Skip to content

A web application for realtime voice conversations with OpenAI's GPT-4o and GPT-4o mini models using WebRTC.

License

Notifications You must be signed in to change notification settings

Mehdisharbaf/openai-realtime-voice

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 

Repository files navigation

OpenAI Realtime Voice

A web application that allows users to interact with OpenAI's realtime voice models using WebRTC. Users can choose between GPT-4o and GPT-4o mini models for realtime voice conversations.

Features

  • Realtime voice conversations with OpenAI's language models
  • Support for both GPT-4o and GPT-4o mini models
  • Voice selection for different audio outputs
  • Dark/light theme toggle
  • Conversation history display
  • Connection status indicators
  • Persistent user preferences

Getting Started

Prerequisites

  • An OpenAI API key with access to GPT-4o models
  • A modern web browser that supports WebRTC

Usage

  1. Visit the live demo or host the application yourself
  2. Enter your OpenAI API key
  3. Select your preferred model (GPT-4o or GPT-4o mini)
  4. Choose a voice for the AI responses
  5. Click "Start Conversation" to begin
  6. Speak naturally to interact with the AI in realtime
  7. Click "Stop" when you're finished

Privacy

This application runs entirely in your browser. Your OpenAI API key and conversations are not stored on any server and are only used to communicate with OpenAI's API.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgments

  • OpenAI for providing the realtime voice API
  • WebRTC for enabling browser-based audio streaming

About

A web application for realtime voice conversations with OpenAI's GPT-4o and GPT-4o mini models using WebRTC.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • HTML 100.0%