SKI
What is SKI?
SKI is an on-device voice assistant for AI coding agents such as Claude Code, Cursor, Codex, Gemini CLI, Windsurf, and OpenClaw. It lets developers speak naturally to their coding agent, have the agent build and manage code, and hear its responses aloud. Unlike dictation tools, SKI provides a full two-way voice conversation with local speech-to-text, neural voice synthesis, full-duplex interruption, agent status updates, multi-project support, and optional meeting participation. Voice data, transcripts, and local meeting recordings remain on the user's computer and are not uploaded.
How to use SKI?
Download and install SKI on macOS, Windows, or Linux, configure the microphone, voice, and global hotkey, then connect an AI coding agent such as Claude Code, Cursor, Codex, Gemini CLI, or OpenClaw. Press the hotkey and speak your request. SKI converts speech to text locally, sends it to the connected agent through project files, and speaks the agent's response aloud. Users can optionally enable approve-before-send, silent mode, screenshots, local meeting transcription, or AgentCall participation in video meetings.
SKI's Core Features
On-device speech-to-text
Natural neural voice responses running locally
Two-way conversational voice loop for coding agents
Full-duplex echo cancellation and voice interruption
Support for Claude Code, Cursor, Codex, Gemini CLI, Windsurf, and OpenClaw
Multi-project voice routing with separate project voices
Live agent listening and activity status
Approve-before-send transcript review
Global hotkeys and push-to-talk support on Mac
On-demand screenshots for coding requests
Offline local meeting transcription
Microphone and system-audio meeting recording
Speaker-tagged meeting tracks
Markdown and plain-text transcript export
Google Calendar meeting auto-join
Optional AI agent participation in Google Meet, Teams, and Zoom
Agentic meeting mode and silent notetaker mode
Screen sharing, screen viewing, and meeting chat support through AgentCall
Mac notch integration and draggable Windows/Linux floating pill
Local transcript and session management
No cloud audio upload
SKI's Use Cases
Build and modify software by speaking to an AI coding agent
Run tests and hear debugging results without using a keyboard
Create web pages and applications through hands-free voice coding
Ask an agent to inspect files, write code, and execute development commands
Work across multiple repositories with project-specific agent voices
Capture screenshots and send visual context with spoken coding requests
Record and transcribe Zoom, Meet, or Teams meetings locally
Have an AI coding agent participate in meetings or take notes
Review meeting transcripts and export them for documentation
Use private offline voice coding for sensitive projects
FAQ from SKI
What is SKI?
Which coding agents does SKI support?
Is SKI a dictation tool?
Does SKI work offline?
Is my voice uploaded to the cloud?
How much does SKI cost?
Which operating systems are supported?
Can I interrupt the AI agent while it is speaking?
Does SKI transcribe meetings?
Can an AI agent join a video meeting?
What is silent mode?
Can I review a transcript before sending it to my agent?
SKI Reviews (0)
SKI Pricing
SKI
Free for life
Voice coding, on-device speech-to-text, neural voice, meeting transcriber, and local recordings on Mac, Windows, and Linux. Register once; no credit card required.
AgentCall
Paid per minute; free hours included
Optional cloud feature that allows an AI coding agent to join Google Meet, Microsoft Teams, or Zoom as an agentic participant or silent notetaker.
Analytic of SKI
SKI Website Traffic Analysis
SKI Launch embeds
Use website badges to drive support from your community for your Toolify Launch. They're easy to embed on your homepage or footer.
Alternative of SKI
Social Listening