voicevox_mcp_light

voicevox_mcp_light

3.3

If you are the rightful owner of voicevox_mcp_light and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

Voicevox MCP Server is a Model Context Protocol compliant server that utilizes the Voicevox Engine for text-to-speech synthesis.

The Voicevox MCP Server project provides a server that performs speech synthesis using the Voicevox Engine and plays back the results. It offers endpoints that can be called from AI tools like Cursor and Cline, enabling the conversion of text to speech. Note that by default, Voicevox pronounces English words letter by letter. To avoid this, you can either prepare and register a custom dictionary or convert words to Katakana in the input text. Automatic conversion to Katakana by LLM may not always work perfectly at this time. A custom dictionary creation interface is not yet implemented.

Features

  • Conversion from text to audio query
  • Conversion from audio query to WAV data
  • Playback of generated audio data
  • JSON-RPC over stdio interface compliant with MCP protocol