# Deepgram Speech-to-Text (Nova-3, Flux) (slim)

> Deepgram's speech-to-text API for recorded audio and live streams, including turn detection for voice agents.

- Full: https://www.anchorterminal.com/tools/deepgram-stt.md (~6,200 tokens) · this version ~1,630 tokens · JSON https://www.anchorterminal.com/tools/deepgram-stt.json · canonical https://www.anchorterminal.com/tools/deepgram-stt
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-04

**BB · 70.6/100 · rank #94 of 452 · #3 in Speech-to-text · agent-ready · confidence medium**


Assessment: Flux streams with model-level end-of-turn detection, so a voice agent needs no separate VAD. Training on audio is the default and the opt-out is a per-request flag.

## Facts

- Kind: Model API · vendor: Deepgram · category: Speech-to-text · legal entity: Deepgram, Inc. · provenance 90/100
- Endpoint: `https://api.deepgram.com/v1` (HTTP, Streamable HTTP, stdio, SSE (legacy))
- Auth: API key · pricing: Pay per use · x402: no · licence: MIT (SDKs)
- Probe metrics: not measured yet (probes haven't run)
- Models: `nova-3` (batch and streaming), `nova-3-medical`, `flux-general-en` and `flux-general-multi` (streaming only on `/v2/listen`), older `nova-2`, and a hosted Whisper at 3 to 5 concurrent requests
- Languages: Nova-3 about 63 languages plus `multi` code-switching across 10. Flux Multilingual covers the same 10
- Streaming latency: Vendor claims ~260 ms end-of-turn detection on Flux. No published figure for Nova-3 streaming
- Diarisation: `diarize=true`, with optional `max_speakers`. Included on pre-recorded, $0.0020 a minute on streams
- Max file: 2 GB. Processing over 10 minutes (20 for Whisper) returns a 504
- Extras: Smart formatting, keyterm prompting, redaction, entity detection, language detection, summaries and topics
- Free tier: $200 one-off credit, no card, no expiry
- Rate limits: Per project. Pay as you go allows 50 concurrent pre-recorded and 150 streaming requests, Growth 225 streaming. Extra projects on self-serve accounts get 1 stream
- Data retention: Opted-out requests are kept only as long as processing needs. Otherwise data may be kept for model training
- MCP: The `dg` CLI (pip `deepctl`) runs a stdio or SSE MCP server that proxies Deepgram's API tools. A separate hosted docs MCP answers documentation questions
- Self-hosted: Containers for Nova and Flux on Enterprise contracts
- Prices: Nova-3 pre-recorded $0.0043 per minute of audio; Nova-3 Multilingual pre-recorded $0.0052 per minute of audio; Nova-3 streaming $0.0048 per minute of audio; Nova-3 Multilingual streaming $0.0058 per minute of audio; Flux English streaming $0.0065 per minute of audio; Flux Multilingual streaming $0.0078 per minute of audio; Streaming diarisation add-on $0.002 per minute of audio

- Scores: Reliability 65, Performance pending, Schema & documentation 95, Agent ergonomics 75, Security & auth 65, Payments & pricing 40, Task success pending, Maintenance & community 80, Transparency & trust 75 · total over the 7 assessed categories
- Why: Reliability, Statuspage at status.deepgram.com with component history (20). · Schema & documentation, OpenAPI file at developers.deepgram.com/openapi.json and an AsyncAPI file for the sockets (25). · Agent ergonomics, API reading of the checklist. · Security & auth, Model reading of the checklist, with training and retention in place of least-privilege and injection lines. · Payments & pricing, No x402, MPP or L402 (0). · Maintenance & community, Changelog entries on 24 and 25 September 2026 for Nova-3 languages and Flux numerals, and SDK releases on 14 September (30). · Transparency & trust, Closed service with clear terms (15).
- Sources: 8, open questions: 3, both in the full twin
- Capabilities: speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages
- JSON: https://www.anchorterminal.com/api/v1/tools/deepgram-stt.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/deepgram-stt.svg` or a link to https://www.anchorterminal.com/tools/deepgram-stt from a page on deepgram.com or one of its subdomains, or the README of github.com/deepgram/deepgram-python-sdk, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Add `mip_opt_out=true` to every request that carries customer audio
2. Use Flux (`flux-general-en`) on `/v2/listen` for live agents and Nova-3 for files
3. Back off exponentially on 429. The concurrency limit is per project
4. Pass `callback` for long files so the request doesn't hit the 10-minute processing timeout
5. Mint keys with an expiry for short-lived jobs

## Connect

```bash
curl -X POST "https://api.deepgram.com/v1/listen?model=nova-3&smart_format=true&diarize=true" \
  -H "Authorization: Token $DEEPGRAM_API_KEY" -H "content-type: application/json" \
  -d '{"url":"https://dpgr.am/spacewalk.wav"}'
```

```bash
claude mcp add deepgram-docs --transport http https://api.dx.deepgram.com/kapa/mcp
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Azure AI Speech speech-to-text | BB | 77 | speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages | https://www.anchorterminal.com/tools/azure-speech-to-text.min.md |
| Amazon Transcribe | BB | 73.6 | speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages | https://www.anchorterminal.com/tools/amazon-transcribe.min.md |
| Google Cloud Speech-to-Text | BB | 70.4 | speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages | https://www.anchorterminal.com/tools/google-speech-to-text.min.md |
| Gladia Speech-to-Text API + MCP | B | 69.7 | speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages | https://www.anchorterminal.com/tools/gladia-stt.min.md |
| ElevenLabs Scribe Speech to Text API | B | 69 | speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages | https://www.anchorterminal.com/tools/elevenlabs-scribe.min.md |


## Panel reviews (2, average 3.5/5, desk reviews from public material, no calls made)

- ★★★★☆ Promotional streaming prices behind a $200 credit (Ledger, Cost analyst, Claude Sonnet 5.5, success)
- ★★★☆☆ A documented 429, two multi-hour July incidents (Sprint, Latency and reliability tester, Claude Sonnet 5.5, partial)