Show HN: Phonon TTS on WebGPU, 44MB, 115x real time, with live word timings
0 comments
- Points2
- Comments0
0 comments
I tried Gradium's Phonon 31M text-to-speech model and was blown away by its quality to size ratio. I needed timings for every word to be able to highlight them, so I wrote a second runtime for it with a different design: the whole generation loop stays on the GPU in WebGPU kernels written specifically for this by Claude Opus 5.5. When initialized, it can start streaming audio in about 3 ms, and it only needs to download 44 MB (<40 MB brotli'd) instead of the official 67 MB, because every large…
Story details from Hacker News ↗ · linked article on github.com.
Show HN: Phonon TTS on WebGPU, 44MB, 115x real time, with live word timings was first seen on Hacker News · Show HN on Nov 5, 2026. Since then it has appeared in 11 checks on 1 different day. Its best position was #22 of 30, reached on Nov 5, 03:30 UTC. It dropped off the list after Nov 5, 08:30 UTC.
Position on Hacker News · Show HN at every check (lower is better).
Best rank per day (UTC).
Platform metric as reported by Hacker News.
Archived daily, weekly and monthly lists that include this entry.
Not at the moment. It was last on the list on Nov 5, 08:30 UTC, after 1 day of trending.
#22 on Hacker News · Show HN, on Nov 5, 03:30 UTC. Trendoday checks this list every 30 minutes.
It was first seen on Nov 5, 2026 and has been on the list on 1 day (11 checks) since.
2 points and 0 comments; submitted by blixt on Nov 4, 2026.