Post #2382475

2026-04-05 05:07 UTC

To expand on that, I have not tried the official Qwen3 TTS UI yet, partly bc @adam@podcastindex.social said it was a pain to install, so I have nothing to compare with. I suspect maybe Gabriele is doing something wrong with the 1.7b model. It does work, but like I said, the "instruct" option doesn't make any meaningful difference, even if you change the temperature. Is it just me? Try for yourself. Regardless, I'm really impressed with the speed & ease of use of the 0.6b model, especially if you prefer a CLI.

Replies (1)

@jaybrunet@podcastindex.social 2026-04-05 05:12

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.

Open ##2382476