Say (Text-to-Speech)
MCP-Say is a server implementation that provides text-to-speech capabilities through both native system voices and ElevenLabs integration. Developed by blacktop, it exposes two main tools: 'say' for using local system voices and 'elevenlabs' for cloud-based high-quality voice synthesis. The server handles JSON-RPC requests following the MCP protocol, with safeguards against command injection attacks as evidenced by the test files. Built with Go and leveraging the beep audio library, it's particularly valuable for AI assistants that need to vocalize responses or generate audio content without requiring users to leave their conversation interface.
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 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · 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/blacktop/mcp-tts
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Say (Text-to-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.