This project provides a browser extension for Google Chrome and Microsoft Edge that enables voice interaction with ChatGPT. It allows users to speak their prompts and listen to ChatGPT's responses, offering a more natural and accessible way to engage with the AI, particularly beneficial for the elderly and individuals with disabilities.

How It Works

The extension integrates with the ChatGPT web interface, utilizing browser-based speech recognition for input and text-to-speech (TTS) for output. It supports various TTS engines, including ElevenLabs API for custom voice generation and Azure Text-to-Speech, allowing users to select preferred voices, languages, and speech rates. The interaction is managed through an in-page widget with controls for starting/stopping, skipping messages, and accessing settings.

Quick Start & Requirements

• Installation: Available via the Chrome Web Store and Edge Add-ons store. Manual installation is possible by downloading a ZIP file from the repository and loading it in developer mode.
• Prerequisites: Google Chrome or Microsoft Edge (desktop versions only).
• Resources: Requires microphone access. ElevenLabs integration may incur API costs.
• Documentation: Chrome Web Store, Edge Web Store, Demo Video

Highlighted Details

• Supports ElevenLabs API for custom and high-quality text-to-speech voices.
• Includes Azure Text-to-Speech as an alternative TTS engine.
• Offers vocal commands for pausing and resuming interaction.
• Features an option to skip code blocks in AI responses.

Maintenance & Community

The project has been discontinued by the original author due to maintenance challenges and the upcoming official desktop applications from OpenAI. Users are encouraged to fork and maintain the project. The last update was on December 3rd, 2023.

Licensing & Compatibility

The project is open-source and appears to be freely usable. The README does not explicitly state a license, but the permissive nature of the code and encouragement for forks suggest a permissive license. Compatibility is limited to Chrome and Edge desktop browsers.

Limitations & Caveats

The extension is discontinued and no longer actively maintained by the original author. Its functionality is dependent on the HTML structure of the ChatGPT website, meaning future OpenAI updates could break compatibility. The author notes that official desktop apps will likely make this extension obsolete.