# @kajidog/mcp-tts-voicevox [Health: Active]

**Category:** 🎧 Text-to-Speech  
**Repository:** https://github.com/kajidog/mcp-tts-voicevox  
**GitHub Stars:** 16  
**Views:** 0  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/kajidog-mcp-tts-voicevox

## Description
VOICEVOX integration for MCP - Text-to-Speech server using VOICEVOX engine

## Tools
Capabilities this server exposes over MCP:

- **voicevox_ping** — Check if VOICEVOX Engine is running and reachable
- **voicevox_stop_speaker** — Stop current audio playback
- **voicevox_get_speakers** — Get a list of available speakers. The returned "speaker" field is the exact ID to pass to speak.speaker
- **voicevox_speak** — Play text as speech immediately. Use this for simple TTS — no UI, no editing. If you need a player UI or want to edit/replay segments, use voicevox_speak_player instead.
- **voicevox_synthesize_file** — Generate an audio file and return its absolute path
- **voicevox_get_accent_phrases** — Get accent phrases (reading and accent positions) from text. Returns inline notation like "コン[ニ]チワ,セ[カ]イ" where brackets indicate accent position.
- **voicevox_get_user_dictionary** — Get words in the VOICEVOX user dictionary. Supports filtering by query and pagination. Pronunciation uses inline accent notation (e.g. "ボイス[ボッ]クス").
- **voicevox_add_user_dictionary_word** — Add a word to the VOICEVOX user dictionary. Pronunciation supports inline accent notation (e.g. "ボイス[ボッ]クス"). If brackets are omitted, accent is auto-estimated.
- **voicevox_update_user_dictionary_word** — Update a word in the VOICEVOX user dictionary. surface and pronunciation are optional — omitted fields keep their existing values. Pronunciation supports inline accent notation.
- **voicevox_delete_user_dictionary_word** — Delete a word from the VOICEVOX user dictionary.
- **voicevox_add_user_dictionary_words** — Add multiple words to the VOICEVOX user dictionary at once. Pronunciation supports inline accent notation.
- **voicevox_update_user_dictionary_words** — Update multiple words in the VOICEVOX user dictionary at once. surface and pronunciation are optional per word — omitted fields keep existing values.
- **voicevox_open_dictionary_ui** — Open the user dictionary manager UI for VOICEVOX.
- **voicevox_speak_player** — Use when you need a player UI (display, edit, or replay audio). Creates a VOICEVOX player session, returns viewUUID. Multi-speaker format: "1:Hello\n2:World". For simple playback without UI, use voicevox_speak instead.
- **voicevox_resynthesize_player** — Edit one player track by index. Requires viewUUID from speak_player/resynthesize_player. Returns new viewUUID.
- **_get_speakers_for_player** — Get speaker list for the player UI. This tool is only callable from the app UI.
- **_get_speaker_icon_for_player** — Get speaker portrait icon by UUID. Only callable from the app UI.
- **_get_player_state_for_player** — Fetch full player segments (including audioQuery/accentPhrases) for a viewUUID. Only callable from the app UI.
- **_save_player_state_for_player** — Persist current player segments to server state without synthesizing audio. Only callable from the app UI.
- **_resynthesize_for_player** — Re-synthesize audio with a different speaker or updated parameters. Only callable from the app UI.
- **_get_user_dictionary_for_player** — Get VOICEVOX user dictionary words for the dictionary manager UI.
- **_add_user_dictionary_word_for_player** — Add a word to VOICEVOX user dictionary.
- **_update_user_dictionary_word_for_player** — Update a VOICEVOX user dictionary word.
- **_delete_user_dictionary_word_for_player** — Delete a VOICEVOX user dictionary word.
- **_preview_dictionary_word_for_player** — Preview pronunciation with a random speaker.
- **_get_export_capability_for_player** — Return whether track export + folder open is available for player UI.
- **_select_directory_for_player** — Open a native OS directory picker dialog, to be called from the player UI.
- **_export_tracks_for_player** — Save player tracks as wav files and open the target folder in file explorer.
- **voicevox_get_player_state** — Read current player state (segments, accent phrases). Use latest viewUUID from speak_player/resynthesize_player. If hasMore is true, call again with nextCursor.

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "mcp-tts-voicevox": {
    "command": "npx",
    "args": ["-y","@kajidog/mcp-tts-voicevox"]
  }
}
```

## Documentation

## What @kajidog/mcp-tts-voicevox does

@kajidog/mcp-tts-voicevox exposes VOICEVOX speech synthesis through MCP. An AI assistant can submit text, choose a speaker, adjust playback speed, and control whether playback starts immediately or waits for completion. Multiple dialogue segments can use different speakers in one request.

The server supports two playback paths. `voicevox_speak` plays generated audio on the server, while `voicevox_speak_player` creates an interactive MCP Apps player that sends playback to the client. The player is useful for remote connections and environments without an audio device on the server.

The player can manage multiple tracks, switch speakers, edit speech parameters, adjust accent phrases, and export numbered WAV files. It also includes a VOICEVOX user dictionary interface and restores player state across sessions.

## How it works

The server communicates with a running VOICEVOX Engine instance. A standard local setup uses stdio and can be launched through `npx` or `bunx`; Claude Desktop starts the process from its MCP configuration. Docker Compose starts both the MCP server and VOICEVOX Engine, exposing the MCP endpoint over HTTP on port 3000.

The `voicevox_speak` tool accepts plain text or inline accent notation. Newline-separated segments can specify speaker IDs individually, allowing a single request to produce a multi-character exchange. When `ffplay` is installed and available on `PATH`, playback can use low-latency streaming; otherwise, the server falls back to temporary-file playback through the operating system's available audio player.

MCP Apps-compatible hosts can render the player UI in the conversation. The documented player clients are Claude Desktop and ChatGPT, with ChatGPT remote HTTP use requiring `VOICEVOX_PLAYER_DOMAIN`.

## Setup and configuration

Install Node.js 24 or later, use Bun, or run the Docker setup. Start VOICEVOX Engine before launching the local MCP process. FFplay is optional, but installing FFmpeg enables streaming playback when `ffplay` is on the system path.

A Claude Desktop stdio configuration can launch the package with:

```json
{
  "mcpServers": {
    "tts-mcp": {
      "command": "npx",
      "args": ["-y", "@kajidog/mcp-tts-voicevox"]
    }
  }
}
```

For Docker, run `docker compose up -d`, then connect Claude Desktop through `mcp-remote` at `http://localhost:3000/mcp`. The container has no audio device, so server-side `voicevox_speak` playback is disabled by default in that setup; use the client-side player instead.

Docker's published port has no authentication by default. Set `MCP_API_KEY` and send it with the `X-API-Key` header, or keep the port restricted to a trusted network. `VOICEVOX_ALLOWED_OUTPUT_DIRS` can limit directories used by file-writing tools.

## Tools and capabilities

- `voicevox_speak`: Generate and play speech from text, with speaker, speed, queue, and completion controls.
- `voicevox_speak_player`: Create an interactive client-side audio player and return a view identifier.
- `voicevox_resynthesize_player`: Update every segment in an existing player session.
- `voicevox_get_player_state`: Read paginated state from a player session.
- `voicevox_open_dictionary_ui`: Open the VOICEVOX user dictionary manager.
- Edit speaker selection, speed, volume, intonation, pause lengths, silence, accent positions, and mora pitch in the player.
- Add, remove, reorder, preview, and export dialogue tracks as WAV files.

## Limitations and notes

VOICEVOX Engine must be running for speech synthesis. Server-side playback also depends on an accessible audio device and playback utility; Docker does not provide an audio device. Hosts without MCP Apps support cannot use `voicevox_speak_player`, so `voicevox_speak` is the fallback.

The player can export WAV files even when opening the file explorer is unavailable. Selecting an output folder uses a native directory picker on Windows and macOS; unsupported environments use the default export directory. Remote or exposed Docker deployments should be protected because the default port configuration has no authentication.

_Full upstream README: https://allmcps.com/mcp/kajidog-mcp-tts-voicevox/readme_