The AI Voice Browser is a Chrome extension that uses voice recognition and Google's built-in AI to enhance web browsing. Designed with accessibility in mind, it allows users to navigate websites and interact with content entirely through voice commands.
- Integrates with Google's Built in AI to convert the voice text into web commands.
- NAVIGATE TO URL - Browse to any website.
- SEARCH CURRENT PAGE - Finds inputs on current page and performs queries.
- SCROLL - Scrolls up and down the page.
- REFRESH PAGE - Refreshes the page.
- CLICK LINK - Click on any link just by describing the text.
- VIDEO CONTROLS - Stop, play, pause, mute, and unmute a video.
- More commands coming soon
- Open-source project with contributions welcome.
To test the extension locally, follow these steps:
-
Clone the repository:
git clone [email protected]:msabree/ai-voice-browser-extension.git
-
Install dependencies and build the project:
npm install npm run build
-
Load the unpacked extension into Chrome:
- Open Chrome and navigate to
chrome://extensions/
- Enable Developer mode
- Click Load unpacked and select the
dist
folder in your project
- Open Chrome and navigate to
- After loading the extension, visit any website.
- Click the extension icon that appears on the right side of the page.
- Click the START Button to start recording.
- Speak any of the supported commands using natural langauge.
- This AI is EXPERIMENTAL and may require multiple attempts.
We welcome contributions! If you'd like to improve the extension, follow these steps:
- Fork the repository.
- Create a new branch for your changes.
- Submit a pull request with a clear description of your changes.
This project is licensed under the MIT License. See the LICENSE file for more details.
For questions or inquiries, please contact msabree.