Hi everyone! I’m excited to share an early preview of a project I’ve been working on called Voqal Browser. It’s a voice-controlled web browser built on OpenAI’s Realtime API. It’s tailored to boost productivity by enabling natural speech voice control and is fully programmable, allowing you to customize and fine-tune it to fit your specific needs.
What sets Voqal Browser apart is its programmability and ability to edit its prompt and tools in real-time, as demonstrated below.
If you’re into enhancing your workflow with AI-driven tools, check it out and let me know your thoughts!
For an example of Voqal Browser’s programmability, I wanted to show how I currently use it as a job application auto-filler. The video below shows how it behaves when it first interacts with you. As you keep using it, it will auto-fill in more and more based on what you’ve said in the past.
This is not how you have to use Voqal Browser. The prompt and tools are fully customizable. The best part is that it doesn’t rely on screenshots like Anthropic’s “computer use,” meaning it can operate faster, cheaper, and smarter.