Skip to content

docs: GitHub Pages as the official site URL #63

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Alex-Wengg merged 1 commit into from
Aug 25, 2026
Merged

docs: GitHub Pages as the official site URL #63

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 8 additions & 7 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,13 +11,14 @@ the browser sibling of the Swift/CoreML
tab** (Parakeet TDT 0.6B v3, multilingual; verified across three runs on the
1-hour benchmark, Chrome/macOS/WebGPU; ~199× under the node harness).

**Live:** https://fluidaudio-web.hanweng9.workers.dev — one page per function:
[speech to text](https://fluidaudio-web.hanweng9.workers.dev) at the root
(one engine at a time), [`/tts`](https://fluidaudio-web.hanweng9.workers.dev/tts.html)
synthesis, [`/analyze`](https://fluidaudio-web.hanweng9.workers.dev/analyze.html)
VAD + diarization, [`/live`](https://fluidaudio-web.hanweng9.workers.dev/live.html)
captions, and [`/music`](https://fluidaudio-web.hanweng9.workers.dev/music.html)
generation.
**Live:** https://fluidinference.github.io/fluidaudio-web/ — one page per
function: [speech to text](https://fluidinference.github.io/fluidaudio-web/)
at the root, [text to speech](https://fluidinference.github.io/fluidaudio-web/tts.html),
[music generation + stem splitting](https://fluidinference.github.io/fluidaudio-web/music.html),
[other audio models](https://fluidinference.github.io/fluidaudio-web/analyze.html)
(VAD, diarization, stems), and [live captions](https://fluidinference.github.io/fluidaudio-web/live.html).
Mirror: https://fluidaudio-web.hanweng9.workers.dev. Both deploy automatically
from every commit to `main`.

> **Why hand-written kernels?** The first iteration of this repo ran the same
> models through onnxruntime-web. Rewriting the hot paths as raw WGSL + Rust
Expand Down
Loading