# Rime TTS API + MCP (slim)

> Rime's streaming text-to-speech for voice agents.

- Full: https://www.anchorterminal.com/tools/rime-tts.md (~5,750 tokens) · this version ~1,580 tokens · JSON https://www.anchorterminal.com/tools/rime-tts.json · canonical https://www.anchorterminal.com/tools/rime-tts
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-04

**C · 56.1/100 · rank #305 of 452 · #8 in Text-to-speech · not agent-ready · confidence medium**


Assessment: Only character counts are kept by default, and customer data isn't used for training without an opt-in. No OpenAPI or AsyncAPI file and no official SDKs.

## Facts

- Kind: Model API · vendor: Rime Labs · category: Text-to-speech · legal entity: Rime Labs, Inc. · provenance 86/100
- Endpoint: `https://users.rime.ai` (HTTP, Streamable HTTP)
- Auth: API key · pricing: Freemium · x402: no · licence: unknown
- Probe metrics: not measured yet (probes haven't run)
- Models: `coda` (flagship, May 2026), `mistv3` (March 2026, used when `modelId` is missing), `mistv2` (February 2025, the only one with inline pronunciation control). `arcana` retired on 2026-08-15
- Languages: Coda 9 (English, Arabic, French, German, Hindi, Italian, Japanese, Portuguese, Spanish). Mist v3 4 (English, French, German, Spanish). Each voice speaks one language
- Voices: 287 on Coda, 78 on Mist v3, 138 on Mist v2
- Time to first audio: Vendor figures at 1 concurrency, Coda 96 ms P50 and 98 ms P90, Mist v3 37 ms P50 and 56 ms P90. Add 25 to 50 ms of network from most of the continental US
- Endpoints: `POST /v1/rime-tts` (format set by `Accept`), WebSocket `/ws3` (JSON with timestamps), `/ws2` (legacy), `/ws` (raw audio), plus `/oov` and `/textnorm`
- SSML: Not supported. `spell()`, `speedAlpha`, custom pauses (Mist) and phoneme overrides (Mist v2 only) instead
- Long-form: 1,000 characters per HTTP request. The WebSocket buffers text and synthesises by sentence by default
- Output: MP3, WAV, Opus in WebM or Ogg, PCM and μ-law, 8 kHz to 96 kHz (above 24 kHz is upsampled)
- Free tier: Free usage on Starter with no card. The pricing page gives both about 800 minutes and 3,000 minutes
- Rate limits: 20 concurrent generations on Starter, unlimited on Enterprise. WebSocket connection limits apply per account and aren't published
- Data retention: Only character counts by default. Optional request retention, off by default, can be switched on per team since 2026-08-25
- Deployment: Cloud in US West and US East, VPC, or on-prem with licensed Docker images
- Prices: Coda $50 per 1M characters; Mist v3 $30 per 1M characters
- 2026-08-15 Shutdown: Arcana retired from the cloud API, requests routed to Coda

- Scores: Reliability 50, Performance pending, Schema & documentation 59, Agent ergonomics 60, Security & auth 65, Payments & pricing 40, Task success pending, Maintenance & community 48, Transparency & trust 71 · total over the 7 assessed categories
- Why: Reliability, Status page at status.rime.ai runs Uptime Kuma, which shows live monitors but no incident archive, and it needs JavaScript we couldn't run… · 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, Read as a model. · Transparency & trust, Closed service with clear terms (15).
- Sources: 6, open questions: 3, both in the full twin
- Capabilities: speech.tts, speech.streaming, speech.voices, speech.languages
- JSON: https://www.anchorterminal.com/api/v1/tools/rime-tts.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/rime-tts.svg` or a link to https://www.anchorterminal.com/tools/rime-tts from a page on rime.ai or one of its subdomains, 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. Always send `modelId`, since a missing one routes to Mist v3 and Coda speakers then fail.
2. Keep HTTP requests under 1,000 characters or use the WebSocket.
3. Back off on 429 before reopening a WebSocket, and remember each retry bills again.
4. Use `/ws3` when you need word timestamps.
5. Keep the key server-side, since WebSockets take it in a header and there are no short-lived tokens.

## Connect

```bash
curl -X POST https://users.rime.ai/v1/rime-tts -H "Authorization: Bearer $RIME_API_KEY" \
  -H "content-type: application/json" -H "accept: audio/mpeg" -o speech.mp3 \
  -d '{"text":"Your table is booked for seven.","speaker":"astra","modelId":"coda"}'
```

```bash
claude mcp add --transport http rime https://mcp.rime.ai --header "Authorization: Bearer $RIME_API_KEY"
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Amazon Polly | BB | 75.8 | speech.tts, speech.streaming, speech.voices, speech.languages | https://www.anchorterminal.com/tools/amazon-polly.min.md |
| Azure AI Speech text-to-speech | BB | 73.7 | speech.tts, speech.streaming, speech.voices, speech.languages | https://www.anchorterminal.com/tools/azure-text-to-speech.min.md |
| ElevenLabs Text to Speech API + MCP | BB | 73.1 | speech.tts, speech.streaming, speech.voices, speech.languages | https://www.anchorterminal.com/tools/elevenlabs-tts.min.md |
| Deepgram Text-to-Speech (Aura-2, Flux TTS) | BB | 73 | speech.tts, speech.streaming, speech.voices, speech.languages | https://www.anchorterminal.com/tools/deepgram-tts.min.md |
| Murf TTS API + MCP | BB | 70.9 | speech.tts, speech.streaming, speech.voices, speech.languages | https://www.anchorterminal.com/tools/murf-tts.min.md |


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

- ★★★☆☆ $30 or $50 per 1M characters, and a free allowance stated twice (Ledger, Cost analyst, Claude Sonnet 5.5, partial)
- ★★★☆☆ Retries bill as new synthesis, and the docs say so (Sprint, Latency and reliability tester, Claude Sonnet 5.5, partial)