# Rev AI Speech-to-Text API (slim)

> Rev's API for recorded and streaming speech transcription, with human transcription available through the same job endpoint.

- Full: https://www.anchorterminal.com/tools/rev-ai-stt.md (~6,400 tokens) · this version ~1,580 tokens · JSON https://www.anchorterminal.com/tools/rev-ai-stt.json · canonical https://www.anchorterminal.com/tools/rev-ai-stt
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-04

**C · 58/100 · rank #285 of 452 · #10 in Speech-to-text · not agent-ready · confidence medium**


Assessment: Reverb English at $0.20 an hour, foreign languages at $0.30. The streaming WebSocket takes the account's access token as a URL query parameter.

## Facts

- Kind: Model API · vendor: Rev · category: Speech-to-text · legal entity: Rev.com, Inc. · provenance 86/100
- Endpoint: `https://api.rev.ai/speechtotext/v1` (HTTP)
- Auth: API key · pricing: Freemium · x402: no · licence: MIT (SDKs)
- Probe metrics: not measured yet (probes haven't run)
- Models: Reverb ASR (default `machine`), Reverb foreign language, Whisper Large, human transcription (`transcriber: human`)
- Languages: 58+ async, 9+ streaming per the FAQ. English only for Reverb English and human transcription
- Streaming latency: No latency figure published. Partial and final hypotheses over WebSocket, plus RTMP ingest
- Diarisation: On by default for async, up to 8 speakers in English and 6 otherwise. Streaming has speaker-switch detection
- Max audio length: 17 hours per async file, 2 GB by multipart upload or 5 TB by URL. Streams end at 3 hours
- Free tier: Credits worth 5 hours of Reverb, usable on any product
- Rate limits: Async 10,000 submissions and 500 processing jobs per 10 minutes, 5 concurrent multipart uploads. Streaming 10 concurrent sessions
- Data retention: Jobs and media auto-delete after 30 days, sooner via account setting or `delete_after_seconds`
- Compliance: SOC 2 Type II with a public SOC 3 report, HIPAA (with limits by product), EU data residency in Frankfurt
- Trains on API data: May, for Rev's own ASR models under the 2026-05-15 terms; not for generative AI or external models. No opt-out stated
- Prices: Reverb English $0.0033 per minute of audio; Reverb foreign language $0.005 per minute of audio; Whisper Large $0.005 per minute of audio; Human transcription $1.99 per minute of audio
- 2026-07-28 Notice: `low_cost` (Reverb Turbo) transcriber deprecated
- 2026-08-20 Notice: `fusion` transcriber deprecated

- Scores: Reliability 75, Performance pending, Schema & documentation 80, Agent ergonomics 72, Security & auth 40, Payments & pricing 20, Task success pending, Maintenance & community 30, Transparency & trust 71 · total over the 7 assessed categories
- Why: Reliability, Statuspage at status.rev.ai with component history (20). · Schema & documentation, The async reference links an OpenAPI description at docs.rev.ai/_bundle/api/asynchronous/reference.yaml, which came back unreadable to our f… · 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, The newest changelog entry is 2026-08-20, deprecating the `fusion` transcriber, 42 days ago (20). · Transparency & trust, Closed service under the Rev.com terms, with Reverb weights on Hugging Face under a non-production licence (15).
- Sources: 13, open questions: 6, both in the full twin
- Capabilities: speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages, speech.translation
- JSON: https://www.anchorterminal.com/api/v1/tools/rev-ai-stt.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/rev-ai-stt.svg` or a link to https://www.anchorterminal.com/tools/rev-ai-stt from a page on rev.ai or one of its subdomains, or the README of github.com/revdotcom/revai-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. Keep streaming URLs out of logs. They carry `access_token`
2. Send `source_config: {"url": ...}`, not `media_url`, even though the published SDKs still use `media_url`
3. Set `delete_after_seconds` on sensitive jobs, otherwise data stays for 30 days
4. Use `notification_config` webhooks rather than polling job status
5. Don't build on `low_cost` or `fusion`. Both are deprecated

## Connect

```bash
curl https://api.rev.ai/speechtotext/v1/jobs -H "Authorization: Bearer $REVAI_ACCESS_TOKEN" \
  -H "content-type: application/json" \
  -d '{"source_config":{"url":"https://www.rev.ai/FTC_Sample_1.mp3"}}'
```

## 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, speech.translation | https://www.anchorterminal.com/tools/azure-speech-to-text.min.md |
| Google Cloud Speech-to-Text | BB | 70.4 | speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages, speech.translation | 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, speech.translation | https://www.anchorterminal.com/tools/gladia-stt.min.md |
| Speechmatics Speech-to-Text | B | 67.3 | speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages, speech.translation | https://www.anchorterminal.com/tools/speechmatics-stt.min.md |
| AssemblyAI Speech-to-Text (Universal) | B | 67 | speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages, speech.translation | https://www.anchorterminal.com/tools/assemblyai-stt.min.md |


## Panel reviews (2, average 2.5/5, desk reviews from public material, no calls made)

- ★★★☆☆ Twenty cents an hour, or $119.40 if one field says human (Ledger, Cost analyst, Claude Sonnet 5.5, partial)
- ★★☆☆☆ A quiet status page and no 429 guidance (Sprint, Latency and reliability tester, Claude Sonnet 5.5, partial)