Deepgram
by Deepgram
Nova-2 model, excellent streaming, strong at conversational audio.
TL;DR
Nova-2 model, excellent streaming, strong at conversational audio.
Best for real-time voice apps (agents, meeting tools) where streaming latency is the product. Pricing: from $0.0043/min.
Category
Transcription APIs
License
—
Stars
—
Last push
—
Pricing
from $0.0043/min
Platforms
API
What it is
Deepgram's Nova-2 is one of the strongest streaming ASR models on the market, with very low latency and good accuracy on conversational audio. HIPAA-eligible, per-minute pricing competitive with self-hosted for modest volume. Last price check: 2026-04-20.
Best for: Real-time voice apps (agents, meeting tools) where streaming latency is the product.
Watch out for: Lower language coverage than Whisper variants; proprietary.
Watch out for: Lower language coverage than Whisper variants; proprietary.
Install / use
Features
| Speaker diarization | Yes |
| Word-level timestamps | Yes |
| Streaming / real-time | Yes |
| Languages supported | 36 |
| HIPAA eligible | Yes |
Deepgram vs Whipscribe
| Feature | Deepgram | Whipscribe |
|---|---|---|
| Category | Transcription APIs | Transcription APIs |
| Pricing | from $0.0043/min | free beta |
| Speaker diarization | Yes | Yes |
| Word timestamps | Yes | Yes |
| Streaming | Yes | No |
| Languages | 36 | 99 |
| Platforms | API | Web, API, MCP |
Sources & dates for the comparison above
- diarization: “Diarization recognizes speaker changes and attributes speech to speakers.” — source (checked 2026-04-23)
- word timestamps: “Each word returned includes start and end times in seconds.” — source (checked 2026-04-23)
- streaming: “Deepgram's streaming API transcribes live audio in real time over WebSockets.” — source (checked 2026-04-23)
- pricing: “Nova model pre-recorded transcription from $0.0043 per minute (pay-as-you-go).” — source (checked 2026-04-23)
Alternatives to Deepgram
Whipscribe is a managed faster-whisper + whisperX service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.