voiceroid_daemon-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VOICEROID_DAEMON_URL | No | voiceroid_daemon server URL (default: http://127.0.0.1:8080) | http://127.0.0.1:8080 |
| VOICEROID_DEFAULT_PITCH | No | Default voice pitch (0.5-2, default: 1.0) | 1.0 |
| VOICEROID_DEFAULT_SPEED | No | Default speech speed (0.5-4, default: 1.3) | 1.3 |
| VOICEROID_DEFAULT_VOLUME | No | Default voice volume (0-2, default: 1.0) | 1.0 |
| VOICEROID_DAEMON_PASSWORD | No | Basic authentication password | |
| VOICEROID_DAEMON_USERNAME | No | Basic authentication username | |
| VOICEROID_DEFAULT_EMPHASIS | No | Default emphasis level (0-2, default: 1.1) | 1.1 |
| VOICEROID_DEFAULT_PAUSE_LONG | No | Default pause long (100-2000, default: 370) | 370 |
| VOICEROID_DEFAULT_PAUSE_MIDDLE | No | Default pause middle (80-500, default: 150) | 150 |
| VOICEROID_DEFAULT_PAUSE_SENTENCE | No | Default pause sentence (0-10000, default: 800) | 800 |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| test_connectionB | Test connection to voiceroid_daemon server |
| convert_textB | Convert text to phonetic kana reading |
| speak_textC | Generate speech audio from text and play it |
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 3 tools
Each tool has a clearly distinct purpose with no overlap: convert_text handles phonetic conversion, speak_text handles speech generation and playback, and test_connection handles server connectivity testing. An agent can easily distinguish between these three functions.
All tools follow a consistent verb_noun pattern with snake_case naming: convert_text, speak_text, and test_connection. The naming is predictable and readable throughout the set.
Three tools is reasonable for a voiceroid daemon server, covering core text-to-speech operations and connectivity. It's slightly minimal but functional for the apparent scope, lacking only minor enhancements like configuration or status tools.
The toolset covers essential text-to-speech workflows: phonetic conversion, speech generation/playback, and server connectivity. Minor gaps exist, such as no tools for managing voice parameters, listing available voices, or controlling playback (e.g., stop/pause), but core functionality is present.