VOICEPEAK
Built by k2wanko using TypeScript and Bun, this server provides Japanese text-to-speech synthesis capabilities through integration with the VOICEPEAK engine. It supports multiple narrators like Tohoku Zunko and Zundamon with customizable emotions, speed, and pitch parameters. The implementation features robust process management with queuing and retry logic, input validation and sanitization, cross-platform support for macOS/Windows/Linux, and pronunciation dictionary management for custom word pronunciations. Advanced safety features include path traversal protection, concurrent process limiting, automatic temp file cleanup, and WAV format validation, making it valuable for creating Japanese voice content, accessibility applications, and language learning tools.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- file-system
- Source
- PulseMCP
- Repository
- github.com/k2wanko/voicepeak-mcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve VOICEPEAK from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.