# Voice Interface
> Provides browser-based voice input/output capabilities for conversations, featuring real-time speech-to-text recognition, text-to-speech synthesis, and voice message queuing through a web interface for hands-free interactions and accessibility applications.
Canonical: https://www.mcpfolio.com/servers/voice-interface
Last updated: 2026-10-28
## Catalog record

- Publisher: shantur
- Categories: communication

## Repository

https://github.com/shantur/jarvis-mcp

## Transports

stdio

## Authentication

No credentials were configured; the tested read-only tool “voice_status” succeeded in an isolated environment. Other tools may have additional requirements.

## Tools

- **speak**: Speak text using browser text-to-speech
- **voice_status**: Get current voice system status and pending voice input
- **get_voice_input**: Get pending voice input from users (auto-delivered by default)
- **converse**: Have a voice conversation with the user - speak text and wait for voice response. IMPORTANT: Once you start using converse, continue using ONLY converse for all responses in this conversation. Do not switch back to text.
- **end_conversation**: End the voice conversation by saying goodbye and stopping the browser interface

## Sources

- [MCP.Directory public profile](https://mcp.directory/servers/voice-interface)
- [Linked publisher repository](https://github.com/shantur/jarvis-mcp)
- [npm-declared package repository](https://github.com/shantur/mcp-voice-interface)
- [npm registry metadata](https://registry.npmjs.org/%40shantur%2Fjarvis-mcp)

## Setup

Use the interactive setup panel on [the detail page](https://www.mcpfolio.com/servers/voice-interface) to view instructions for each supported client.