state-of-the-art on proprietary benchmarks including earnings calls and phone audio. | — |
Operator guidance
The default choice for high-accuracy production STT. Best-in-class streaming latency makes it ideal for real-time apps; per-second billing (no rounding) keeps cost predictable. Use Whisper-1 for broad 99-language coverage or if you are already on the OpenAI platform. Use Universal-2 for the lowest per- minute rate on batch workloads.
Use cases
- Call centre and phone audio transcription at scale
- Real-time meeting transcription and captioning
- Voice assistants requiring low-latency incremental transcription
- Podcast and broadcast media transcription
Limitations
- Primarily English; multilingual quality lags significantly behind English
- Streaming tier is ~80% more expensive per minute than batch
- No native translation endpoint — transcription only