voicevox_get_accent_phrases
Get reading and accent positions of a text as inline notation
How to use it
voicevox_get_accent_phrases is exposed by the MCP Tts Voicevox MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the voicevox_get_accent_phrases tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
Install MCP Tts Voicevox
npx @kajidog/mcp-tts-voicevox --url http://192.168.1.100:50021 --speaker 3 --speed 1.2Other tools in MCP Tts Voicevox (21)
Immediate playback (clears queue)
Inline accent notation (takes priority over text)
Speaker ID
Playback speed
Text to speak (multiple segments separated by newlines)
Add a word (pronunciation accepts inline accent notation)
Add multiple words at once
Delete a word by UUID
Read the current player state (paginated) for AI tuning.
Get list of available speakers
List user dictionary words (filter + pagination)
Open the user dictionary manager UI.
Check VOICEVOX Engine connection
Update all segments for an existing player (new viewUUID each call).
Create a new player session and display the UI. Returns viewUUID.
Stop playback and clear queue
Generate audio file
Update a word (omitted fields keep their value)
Update multiple words at once
Wait for playback completion
Wait for playback to start