# Cartesia Sonic TTS API + MCP (slim)

> Sonic text-to-speech, currently sonic-3.6 in 44 languages, over /tts/bytes, /tts/sse and a WebSocket that takes streamed LLM text with contexts and word timestamps.

- Full: https://www.anchorterminal.com/tools/cartesia-tts.md (~6,700 tokens) · this version ~1,530 tokens · JSON https://www.anchorterminal.com/tools/cartesia-tts.json · canonical https://www.anchorterminal.com/tools/cartesia-tts
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-04

**B · 64.2/100 · rank #187 of 452 · #6 in Text-to-speech · not agent-ready · confidence medium**


Assessment: WebSocket input accepts streamed LLM text with contexts, flushing and word timestamps. Five TTS incidents on the status page between 29 July and 21 August 2026.

## Facts

- Kind: Model API · vendor: Cartesia · category: Text-to-speech · legal entity: Cartesia AI, Inc. · provenance 82/100
- Endpoint: `https://api.cartesia.ai` (HTTP, Streamable HTTP, stdio)
- Auth: OAuth or key · pricing: Freemium · x402: no · licence: Apache-2.0 (SDKs)
- Probe metrics: not measured yet (probes haven't run)
- Models: `sonic-3.6` (snapshot `sonic-3.6-2026-08-27`), `sonic-3.5`, `sonic-preview` (beta). Older `sonic-3`, `sonic-2`, `sonic-turbo` documented separately
- Languages: 44 on Sonic 3.6, including Odia and Urdu new in this release, plus romanised Hindi
- Time to first audio: Vendor claims sub-90 ms latency on its Sonic page
- Endpoints: `POST /tts/bytes`, `POST /tts/sse`, WebSocket `/tts/websocket` with contexts, flushing and buffering controls, `POST /infill/bytes`
- SSML: `speed` (0.6 to 1.5), `volume`, `emotion` (beta), `break` and `spell` tags, plus custom pronunciation dictionaries
- Voices: Curated Voice Library plus instant and pro clones. Multilingual voices can speak other languages natively after localisation
- Output: WAV, MP3 or raw PCM, 8 kHz to 48 kHz
- Free tier: 20,000 credits a month (about 27 minutes), no commercial use
- Rate limits: TTS concurrency 2 on Free, 3 Pro, 5 Startup, 15 Scale, custom on Enterprise
- Data retention: No retention period published. Terms allow training use of inputs and outputs unless agreed otherwise
- Prices: Sonic TTS overage on Pro $65 per 1M characters; Sonic TTS overage on Startup $45 per 1M characters; Sonic TTS overage on Scale $38 per 1M characters; Pro plan $5 per month (plan); Startup plan $49 per month (plan); Scale plan $299 per month (plan)

- Scores: Reliability 63, Performance pending, Schema & documentation 86, Agent ergonomics 65, Security & auth 58, Payments & pricing 30, Task success pending, Maintenance & community 79, Transparency & trust 71 · total over the 7 assessed categories
- Why: Reliability, incident.io status page at status.cartesia.ai with TTS components for the US, EU, APAC and Australia and a dated history (20). · Schema & documentation, OpenAPI files for the latest and each dated API version, plus AsyncAPI files for the WebSocket, are listed in llms.txt (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, Read as a model. · Transparency & trust, Closed service with clear terms, SDKs under Apache-2.0 (15).
- Sources: 18, open questions: 5, both in the full twin
- Capabilities: speech.tts, speech.streaming, speech.voices, speech.ssml, speech.languages
- JSON: https://www.anchorterminal.com/api/v1/tools/cartesia-tts.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/cartesia-tts.svg` or a link to https://www.anchorterminal.com/tools/cartesia-tts from a page on cartesia.ai or one of its subdomains, or the README of github.com/cartesia-ai/cartesia-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. Send the `Cartesia-Version` header on every request.
2. Pin a dated snapshot such as `sonic-3.6-2026-08-27` if output must not change.
3. Move off `sonic-2`, `sonic-turbo` and `sonic-3-2025-10-27` before 2026-10-20.
4. Expect a 429 at the plan's concurrency limit and queue requests yourself.
5. Mint a short-lived access token for browser clients instead of shipping the API key.

## Connect

```bash
curl -X POST https://api.cartesia.ai/tts/bytes -H "Authorization: Bearer $CARTESIA_API_KEY" \
  -H "Cartesia-Version: 2026-08-14" -H "content-type: application/json" -o speech.wav \
  -d '{"model_id":"sonic-3.6","transcript":"Your table is booked for seven.","voice":{"id":"47c38ca4-5f35-497b-b1a3-415245fb35e1"},"output_format":{"container":"wav","encoding":"pcm_s16le","sample_rate":44100}}'
```

```bash
claude mcp add --transport http --scope user cartesia https://mcp.cartesia.ai/mcp
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Amazon Polly | BB | 75.8 | speech.tts, speech.streaming, speech.voices, speech.ssml, 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.ssml, 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.ssml, 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)

- ★★★☆☆ $37 to $50 per 1M characters in plans, overage unconfirmed (Ledger, Cost analyst, Claude Sonnet 5.5, partial)
- ★★★☆☆ Five TTS incidents in three weeks, 2 to 15 concurrent streams (Sprint, Latency and reliability tester, Claude Sonnet 5.5, partial)