local-voice-mcp

Local Voice MCP Server

local-voice-mcp brings local text-to-speech and audio playback to MCP clients and AI agents. It supports reference-audio voice cloning, speech-style controls, and service-status checks.

Server facts

local-voice-mcp

Project

License
Not specified

Tech

Runtime / language
Not specified
Transports
stdio
Remote available
No
Authentication
Not specified

Activity

GitHub stars
13
Last commit
Data as of

Tags

  • audio
  • local
  • speech
  • tts
  • voice

Overview

Local speech generation and playback give MCP clients a workflow from written text to audible output. The synthesize_text tool creates speech and returns structured results with a generated audio file path. Reference audio can guide voice cloning, while Chatterbox settings adjust exaggeration and configuration weight. Clients can then pass the resulting file to play_audio, which handles WAV and MP3 playback through system audio players. That tool restricts files to the temporary directory and offers volume adjustment and cleanup. The tts_status tool reports the service’s operational state and available capabilities.

Voice selection can use the bundled female reference, the default Chatterbox male voice, or custom reference audio. Environment settings supply defaults for synthesis, output location, text length, and playback volume; tool-level options take precedence where provided. Beyond its stdio-based MCP interface, the project documents an HTTP mode with an ElevenLabs-compatible speech endpoint that returns WAV audio. This gives developers a direct HTTP integration route alongside the tool-based workflow for MCP clients such as Cursor.

local-voice-mcp setup notes

  • local-voice-mcp records stdio only; confirm a network transport upstream before planning remote access.
  • local-voice-mcp has no recorded license; confirm reuse terms in its repository.

Related MCP servers