VOICEVOX TTS MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VOICEVOX_URL | No | VOICEVOX Engine URL | http://localhost:50021 |
| MCP_HTTP_HOST | No | HTTP host | 0.0.0.0 |
| MCP_HTTP_MODE | No | Enable HTTP mode | false |
| MCP_HTTP_PORT | No | HTTP port | 3000 |
| MCP_ALLOWED_HOSTS | No | Allowed hosts (comma-separated) | localhost,127.0.0.1,[::1] |
| MCP_ALLOWED_ORIGINS | No | Allowed origins (comma-separated) | http://localhost,http://127.0.0.1 |
| VOICEVOX_USE_STREAMING | No | Streaming playback (requires ffplay) | false |
| VOICEVOX_DISABLED_TOOLS | No | Comma-separated list of tools to disable (e.g., generate_query,synthesize_file) | |
| VOICEVOX_DEFAULT_SPEAKER | No | Default speaker ID | 1 |
| VOICEVOX_DEFAULT_IMMEDIATE | No | Immediate playback default setting | true |
| VOICEVOX_RESTRICT_IMMEDIATE | No | Restrict AI from specifying the immediate option | |
| VOICEVOX_DEFAULT_SPEED_SCALE | No | Default playback speed | 1.0 |
| VOICEVOX_DEFAULT_WAIT_FOR_END | No | Wait for playback end default setting | false |
| VOICEVOX_RESTRICT_WAIT_FOR_END | No | Restrict AI from specifying the waitForEnd option | |
| VOICEVOX_DEFAULT_WAIT_FOR_START | No | Wait for playback start default setting | false |
| VOICEVOX_RESTRICT_WAIT_FOR_START | No | Restrict AI from specifying the waitForStart option |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ping_voicevoxB | Check if VOICEVOX Engine is running and reachable |
| speakA | Convert text to speech and play it. Text is split by line breaks (\n) into separate speech units. Each line is processed as an independent audio segment. |
| generate_queryC | Generate a query for voice synthesis |
| synthesize_fileC | Generate an audio file and return its absolute path |
| stop_speakerA | Stop current audio playback |
| get_speakersC | Get a list of available speakers |
| get_speaker_detailC | Get detail of a speaker by id |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/kajidog/mcp-tts-voicevox'
If you have feedback or need assistance with the MCP directory API, please join our Discord server