clear_queue
再生キューをクリア
LABSCO SUMMARY
Spoken replies, with the queue under your control.
Synthesis is asynchronous and queued, which is what makes voice output usable during a working session rather than a novelty. The per-session and unused-voice tools are the thoughtful part: run several agents at once and each one sounds like a different speaker.
What it is
An MCP server that sends text to a locally running VOICEVOX engine and plays the synthesized audio, with a playback queue you can inspect and clear.
What you get
- Text synthesized and played asynchronously, so a long line does not block the conversation
- The available voices listed, with playback speed and default voice set by configuration
- The playback queue's state readable, and clearable when the backlog is no longer wanted
- Voice ids currently in use across all processes, so two sessions do not end up sounding identical
- A random unused voice on request, and a per-session voice that stays fixed for the length of that session
- Playback handled per platform: afplay on macOS, pw-play or paplay on Linux, PowerShell on Windows
Requirements
Node.js 18 or newer, and VOICEVOX installed and running — the server talks to it at the local address in VOICEVOX_URL, which the shipped configuration already fills in. DEFAULT_VOICE_ID and DEFAULT_SPEED set the starting voice and rate. Linux additionally needs PipeWire's pw-play or PulseAudio's paplay; macOS and Windows need nothing extra.
Setup effort
One command — npx -y @arrow2nd/vv-mcp
USE CASES
01
Hearing a reply while your eyes are on the code
Send the text to be spoken and keep working — playback is asynchronous, so the conversation does not wait for it.
02
Choosing a voice you can listen to all day
List the available voices and set the one that works as your default speed and speaker.
03
Telling two agents apart by ear
Take a voice not currently in use, or hold one fixed for the session, so parallel sessions are distinguishable without looking.
04
Stopping a backlog you no longer want to hear
Check what is queued and clear it, instead of waiting out several minutes of speech that is now irrelevant.
05
Following a long build or run by sound
Have milestones spoken as they happen, so a long-running task can be monitored from across the room.
7 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
get_queue_status
再生キューの状態を取得
get_random_unused_voice
使用されていない音声をランダムに1つ取得
get_session_voice
このセッションで使用する音声を取得（セッション毎に固定）
get_voices_in_use
現在使用中の音声IDのリストを取得（全プロセス共通）
list_voices
利用可能な音声の一覧を取得
say
VOICEVOXで音声合成して再生（非同期実行）
BEFORE YOU INSTALL
What to know first
Tools you get
7 tools when we connected.
Requires
- npx on PATH
- Node.js 18
- VOICEVOX_URL in your environment
- DEFAULT_VOICE_ID in your environment
- DEFAULT_SPEED in your environment
CONTEXT COST
Light Standing cost
Rated by the size of the 7 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Add the block to your client, or run the command directly.
Server setup
Configuration file
JSON
{
"mcpServers": {
"vv-mcp": {
"command": "npx",
"args": [
"-y",
"@arrow2nd/vv-mcp"
],
"env": {
"VOICEVOX_URL": "http://localhost:50021",
"DEFAULT_VOICE_ID": "47",
"DEFAULT_SPEED": "1.0"
}
}
}
}npx
TERMINAL
npx -y @arrow2nd/vv-mcp
