https://github.com/k2wanko/voicepeak-mcp
MCP server for VOICEPEAK text-to-speech synthesis
https://github.com/k2wanko/voicepeak-mcp
ai-assistant bun claude mcp model-context-protocol speech-synthesis text-to-speech tts typescript voicepeak
Last synced: 8 months ago
JSON representation
MCP server for VOICEPEAK text-to-speech synthesis
- Host: GitHub
- URL: https://github.com/k2wanko/voicepeak-mcp
- Owner: k2wanko
- License: mit
- Created: 2025-10-04T14:33:37.000Z (9 months ago)
- Default Branch: main
- Last Pushed: 2025-10-04T16:56:00.000Z (9 months ago)
- Last Synced: 2025-10-04T17:21:30.903Z (9 months ago)
- Topics: ai-assistant, bun, claude, mcp, model-context-protocol, speech-synthesis, text-to-speech, tts, typescript, voicepeak
- Language: TypeScript
- Homepage:
- Size: 78.1 KB
- Stars: 2
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.en.md
- License: LICENSE
Awesome Lists containing this project
README
# voicepeak-mcp
MCP server for VOICEPEAK text-to-speech synthesis.
## Prerequisites
- VOICEPEAK installed
## Installation
### Using NPX (Recommended)
```bash
npx voicepeak-mcp@latest
```
### Using Bunx
```bash
bunx voicepeak-mcp
```
## Configuration
Add to your Claude Desktop configuration:
```json
{
"mcpServers": {
"voicepeak": {
"command": "npx",
"args": ["voicepeak-mcp@latest"]
}
}
}
```
## Available Tools
### synthesize
Generate speech audio file from text.
Parameters:
- `text` (required): Text to synthesize
- `narrator`: Narrator name
- `emotion`: Emotion parameters
- `speed`: Speech speed (50-200)
- `pitch`: Speech pitch (-300 to 300)
- `outputPath`: Output file path
### synthesize_and_play
Generate and immediately play speech.
### play
Play an audio file.
### list_narrators
List available narrators.
### list_emotions
List available emotions for a narrator.
### dictionary_list
List all pronunciation dictionary entries.
**Note**: Dictionary features are not available on Windows. Windows users should manage pronunciation dictionary through the VOICEPEAK application.
### dictionary_add
Add or update a dictionary entry for custom pronunciation.
Parameters:
- `surface` (required): Text to be replaced
- `pronunciation` (required): Japanese kana pronunciation
- `priority`: Priority (0-10, default: 5)
**Note**: Not available on Windows.
### dictionary_remove
Remove a dictionary entry.
**Note**: Not available on Windows.
### dictionary_find
Find dictionary entries by text.
**Note**: Not available on Windows.
### dictionary_clear
Clear all dictionary entries.
**Note**: Not available on Windows.
## Supported Platforms
- ✅ macOS (full support)
- ⚠️ Windows (partial support: speech synthesis and playback only, dictionary features not supported)
- 🚧 Linux (planned)
### Windows Limitations
On Windows, dictionary management features (dictionary_*) are not available. If you need custom pronunciation, please manage the dictionary through the VOICEPEAK application.
## Contributing
Issues and pull requests are welcome!