Talk to Cursor

Cross-platform text-to-speech for Cursor and compatible MCP coding hosts, plus an optional hands-free Cursor workflow.

Install Now Download Guide
$ npx -y talktocursor
Features

Everything you need for voice-driven coding

🔊

Text-to-Speech

Your assistant speaks progress, completions, and errors through TalkToCursor Cloud, ElevenLabs, or local Voicebox with the voice of your choice.

🎙

Voice Commands

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

🔄

Smarter Conversational Loop

Task-start speech can play without blocking work. After completion playback, Auto-Listen starts only when enabled.

🎨

Three Speech Options

Use managed Cloud voices with no provider key, customize ElevenLabs, or keep synthesis private on your computer.

🛠

Settings UI

Choose Spoken Response Detail, preview Cloud voices, pause playing media on macOS, and manage hands-free features.

⚡

Smart Turn v3.2

A verified 8.7 MB local model detects when you finish speaking. Optional wake phrases start a turn; saying “send it” submits immediately.

☁

Cloud Profiles & Sync

Save up to 10 paid named profiles per account, assign them by project and coding host, and keep automatic conflict-safe sync with 30-version/90-day history and rollback. Free accounts can pair devices and sync preferences.

📝

Pronunciation Dictionaries

With a paid profile, add up to 50 explicit word or phrase replacements that sync with that profile. Spoken text, generated audio, credentials, and local paths are never synced or stored in Cloud.

📊

Usage Controls

In the Cloud dashboard, set hard per-device billing-period budgets, review up to 12 periods by day or device, export CSV, and get in-app warnings at 80% and 95% of the included allowance, with optional email alerts.

Integrations

One voice layer, more than one coding host

TalkToCursor is one package and one set of voice settings. TTS works across compatible hosts, while Smart Turn, wake phrases, spoken “send it,” automatic submission, and the Background Helper are specifically for Cursor on macOS.

Cursor

The hands-free workflow with spoken updates, custom voices, and dictation.

CURSOR GUIDE →

Claude Code

Complement native voice dictation with spoken agent updates through MCP.

CLAUDE CODE GUIDE →

OpenAI Codex

Add custom or local TTS and spoken milestones alongside native Codex Voice.

CODEX GUIDE →

Google Antigravity

Complement native voice transcription with spoken agent output through MCP.

ANTIGRAVITY GUIDE →
MCP compatibility guide
Installation

Up and running in 3 minutes

Recommended: give this link to your Cursor or AI agent
Install TalkToCursor for my current coding assistant by following:
https://github.com/MindSyncTech/talk-to-cursor/blob/main/INSTALL.md

Configure the MCP and persistent voice-feedback instructions.
Ask before enabling paid Cloud services or installing the macOS Background Helper.
Restarts, account sign-in, purchases, and operating-system permissions may still require you.
1

Add to Cursor

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

{
  "mcpServers": {
    "talktocursor": {
      "command": "npx",
      "args": ["-y", "--prefer-online", "talktocursor@latest"]
    }
  }
}
2

Open the Settings UI

Start the packaged settings server, then open http://localhost:3847 in your browser.

npx -y --prefer-online --package talktocursor@latest talktocursor-settings
3

Choose how TalkToCursor speaks

Select a text-to-speech provider in Settings:

  • TalkToCursor Cloud: Create a free account to pair devices and manually upload or download portable preferences. The optional $15/month plan adds managed Google Cloud TTS, synced profiles, and usage controls - with no provider key stored locally. See full plan details →
  • ElevenLabs: Create an API key and paste it into Settings for full voice controls.
  • Voicebox: Install Voicebox for free local speech, then connect its localhost server.
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

Set up Cursor hands-free (macOS only)

Install Wispr Flow or the free local Handy app. Then:

  • 1. Select your transcription app and configure Smart Turn, wake phrases, and “send it” in Settings
  • 2. Click Install & Start Background Helper
  • 3. Run Check Permissions, then grant Accessibility and Microphone access

The Background Helper runs without a setup terminal. The packaged talktocursor-auto-submit command remains a manual fallback.

Configurable

Fully customizable to your workflow

Choose the speech setup that fits your workflow, then manage voices and hands-free controls from one local settings page.

  • Pair devices and sync preferences with a free Cloud account
  • Bring your own ElevenLabs API key
  • Run Voicebox privately on localhost
  • Manually upload or download speech and hands-free preferences
  • Save up to 10 project/host profiles and review managed TTS analytics
  • Assign profiles with automatic conflict-safe sync (paid)
  • Keep 30 profile versions for 90 days and roll back changes (paid)
  • Customize up to 50 pronunciation replacements in paid profiles
  • Set device budgets, export usage, and allowance alerts in Cloud
  • Choose minimal, brief, or detailed spoken responses
  • Preview Cloud voices before saving
  • Toggle Auto-Listen for voice loops
  • Optionally pause media before speech on macOS
  • Choose Wispr Flow or local Handy dictation
// config.json
{
  "provider": "cloud",
  "cloud": {
    "apiUrl": "https://cloud.talktocursor.com",
    "voiceId": "Kore",
    "model": "gemini-2.5-flash-tts"
  },
  "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 TalkToCursor Cloud