Voice Hooks
Real-time voice interaction system for Claude Code that enables natural speech-based conversations during AI-assisted development workflows. Built with TypeScript and Express, it provides browser-based speech recognition, text-to-speech responses, and a comprehensive hook system that integrates with Claude's execution flow to ensure proper conversation state management. The implementation includes utterance queuing with pending/delivered/responded status tracking, voice preference controls, and validation hooks that prevent tool execution or conversation termination until voice interactions are properly processed. Designed for developers who want hands-free interaction with Claude Code, allowing them to speak naturally while the AI works, interrupt or redirect conversations mid-execution, and receive spoken responses without breaking the development flow.
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
- browser-automation
- Source
- PulseMCP
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Voice Hooks 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.