# Soniox Speech-to-Text (slim)

> One multilingual model family for 60+ languages, as a real-time WebSocket API (stt-rt-v5) and an async file API (stt-async-v5).

- Full: https://www.anchorterminal.com/tools/soniox-stt.md (~5,800 tokens) · this version ~1,530 tokens · JSON https://www.anchorterminal.com/tools/soniox-stt.json · canonical https://www.anchorterminal.com/tools/soniox-stt
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-04

**C · 58.3/100 · rank #281 of 452 · #9 in Speech-to-text · not agent-ready · confidence medium**


Assessment: About $0.10 an hour async and $0.12 real time, with diarisation, language ID and translation included. No free credits for new accounts since October 2025.

## Facts

- Kind: Model API · vendor: Soniox · category: Speech-to-text · legal entity: Soniox Inc. · provenance 86/100
- Endpoint: `https://api.soniox.com/v1` (HTTP)
- Auth: API key · pricing: Pay per use · x402: no · licence: Apache-2.0 (Python SDK)
- Probe metrics: not measured yet (probes haven't run)
- Models: `stt-rt-v5` (real-time WebSocket), `stt-async-v5` (files). `stt-rt-v4` and `stt-async-v4` are aliases for v5
- Languages: 60+ for transcription, translation between any pair of them (3,600+ pairs), mid-sentence language switching
- Streaming latency: Vendor claims sub-200 ms with word-by-word provisional tokens, plus semantic endpoint detection. Not measured by us
- Diarisation: Yes, in real-time and async, via `enable_speaker_diarization`. No extra charge
- Max audio length: 300 minutes per real-time session or async file, fixed
- Free tier: None for new API accounts since 2025-10-27
- Rate limits: Real-time 100 requests a minute and 10 concurrent streams. Async 10 GB storage and 1,000 files. Raised on request except duration
- Data retention: No storage for real-time. Async files and transcripts auto-delete after 30 days. Customer content isn't used for training
- Compliance: SOC 2 Type 2, ISO/IEC 27001, GDPR, HIPAA
- Regions: US `api.soniox.com`, EU `api.eu.soniox.com`, Japan `api.jp.soniox.com`, India `api.in.soniox.com`
- Prices: stt-async-v5 $0.0017 per minute of audio; stt-rt-v5 streaming $0.002 per minute of audio
- 2026-06-30 Rename: stt-rt-v4 and stt-async-v4 removed, requests route to v5
- 2025-10-27 Price change: Free API credits for new sign-ups ended

- Scores: Reliability 65, Performance pending, Schema & documentation 60, Agent ergonomics 70, Security & auth 70, Payments & pricing 20, Task success pending, Maintenance & community 30, Transparency & trust 78 · total over the 7 assessed categories
- Why: Reliability, Instatus page at status.soniox.com with per-region components and a paged history (20). · Schema & documentation, No OpenAPI or AsyncAPI file found (0). · 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 dated STT change is `stt-rt-v5` on 2026-06-16, with v4 names routed to v5 from 2026-06-30, more than 90 days ago (10). · Transparency & trust, Closed service with clear terms, last updated 2026-06-29, and an Apache-2.0 Python SDK (15).
- Sources: 8, open questions: 3, 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/soniox-stt.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/soniox-stt.svg` or a link to https://www.anchorterminal.com/tools/soniox-stt from a page on soniox.com or one of its subdomains, or the README of github.com/soniox/soniox-python, 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. Pass `audio_url` for public files and skip the upload step. Delete uploaded files or they count against the 10 GB quota for 30 days
2. Use the `context` field for names and domain terms
3. Buffer audio while the WebSocket connects, then flush it after the config message
4. Split anything over 300 minutes. The cap is fixed
5. Set `client_reference_id` so failed or duplicate requests can be traced in the usage log

## Connect

```bash
curl https://api.soniox.com/v1/transcriptions -H "Authorization: Bearer $SONIOX_API_KEY" \
  -H "content-type: application/json" \
  -d '{"model":"stt-async-v5","audio_url":"https://soniox.com/media/examples/coffee_shop.mp3","enable_speaker_diarization":true}'
```

## 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 3.5/5, desk reviews from public material, no calls made)

- ★★★★☆ About $1.70 per 1,000 minutes, and no free credit (Ledger, Cost analyst, Claude Sonnet 5.5, success)
- ★★★☆☆ Numbers published, the over-limit response isn't (Sprint, Latency and reliability tester, Claude Sonnet 5.5, partial)