Voice Interface
This MCP Voice Interface server provides browser-based voice input/output capabilities for AI Assistant conversations, featuring real-time speech-to-text recognition, text-to-speech synthesis, and voice message queuing through a web interface served on both HTTP and HTTPS ports. Built with Express, the MCP SDK, and Web Speech APIs, it offers tools for voice conversations through a 'converse' tool that speaks text and waits for voice responses, voice status monitoring, and message delivery management, while including an OpenCode plugin for automatic voice message forwarding to busy sessions. The implementation features self-signed certificate generation for HTTPS support, Server-Sent Events for real-time browser communication, configurable speech settings, and always-on microphone modes, making it valuable for hands-free AI interactions, accessibility applications, and voice-driven workflows where users need natural speech-based communication with AI assistants.
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
- browser-automation
- Source
- PulseMCP
- Repository
- github.com/shantur/jarvis-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Voice Interface 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.