v1.0 — Now available on npm

Talk to Cursor

A hands-free voice interface for Cursor AI. Your coding assistant speaks progress updates aloud and listens for voice commands.

Install Now Download Guide
$ npx -y talktocursor
Features

Everything you need for voice-driven coding

🔊

Text-to-Speech

Your AI assistant speaks task progress, completions, and errors aloud so you can follow along without staring at the screen.

🎙

Voice Commands

Dictate your instructions and have them automatically submitted. Works with macOS dictation and Wispr Flow for seamless hands-free control.

🔄

Conversational Loop

Full voice loop with automatic listening after task completion. Speak, code, speak - no keyboard needed.

🎨

Voice Presets

Choose from quick presets: fast, slow, expressive, stable, or dramatic - or fine tune speed, stability, and style yourself.

🛠

Settings UI

Beautiful web interface to configure your API key, choose voices, adjust speech parameters, and manage all features.

⚡

Easy Setup

One npm command to install. Add a few lines to your Cursor config. Paste your ElevenLabs key. You're done.

Installation

Up and running in 3 minutes

1

Add to Cursor

Add the MCP server to your Cursor configuration file at ~/.cursor/mcp.json:

{
  "mcpServers": {
    "tts": {
      "command": "npx",
      "args": ["-y", "talktocursor"]
    }
  }
}
2

Get your ElevenLabs API key

Sign up for a free account at elevenlabs.io and create an API key. The free tier is sufficient for most cases.

3

Configure via Settings UI

Run the settings server and open http://localhost:3847 to paste your API key, pick a voice, and customize additional settings (optional).

# In the talktocursor directory:
npm run settings
4

Restart Cursor and talk

Fully quit and reopen Cursor. Open a chat and type "Say hello using the speak tool" - you should hear your assistant's voice. Then, just enable dictation or a transcription tool to start talking to your code.

5

Install Wispr Flow (recommended)

For the full hands-free conversational loop, install Wispr Flow - a voice-to-text tool that lets you dictate anywhere on macOS. Once installed:

  • 1. Enable Wispr Voice Loop in the settings UI
  • 2. Set the hotkey to match your Wispr Flow dictation shortcut
  • 3. Run npm run auto-submit to start the background listener

Now after each task, your assistant speaks the result, automatically starts Wispr to listen for your next command, and submits it — a fully voice-driven coding loop.

Configurable

Fully customizable to your workflow

Every aspect of TalkToCursor can be configured through the web-based settings UI or directly in the config file. No code changes needed.

  • Choose from any ElevenLabs voice
  • Adjust speed, stability, and expressiveness
  • Toggle auto-listen for voice loops
  • Configure hands-free dictation
  • Set custom hotkeys for Wispr Flow
  • Environment variable overrides supported
// config.json
{
  "voiceId": "Rachel",
  "model": "eleven_flash_v2_5",
  "voiceSettings": {
    "speed": 1.0,
    "stability": 0.5,
    "similarityBoost": 0.75,
    "style": 0.0
  },
  "autoListen": true,
  "autoSubmit": {
    "enabled": true,
    "silenceDelay": 3.0
  }
}

Start talking to your code

Install TalkToCursor in minutes and experience hands-free coding with voice feedback.

Get Started Download Install Guide View on npm