This directory contains beginner-friendly, step-by-step integration guides for setting up Voice Mode with various AI coding assistants and development tools. Each guide assumes no prior experience with the tool and walks you through from installation to your first voice conversation.
- π€ Claude Code - Anthropic's official CLI for Claude
- π₯οΈ Claude Desktop - Claude's desktop application
- π Gemini CLI - Google's Gemini command-line interface
- π¦ Roo Code - Roo Coder assistant
- β‘ Cursor - The AI-first code editor
- π» VS Code - Visual Studio Code with MCP support
- π§ Cline - Autonomous coding agent for VS Code
- β‘ Zed - High-performance, multiplayer code editor
- π Windsurf - The IDE that writes code for you
- π Continue - Open-source AI code assistant
Note: These integration guides were created based on documentation and API specifications. We haven't yet tested installing and configuring each desktop application firsthand. If you're familiar with any of these tools, we'd greatly appreciate your review and feedback!
How you can help:
- Test the integration steps with your tool
- Submit issues for any inaccuracies or missing steps
- Open PRs with improvements or corrections
- Share tips that would help newcomers
These guides are written for complete beginners - someone who has never used the tool before. Each guide should walk through everything from installation to first voice conversation.
- Choose your tool from the list above
- Follow the integration guide specific to your tool
- Configure Voice Mode with your OpenAI API key
- Start talking to your AI assistant!
All integrations require:
- Python 3.10 or higher
- uv package manager
- OpenAI API key (or compatible service)
- System audio dependencies (see tool-specific guides)
To add a new integration guide:
- Copy the TEMPLATE.md file
- Create a new directory for your tool (e.g.,
new-tool/) - Save the template as
README.mdin that directory - Fill in all the placeholders with tool-specific information
- Add screenshots or example configs if helpful
- Update this README.md to include the new integration
Voice Mode adds these capabilities to your development tools:
- ποΈ Natural voice conversations - Speak your questions and hear responses
- π Real-time interaction - Code changes happen as you talk
- π Privacy options - Use local STT/TTS services for offline operation
- π Room-based collaboration - Share voice sessions via LiveKit
- π Performance metrics - Track conversation statistics
- π Check the main documentation
- π§ Review configuration options
- π¬ Join our Discord community
- π See troubleshooting guides
- π¨ Report issues or contribute improvements