Skip to content

lucasdalrymple/Hack-Western-VS-Code

Repository files navigation

Speech-to-Text with Eleven Labs

A web application that uses Eleven Labs API for speech-to-text conversion with a simple activation button interface.

Features

  • 🎤 One-click audio recording
  • 🔊 Real-time speech-to-text conversion
  • 🎨 Modern, responsive UI
  • 🔒 Secure API key handling

Setup

  1. Install dependencies:

    npm install
  2. Configure API Keys:

  3. Start the server:

    npm start
  4. Open your browser:

    • Navigate to http://localhost:3000
    • Click the "Record" button to start recording
    • Click "Stop" when finished
    • Your transcript will appear below

Usage

  1. Connect Google Calendar (optional but recommended):

    • Click the "Connect Google Calendar" button
    • Sign in with your Google account
    • Grant calendar permissions
  2. Record and Add to Calendar:

    • Click the Record button to start recording
    • Speak your calendar request (e.g., "Add a meeting tomorrow at 2pm")
    • Click Stop when you're done
    • Your transcript will appear and automatically be processed
    • If calendar intent is detected, the event will be added to your Google Calendar

Requirements

  • Node.js (v14 or higher)
  • Modern web browser with microphone access
  • Eleven Labs API key
  • Gemini API key (for calendar processing)
  • Google OAuth credentials (for calendar integration)

Notes

  • The application requires microphone permissions in your browser
  • Audio is recorded in WebM format and sent to Eleven Labs for transcription
  • Make sure your Eleven Labs account has speech-to-text access enabled
  • Google Calendar integration requires OAuth 2.0 setup in Google Cloud Console
  • Calendar events are automatically created when you speak calendar-related commands

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors