# ElevenLabs Text to Speech API + MCP (slim)

> ElevenLabs text-to-speech over REST, HTTP streaming and WebSocket.

- Full: https://www.anchorterminal.com/tools/elevenlabs-tts.md (~6,550 tokens) · this version ~1,630 tokens · JSON https://www.anchorterminal.com/tools/elevenlabs-tts.json · canonical https://www.anchorterminal.com/tools/elevenlabs-tts
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-04

**BB · 73.1/100 · rank #61 of 452 · #3 in Text-to-speech · agent-ready · confidence high**


Assessment: Keys can be limited to chosen endpoints and given a credit quota, and service accounts hold keys that don't belong to a person. Content may be used for training unless you opt out under Data use, and the opt-out only applies going forward.

## Facts

- Kind: Model API · vendor: ElevenLabs · category: Text-to-speech · legal entity: Eleven Labs Inc. · provenance 92/100
- Endpoint: `https://api.elevenlabs.io/v1` (HTTP, Streamable HTTP, stdio)
- Auth: OAuth or key · pricing: Freemium · x402: no · licence: MIT (SDKs)
- Probe metrics: not measured yet (probes haven't run)
- Models: `eleven_v4`, `eleven_v4_turbo`, `eleven_v3`, `eleven_v3_conversational`, `eleven_multilingual_v2`, `eleven_flash_v2_5`, `eleven_flash_v2`. Turbo v2 and v2.5 are deprecated in favour of Flash
- Languages: 90+ on v4 and v4 Turbo, 70+ on v3, 32 on Flash v2.5, 29 on Multilingual v2
- Time to first audio: Vendor claims ~75 ms for Flash, ~100 ms median for v4 Turbo and ~280 ms for v3 Conversational, excluding network and application latency
- Voices: 3,000+ community voices in the Voice Library plus premade, cloned and designed voices
- SSML: `<break>` tags up to 3 seconds on Multilingual v2 and Flash. Not supported on v4 or v3, which use audio tags and punctuation instead
- Long-form: Per-request limit of 40,000 characters on Flash v2.5, 10,000 on v4 and Multilingual v2, 5,000 on v3
- Endpoints: `POST /v1/text-to-speech/{voice_id}`, `/stream`, `/with-timestamps`, WebSocket `stream-input` and multi-context WebSocket, Text to Dialogue for v4
- Output: MP3 (default 44.1 kHz 128 kbps), PCM, WAV, Opus, µ-law and A-law at 8 kHz. 192 kbps MP3 needs Creator, 44.1 kHz PCM or WAV needs Pro
- Free tier: 10,000 v4 characters (20,000 on the $0.04 models) a month. No commercial licence, no Voice Library voices over the API
- Rate limits: Concurrency by plan, 2 (Multilingual) or 4 (Flash) on Free up to 15 and 30 on Scale. Excess requests queue
- Data retention: Requests are logged for history by default. `enable_logging=false` gives zero retention on Enterprise plans only
- Prices: Eleven v4 $80 per 1M characters; Eleven v4 Turbo $40 per 1M characters; Eleven v3 / Multilingual v2 $80 per 1M characters; Flash v2.5 / v3 Conversational $40 per 1M characters; Starter plan $6 per month (plan); Creator plan $22 per month (plan)

- Scores: Reliability 80, Performance pending, Schema & documentation 94, Agent ergonomics 82, Security & auth 60, Payments & pricing 40, Task success pending, Maintenance & community 77, Transparency & trust 71 · total over the 7 assessed categories
- Why: Reliability, incident.io status page with a Text-to-Speech component and dated history (20). · Schema & documentation, OpenAPI file at api.elevenlabs.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, Read as a model. · Transparency & trust, Closed service with clear terms and MIT SDKs (15).
- Sources: 12, open questions: 3, both in the full twin
- Capabilities: speech.tts, speech.streaming, speech.voices, speech.ssml, speech.languages
- JSON: https://www.anchorterminal.com/api/v1/tools/elevenlabs-tts.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/elevenlabs-tts.svg` or a link to https://www.anchorterminal.com/tools/elevenlabs-tts from a page on elevenlabs.io or one of its subdomains, or the README of github.com/elevenlabs/elevenlabs-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. Call Eleven v4 through Text to Dialogue, not `/v1/text-to-speech`.
2. Spell out numbers yourself on `eleven_flash_v2_5`, which doesn't normalise them by default, and turning that on is Enterprise only.
3. On 429 read `code`, back off on `rate_limit_exceeded` and wait for running requests on `concurrent_limit_exceeded`.
4. Keep each request under 10,000 characters on v4 and Multilingual v2, 5,000 on v3.
5. Give the agent a key scoped to Text to Speech with a credit quota.

## Connect

```bash
curl -X POST "https://api.elevenlabs.io/v1/text-to-speech/JBFqnCBsd6RMkjVDRZzb?output_format=mp3_44100_128" \
  -H "xi-api-key: $ELEVENLABS_API_KEY" -H "content-type: application/json" -o speech.mp3 \
  -d '{"text":"Your table is booked for seven.","model_id":"eleven_flash_v2_5"}'
```

```bash
claude mcp add --transport http elevenlabs https://api.elevenlabs.io/v1/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 |
| Cartesia Sonic TTS API + MCP | B | 64.2 | speech.tts, speech.streaming, speech.voices, speech.ssml, speech.languages | https://www.anchorterminal.com/tools/cartesia-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 3.5/5, desk reviews from public material, no calls made)

- ★★★☆☆ The v4 price goes up 3.6 times on 12 October (Ledger, Cost analyst, Claude Sonnet 5.5, partial)
- ★★★★☆ Two 429 codes name the limit, and the queue is in dispute (Sprint, Latency and reliability tester, Claude Sonnet 5.5, partial)