kokoro-tts-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TTS_AUTO | No | Set to true to start with auto-speak on. | false |
| TTS_SPEED | No | Playback speed, 0.5 – 2.0. | 1.0 |
| TTS_VOICE | No | Default voice (e.g. af_heart). | af_heart |
| TTS_ENABLED | No | Set to false to start muted. | true |
| TTS_BASE_DIR | No | Data directory (venv, state). | ~/.kokoro-tts |
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 |
|---|---|
| tts_configA | View or change TTS settings. Call with no parameters to see current config. Use to: enable/disable TTS, turn auto-speak on/off (auto-speak makes Claude speak every response), change voice, change speed. When the user says 'mute tts', 'unmute tts', 'tts on', 'tts off', 'stop speaking', 'start speaking', 'auto speak', 'speak all responses', 'change voice', or 'change speed' — use this tool. |
| speakA | Convert text to speech and play it through speakers using Kokoro TTS (local, free, no API key needed). IMPORTANT: If auto-speak is enabled (check via tts_config), you MUST call this tool with your full response text for EVERY response, no exceptions. Never skip calling speak when auto-speak is ON. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
The two tools have clearly separate purposes: tts_config manages settings (enable/disable, auto-speak, voice, speed) while speak performs text-to-speech playback. Descriptions explicitly cross-reference each other, so an agent can trivially choose the right tool.
Both names are lowercase snake_case, but tts_config is a noun-style resource name while speak is a bare verb, a minor deviation from a single convention. With only two tools the pattern remains readable and predictable.
Two tools is on the light side, but the server's scope is narrow (local TTS playback plus configuration), and both tools earn their place without redundancy. Slightly thin if one expected richer voice management, but reasonable overall.
Configuration covers the key lifecycle controls (enable/disable, auto-speak, voice, speed) and speak handles playback with clear guidance on when to invoke it. Minor gaps like listing available voices or pausing/stopping mid-utterance are handled indirectly via disabling TTS.