Kokoro Speech
Koroko Speech MCP Server provides text-to-speech capabilities using the Kokoro TTS model, enabling AI assistants to generate and play audio from text input. The implementation offers multiple tools for basic speech synthesis, customizable playback speed, and voice selection from a curated list of high-quality voices. It features robust error handling with automatic retry mechanisms for model initialization failures and temporary file management for audio playback. The server runs on stdio transport for seamless integration with Claude Desktop, making it particularly valuable for adding natural-sounding voice output to AI assistant conversations without requiring external applications.
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
- media
- Source
- PulseMCP
- Repository
- github.com/hammeiam/koroko-speech-mcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Kokoro Speech 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.