@jaybrunet@podcastindex.social
Post #1965810
2026-04-05 04:56 UTC
Putting off trying qwen3 TTS?
I recommend this C application -- easy installation, good documentation, very fast on CPU & no Python headaches!
https://github.com/gabriele-mastrapasqua/qwen3-tts/tree/main
I was able to clone my voice easily -- and it's free.
I recommend starting with the 0.6b model for cloning and experiment with different seeds. 1.7b should be better, but for whatever reason, the smaller model sounds better -- either I'm doing something wrong, or there's a problem with his code.
Replies (1)
-
@jaybrunet@podcastindex.social 2026-04-05 05:01
FWIW the default voices are retarded, try the cloning feature. The separate "voice design" model is fun, BUT it won't repeat the same voice twice. If you really like a voice you 'designed' -- I suppose you could clone it, and then it's reusable -- if that makes sense. Also important, the "instruct" feature does not work at all in the 0.6b model. It's supposed to work with the 1.7b model, but I found it doesn't make much difference with my cloned voice...