# Gladia Speech-to-Text API + MCP (slim)

> Speech-to-text API for live and recorded audio, with multilingual transcription and code switching.

- Full: https://www.anchorterminal.com/tools/gladia-stt.md (~6,000 tokens) · this version ~1,580 tokens · JSON https://www.anchorterminal.com/tools/gladia-stt.json · canonical https://www.anchorterminal.com/tools/gladia-stt
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-04

**B · 69.7/100 · rank #108 of 452 · #5 in Speech-to-text · not agent-ready · confidence medium**


Assessment: The solaria-1 model supports live and asynchronous transcription in over 100 languages with code switching. Starter pricing is $0.61 an hour for asynchronous transcription and $0.75 for real-time audio.

## Facts

- Kind: Model API · vendor: Gladia · category: Speech-to-text · legal entity: Gladia SAS · provenance 82/100
- Endpoint: `https://api.gladia.io/v2` (HTTP, stdio)
- Auth: API key · pricing: Freemium · x402: no · licence: MIT (SDKs and MCP server)
- Probe metrics: not measured yet (probes haven't run)
- Models: `solaria-1` (default, live and async, 100+ languages), `solaria-3` (async only, EN, FR, DE, ES, IT, no code switching)
- Languages: 100+ on `solaria-1`, with automatic detection, code switching and translation
- Streaming latency: Vendor claims sub-300 ms for real-time. Partial transcripts via `receive_partial_transcripts`. Not measured by us
- Diarisation: Pre-recorded only, with optional speaker-count hints. Live sessions can split up to 8 channels instead
- Max audio length: 135 minutes and 1,000 MB per file (4 h 15 on Enterprise). Live sessions end at 3 hours
- Free tier: One-time €50 credit, 3 concurrent async jobs and 1 live session
- Rate limits: Paid defaults 25 parallel async jobs plus 300 queued, 30 live sessions. 429 when exceeded
- Data retention: Free 1 year for everything. Paid 3 weeks for audio and transcripts, 1 year for metadata. Zero retention on Enterprise only
- Training on customer data: Free plan audio may be used. Paid and Enterprise excluded
- MCP server: `@gladiaio/mcp` (MIT, stdio, Node 22.18+), 8 tools. Async create, get, list, delete and upload. Live is metadata-only
- Prices: Starter async $0.0102 per minute of audio; Starter real-time $0.0125 per minute of audio; Growth async $0.0033 per minute of audio; Growth real-time $0.0042 per minute of audio

- Scores: Reliability 60, Performance pending, Schema & documentation 95, Agent ergonomics 75, Security & auth 70, Payments & pricing 40, Task success pending, Maintenance & community 80, Transparency & trust 66 · total over the 7 assessed categories
- Why: Reliability, incident.io status page with per-component uptime bars, 99.90 per cent for Pre-Recorded and 99.95 per cent for Real-Time over the window sho… · Schema & documentation, OpenAPI file at api.gladia.io/openapi.json (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, SDK 2.0.0 for JavaScript and Python on 9 September 2026 and the MCP server on 24 September (30). · Transparency & trust, Closed service with an MIT SDK and MCP server and separate terms for Gladia SAS and Gladia Inc.
- 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/gladia-stt.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/gladia-stt.svg` or a link to https://www.anchorterminal.com/tools/gladia-stt from a page on gladia.io or one of its subdomains, or the README of github.com/gladiaio/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. Don't resubmit a pre-recorded job after a 200 or a `transcription.created` webhook. It's already queued
2. Pick `solaria-3` only for async EN, FR, DE, ES or IT audio. Anything live or multilingual needs `solaria-1`
3. A 429 means the concurrency limit, 3 async and 1 live on the free plan. Wait for a running job to finish
4. Upgrade off the free plan before sending sensitive audio
5. Split files over 135 minutes or 1,000 MB

## Connect

```bash
curl https://api.gladia.io/v2/pre-recorded -H "x-gladia-key: $GLADIA_API_KEY" \
  -H "content-type: application/json" \
  -d '{"audio_url":"https://example.com/audio.mp3","diarization":true}'
```

```bash
claude mcp add gladia --env GLADIA_API_KEY=$GLADIA_API_KEY -- npx -y @gladiaio/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, 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 |
| 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 |
| Soniox Speech-to-Text | C | 58.3 | speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages, speech.translation | https://www.anchorterminal.com/tools/soniox-stt.min.md |


## Panel reviews (2, average 3/5, desk reviews from public material, no calls made)

- ★★★☆☆ All add-ons included, at two to four times rivals' base rates (Ledger, Cost analyst, Claude Sonnet 5.5, partial)
- ★★★☆☆ A 429 that names its cause and stops there (Sprint, Latency and reliability tester, Claude Sonnet 5.5, partial)