OpenCode Voice MCP Server
The OpenCode Voice MCP Server provides local, privacy-first voice input for AI coding assistants. You can record audio, transcribe it to text, and optionally type it at the cursorβall offline.
voice_transcribe: Records audio (configurable duration) and transcribes it to text using a local Whisper model. Supports 99+ languages with auto-detect or specified language code.
voice_type: Records audio, transcribes it, and automatically types the text at the current cursor position in the active window.
voice_status: Checks system readiness by verifying recording/transcription dependencies (e.g., sox, ffmpeg, faster-whisper) and returns platform, engine, and readiness details.
π 100% offline & private β Audio processed locally; no cloud.
π Multi-language β 99+ languages via Whisper.
π» Cross-platform β macOS, Linux, Windows (requires sox/ffmpeg).
π§ Configurable β Model size, device, compute type via environment variables.
π MCP-compatible β Works with OpenCode, Claude Code, Cursor, and other MCP clients.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@OpenCode Voice MCP Server Record 5 seconds and type what I say"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
π€ OpenCode Voice MCP Server
Voice Input for AI Coding Assistants
Speak your prompts. No typing required.
Installation β’ Quick Start β’ Tools β’ Configuration β’ Architecture β’ Contributing
β¨ Features
Feature | Description |
π€ Voice Recording | Record audio from microphone with configurable duration |
π£οΈ Speech-to-Text | Transcribe using local Whisper model (100% offline) |
β¨οΈ Auto-Typing | Type transcribed text at cursor position |
π Privacy First | No cloud API β audio never leaves your machine |
π Multi-Language | Support for 99+ languages via Whisper |
π MCP Standard | Works with OpenCode, Claude Code, Cursor, and more |
Related MCP server: Claude Voice Commands
π¦ Installation
# Install globally
npm install -g @yuvarjbhado/voice-mcp
# Or use with npx (no install required)
npx @yuvarjbhado/voice-mcpPrerequisites
# Install recording tool
brew install sox
# Install transcription engine
pip install faster-whisper# Install recording tool
sudo apt install sox
# Install transcription engine
pip install faster-whisper# Install FFmpeg (via scoop)
scoop install ffmpeg
# Install transcription engine
pip install faster-whisperπ Quick Start
Step 1: Configure MCP Server
Add to your MCP config file:
Tool | Config Location |
OpenCode |
|
Claude Code |
|
Cursor |
|
OpenCode (use mcp key):
{
"mcp": {
"voice": {
"command": "npx",
"args": ["-y", "@yuvarjbhado/voice-mcp"]
}
}
}Claude Desktop / Cursor (use mcpServers key):
{
"mcpServers": {
"voice": {
"command": "npx",
"args": ["-y", "@yuvarjbhado/voice-mcp"]
}
}
}Step 2: Restart Your Tool
Restart OpenCode, Claude Code, or Cursor to load the MCP server.
Step 3: Use Voice Input
@voice voice_transcribe
@voice voice_type
@voice voice_statusπ οΈ Tools
voice_transcribe
Record audio from microphone and transcribe to text.
{
"name": "voice_transcribe",
"arguments": {
"duration": 10,
"language": "en"
}
}Parameter | Type | Default | Description |
| number |
| Recording duration in seconds |
| string |
| Language code (e.g., |
Returns: Transcribed text as string.
voice_type
Record audio, transcribe to text, and type it at the cursor position.
{
"name": "voice_type",
"arguments": {
"duration": 10,
"language": "en"
}
}Parameter | Type | Default | Description |
| number |
| Recording duration in seconds |
| string |
| Language code |
Returns: Confirmation message with typed text.
voice_status
Check if voice recording and transcription are available.
{
"name": "voice_status",
"arguments": {}
}Returns:
{
"recording": "rec",
"transcription": "faster-whisper (local)",
"platform": "darwin",
"ready": true
}βοΈ Configuration
Environment Variables
Variable | Description | Default |
| Whisper model size |
|
| Device to use ( |
|
| Compute type ( |
|
Model Sizes
Model | Size | Speed | Accuracy | VRAM |
| ~75MB | β‘β‘β‘β‘ | ββ | ~1GB |
| ~150MB | β‘β‘β‘ | βββ | ~1GB |
| ~500MB | β‘β‘ | ββββ | ~2GB |
| ~1.5GB | β‘ | βββββ | ~5GB |
| ~3GB | π | βββββ | ~10GB |
Recommendation: Use base for best balance of speed and accuracy.
ποΈ Architecture
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β MCP Client β
β (OpenCode / Claude Code / Cursor) β
ββββββββββββββββββββββββββββ¬βββββββββββββββββββββββββββββββββββββββ
β JSON-RPC
βΌ
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β Voice MCP Server β
β (Node.js) β
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ€
β ββββββββββββββββ ββββββββββββββββ ββββββββββββββββ β
β β voice_record β βvoice_transcribeβ β voice_type β β
β β Tool β β Tool β β Tool β β
β ββββββββ¬ββββββββ ββββββββ¬ββββββββ ββββββββ¬ββββββββ β
β β β β β
β βΌ βΌ βΌ β
β βββββββββββββββββββββββββββββββββββββββββββββββββββββββ β
β β Audio Recording Layer β β
β β (sox / ffmpeg / macOS rec) β β
β βββββββββββββββββββββββββββ¬ββββββββββββββββββββββββββββ β
β β β
β βΌ β
β βββββββββββββββββββββββββββββββββββββββββββββββββββββββ β
β β Transcription Engine β β
β β (faster-whisper / OpenAI API) β β
β βββββββββββββββββββββββββββ¬ββββββββββββββββββββββββββββ β
β β β
β βΌ β
β βββββββββββββββββββββββββββββββββββββββββββββββββββββββ β
β β Output Layer β β
β β βββββββββββββββ βββββββββββββββββββββββ β β
β β β Return Text β β Type at Cursor β β β
β β β (MCP) β β (osascript/xdotool) β β β
β β βββββββββββββββ βββββββββββββββββββββββ β β
β βββββββββββββββββββββββββββββββββββββββββββββββββββββββ β
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββData Flow
βββββββββββ βββββββββββ βββββββββββββββ βββββββββββ
β User βββββΆβ Micro- βββββΆβ Whisper βββββΆβ Text β
β Speaks β β phone β β Transcribe β β Output β
βββββββββββ βββββββββββ βββββββββββββββ βββββββββββ
β β β β
β β β β
βΌ βΌ βΌ βΌ
"Hello Records 16kHz Processes with Returns text
world" mono audio base model or types itπ§ Development
Setup
# Clone repository
git clone https://github.com/YuvrajSinghBhadoria2/opencode-voice-mcp.git
cd opencode-voice-mcp
# Install dependencies
npm install
# Build
npm run build
# Run in development
npm run devProject Structure
opencode-voice-mcp/
βββ src/
β βββ index.ts # MCP server implementation
βββ dist/
β βββ index.js # Compiled output
βββ package.json # Package configuration
βββ tsconfig.json # TypeScript config
βββ build.sh # Build script
βββ publish.sh # npm publish scriptAvailable Scripts
Command | Description |
| Compile TypeScript to JavaScript |
| Run in development mode with tsx |
| Run compiled server |
| Build and publish to npm |
π€ Contributing
Contributions are welcome! Please follow these steps:
Fork the repository
Create a feature branch (
git checkout -b feat/amazing-feature)Commit your changes (
git commit -m 'feat: add amazing feature')Push to the branch (
git push origin feat/amazing-feature)Open a Pull Request
Development Guidelines
Follow TypeScript best practices
Add tests for new features
Update documentation as needed
Use conventional commit messages
π License
This project is licensed under the MIT License - see the LICENSE file for details.
π Acknowledgments
Model Context Protocol - Standard for AI tool integration
faster-whisper - Fast Whisper implementation
OpenCode - AI coding assistant
OpenAI Whisper - Speech recognition model
Built with β€οΈ for the developer community
Report Bug β’ Request Feature β’ Discussions
Available Tools
3 toolsvoice_statusA
Check if voice recording and transcription are available.
Inputs: no named parameters.
voice_transcribeA
Record audio from microphone and transcribe to text. Returns the transcribed text.
Inputs: duration, language.
voice_typeA
Record audio, transcribe to text, and type it at the cursor position in the active window.
Inputs: duration, language.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
TDQS
Scored across 3 tools
voice_transcribe and voice_type both perform recording and transcription, differing only in whether the result is typed into the active window. This creates some overlap, though voice_status is clearly distinct. Descriptions clarify the intended use.
The voice_ prefix is consistent across all tools, but the suffix alternates between a verb (transcribe, type) and a noun (status), slightly breaking the uniform verb pattern. Overall, the naming is predictable and readable.
With only three tools, the server is tightly scoped to the core voice capture and transcription workflows. Each tool serves a clear purpose, and the count feels appropriate for the narrow domain.
The server covers the primary actions of transcribing and typing, plus a status check. Missing optional features like language selection or audio device configuration, but these are not essential to the main workflow.
Related MCP Connectors
Use AI models for chat, image, and video generation from Claude Code and other MCP hosts.
Carbon Voice MCP serves as a bridge that connects AI assistants like ChatGPT, Claude, and Cursor to a user's Carbon Voice account, turning voice messages and conversations into a private, on-demand knowledge base. It provides 28 specialized tools for comprehensive voice messaging management, including creating and sending messages, accessing conversation history with instant transcription, running AI actions (summarization, TLDR generation, meeting notes), and managing workspace collaboration through folders, contacts, and team communications.
AI voice generation: text-to-speech and voice cloning from any MCP client.
Make AI videos and images in Qulture Studio from ChatGPT, Claude, Cursor or any MCP client.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables recording audio from a microphone and transcribing it using OpenAI's Whisper model. Works as both a standalone MCP server and a Goose AI agent extension.6MIT
- FlicenseNot gradedqualityDmaintenanceEnables natural voice interaction with Claude Code through speech-to-text, supporting wake word activation and multiple backends like Whisper and Google. It allows users to execute commands and control their coding environment hands-free via their microphone.2-
- AlicenseAqualityDmaintenanceEnables continuous voice conversation with AI coding assistants by locally transcribing speech with Whisper and delivering utterances as text prompts.41MIT
- AlicenseAqualityDmaintenanceLocal speech-to-text transcription using Microsoft's VibeVoice-ASR model with speaker diarization, enabling audio transcription directly in AI tools like Claude Code, Cursor, and OpenCode.33MIT