MCP server for streaming text-to-speech via PocketTTS
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"pocket-tts-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# pocket-tts-mcp MCP server for streaming text-to-speech via [PocketTTS](https://github.com/KoljaB/PocketTTS). Speaks text out loud with near-instant playback — audio streams to speakers in ~200ms. ## Install ```bash # Run directly (no install needed) uvx pocket-tts-mcp # Or install globally pip install pocket-tts-mcp ``` ## Claude Code integration Add to your Claude Code MCP config: ```json { "mcpServers": { "pockettts": { "command": "uvx", "args": ["pocket-tts-mcp"] } } } ``` ## Tools ### `speak(text, voice?)` Queue text for playback. Returns immediately with a speech ID. Voices: `"male"` (default), `"female"`. ### `speech_status()` Check how much audio is queued. Returns instantly. ### `await_speech(id?)` Block until speech finishes. No args = wait for all. Pass an ID to wait for just that item.
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.