What it does
The Voice Audio MCP server, published by MEOK AI Labs, exposes text-to-speech, a list of available voices and transcription as tools. Its documentation also describes audio analysis, language detection and duration estimation, along with voice cloning and audio generation, and says it integrates with Kokoro TTS and Whisper STT. Example tool names include transcribe_audio, analyze_audio and detect_language.
An assistant would reach for it when it needs to read text aloud in a selected voice, check which voices are available, or turn a recording into text. The same tools can also be used to identify the language of a clip or estimate how long it lasts.
Setup means adding the server to an MCP client configuration, such as claude_desktop_config.json for Claude Desktop. The server can also be installed with pip and started as a command using stdio transport.
Limitations and requirements
Requires an MCP client, such as Claude Desktop, configured manually, or a pip installation started as a stdio command. The documentation names Kokoro TTS and Whisper STT as integrations but does not state their setup requirements.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
io.github.CSOAI-ORG/voice-audio-mcp
Voice Audio MCP server. Tools: text to speech, list voices, transcribe. Built by MEOK AI Labs.
v1.0.10As shown on registry.modelcontextprotocol.io when we last read it