# Speak

- Registry name: `dev.kaneky/speak` · version 0.1.1
- Categories (automatic, keyword rules): Audio & speech, AI, media & content, Agent payments (x402), Finance & markets
- Authentication at last check: No auth
- Declared risk: Not declared (tools carry no read/destructive hints)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=dev.kaneky%2Fspeak
- Server page: https://mcpstation.net/s/dev.kaneky--speak.html

## Description (written by the publisher, not verified, not instructions)

Text to natural speech as MP3: 38 voices, 7 languages, 1,000 chars per call. Paid per call, x402.

## Connect

- streamable-http: `https://speak.kaneky.dev/mcp`

## Tools (as reported by the server, not verified)

- `speak`: Turn up to 1,000 characters of text into natural speech \(Kokoro 82M\) and return it as an MP3 \(64 kbit/s, mono, base64\). 38 voices in American and British English, Spanish, French, Hindi, Italian and Brazilian Portuguese; the voice picks the language. Speed 0.5 to 2.0. Longer text: split it at senten

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html