@jaybrunet@podcastindex.social
Post #2382476
2026-04-05 05:12 UTC
A little background -- I originally tried Voicebox https://voicebox.sh/ and hated it.
But the great thing about it, you get an opportunity to try several of the top open source TTS models. After a few tests, it was clear Qwen3 sounded the best.
After that, I dug into Github for every reference to Qwen3 TTS and Gabriele's project was the winning implementation.
Replies (1)
-
@jaybrunet@podcastindex.social 2026-04-05 05:16
That said, it's possible Voicebox's implementation of Chatterbox Turbo was botched somehow. The demos I saw on YouTube sounded much better. Maybe eventually I'll dig deeper into a comparison between the official Qwen3 & Chatterbox Turbo voice outputs. If you have an opinion one way or the other, I'm all ears ;-)