Speak is answering right now. Last checked 9 min ago. It exposes 1 tools.
Text to natural speech as MP3: 38 voices, 7 languages, 1,000 chars per call. Paid per call, x402.
Nothing serious here today
Today is the operative word: we check Speak every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 9 min ago.
claude mcp add speak --transport http https://speak.kaneky.dev/mcphttps://speak.kaneky.dev/mcp[mcp_servers.speak]
url = "https://speak.kaneky.dev/mcp"{
"mcpServers": {
"speak": {
"url": "https://speak.kaneky.dev/mcp"
}
}
}{
"servers": {
"speak": {
"type": "http",
"url": "https://speak.kaneky.dev/mcp"
}
}
}Available tools 1
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
speak
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://speak.kaneky.dev/mcp | streamable-http | answering | 179 ms | 9 min ago |
Alternatives to Speak
same job, measured the same wayGive Your Agent A Voice: x402 pay-per-call speech with 20 voices, 10 personas, 31 languages.
Text to speech in 200+ languages, voice cloning, voice design and SRT captions.
Turn text into natural-sounding MP3 voice-overs in 6 languages. Free plan included.
Text-to-speech with 200+ voices in 70+ languages. Requires a LuvVoice API token.
Local text to speech in about 190 voices and 31 languages, offline with no limits.
Everyday tools for AI agents, paid per call with x402: images, markdown, speech-to-text, embeddings.
API discovery and x402 paid execution via MCP. Search by natural-language, call with USDC payment
ElevenLabs in natural language: generate speech in any language, create and manage voices, compose m
Speak — questions
Answers built from our own checks of this server.