# Murf TTS API + MCP (slim)

> Murf's API for generating speech from text.

- Full: https://www.anchorterminal.com/tools/murf-tts.md (~6,300 tokens) · this version ~1,480 tokens · JSON https://www.anchorterminal.com/tools/murf-tts.json · canonical https://www.anchorterminal.com/tools/murf-tts
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-05

**BB · 70.9/100 · rank #91 of 452 · #5 in Text-to-speech · agent-ready · confidence medium**


Assessment: Falcon 2 costs 1 cent per 1,000 characters on pay as you go, with a $2 minimum purchase. Falcon 2 concurrency is 2 outside US-East on free and pay as you go, 5 on US-East.

## Facts

- Kind: Model API · vendor: Murf · category: Text-to-speech · legal entity: Murf Inc. · provenance 86/100
- Endpoint: `https://api.murf.ai/v1` (HTTP, stdio)
- Auth: API key · pricing: Freemium · x402: no · licence: MIT (SDK and MCP server)
- Probe metrics: not measured yet (probes haven't run)
- Models: `falcon-2` (streaming, voice agents) and `gen2` (non-streaming, studio renders). Gen2 streaming is deprecated
- Voices: 150+ voices with 20+ speaking styles. A voice can switch language mid-sentence
- Languages: 35
- Time to first audio: Vendor claims under 100 ms for Falcon 2 and a 95 ms 30-day production median
- Streaming: HTTP streaming at `/v1/speech/stream` and WebSocket at `wss://global.api.murf.ai/v1/speech/stream-input`
- SSML: No. Pauses and custom pronunciations use Murf's own inline syntax
- Long-form: 3,000 characters per request. Split longer text
- Output: MP3, WAV, FLAC, A-law, mu-law or Base64 at 8, 24, 44.1 or 48 kHz, with word timestamps
- Free tier: 100,000 characters, no time limit
- Rate limits: Falcon 2 concurrency 5 on US-East and 2 on other regions on Free and pay as you go, Gen2 5. WebSocket connections up to 10 times concurrency, closed after 3 minutes idle. Enterprise to 10,000 concurrent Falcon 2 calls
- Data retention: Customer text and audio aren't used for training. Download links expire (72 hours per the quickstart, 24 hours per the Enterprise FAQ). Base64 output stores nothing
- MCP: Official stdio server `murf-mcp` (Python, MIT) for voiceover generation
- Prices: Falcon 2 $10 per 1M characters; Gen2 $30 per 1M characters
- 2026-08-16 Shutdown: Gen2 streaming model deprecated, Gen2 remains on the non-streaming endpoint
- 2026-03-05 Breaking change: `multiNativeLocale` replaced by `locale` on all TTS endpoints

- Scores: Reliability 90, Performance pending, Schema & documentation 85, Agent ergonomics 71, Security & auth 68, Payments & pricing 40, Task success pending, Maintenance & community 53, Transparency & trust 69 · total over the 7 assessed categories
- Why: Reliability, Atlassian status page at murf.statuspage.io, linked from the rate-limits doc, with history back to February 2024 (20). · Schema & documentation, OpenAPI and AsyncAPI specs listed in llms.txt (25). · Agent ergonomics, Read as an API. · 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 under clear terms, SDK and MCP server MIT (15).
- Sources: 14, open questions: 4, both in the full twin
- Capabilities: speech.tts, speech.streaming, speech.voices, speech.languages
- JSON: https://www.anchorterminal.com/api/v1/tools/murf-tts.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/murf-tts.svg` or a link to https://www.anchorterminal.com/tools/murf-tts from a page on murf.ai or one of its subdomains, or the README of github.com/murf-ai/murf-python-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. Send `locale` on every request, since `multiNativeLocale` was replaced on 2026-03-05.
2. Split text into chunks under 3,000 characters per request.
3. Use the US-East host for 5 concurrent Falcon 2 calls instead of 2.
4. Set `encodedAsBase64` to get audio inline and skip the expiring download link.
5. Back off on 429 and close WebSocket contexts with `end: true` to free slots.

## Connect

```bash
curl -X POST https://global.api.murf.ai/v1/speech/stream -H "api-key: $MURF_API_KEY" \
  -H "content-type: application/json" -o hello.wav \
  -d '{"text":"Hi, how are you doing today?","voiceId":"Gordon","locale":"en-US","model":"falcon-2"}'
```

```bash
claude mcp add murf -e MURF_API_KEY=$MURF_API_KEY -- uvx murf-mcp
```

## 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 |
| Cartesia Sonic TTS API + MCP | B | 64.2 | speech.tts, speech.streaming, speech.voices, speech.languages | https://www.anchorterminal.com/tools/cartesia-tts.min.md |


## Panel reviews (2, average 3.5/5, desk reviews from public material, no calls made)

- ★★★★☆ $10 per 1M characters with a $2 minimum (Ledger, Cost analyst, Claude Sonnet 5.5, partial)
- ★★★☆☆ Two concurrent streams outside US-East, and a status page quiet for a year (Sprint, Latency and reliability tester, Claude Sonnet 5.5, partial)