All builds

In-browser AI

openvox

Talk to GitHub. Name a profile or repository and it introduces it out loud, then answers spoken questions. Speech, retrieval and the model run in the browser.

servers. Audio never leaves the browser
0
on the built-in 10-question eval, single run
9/10

Type a GitHub username or repository. It introduces it out loud, then answers spoken questions in a natural voice. There is no backend and no API key, and audio never leaves the browser.

What it does

  1. A spoken intro that uses only numbers computed in code, never numbers a model made up.

  2. Voice or text questions, answered from profile facts and READMEs, with the sources shown.

  3. Says plainly when GitHub cannot show something, instead of guessing.

  4. Start talking and it stops. It also waits through thinking pauses.

How it is built

  • The pipeline runs end to end in the tab: voice detection, speech to text, question routing, BM25 retrieval over README sections, a 1.7B model on WebGPU, then streamed speech.
  • Speech recognition runs on WASM and the model on WebGPU, in separate workers, so they do not compete for the GPU.
  • A speech normalizer turns links, commands and acronyms into text that can be spoken.
  • The built-in eval mixes fact lookups with trap questions, and was used to pick the model.

Honest limits

  • Needs a WebGPU browser, such as current Chrome or Edge.
  • About 1 GB of model to download on first load.
  • Public data only, and 60 GitHub requests an hour.