Qwen3-TTS

“I found Qwen ASR and QwenTTS to be quite good, and not too large.”

“Qwen3 TTS is a very good model esp. if you take some effort to craft a voice file”

“I was able to make a robo-me that sounds absurdly good, family was shocked”

“it switched voices half way through a 33 second clip”

“dirt cheap at $5 per 1M characters, still faster than industry avg at 200 ms TTFA”

“you can spin up a machine on runpod or modal to quickly test it out”

“we open source the implementation and benchmark, as well as a breakdown of how it was done”

“I use mlx-audio almost daily with mlx-community/Qwen3-TTS-12Hz-1.7B-Base-bf16 (for voice cloning).”

“Just tried it and it works really really well, thank you for the pointer.”

“It runs locally and I can run it as many times as I want.”

“Qwen only has one pitch accent for pure hiragana words”

“from time to time it will mix with some Mandarin in between, making it unusable”

“Qwen 3 TTS is good for voice cloning but requires GPU of some sort.”

“Qwen3-TTS is a genuinely good open model”

“it was mind blowingly good, you can even provide directions for the overall tone etc.”

“qwen 3 tts was also great but its unisable as any real time agentic voice as its too slow”

“This is the best one I have seen so far.”

“The current code doesn't appear very optimized. Running on CPU-only it only uses four threads for example”

“Demo ran fine, if very slowly, with CPU-only”

“It flat didn't work for me on mps. CUDA only until someone patches it.”

“It has great voice cloning capabilities and creates rich speech with emotions with low latency.”

“It definitely kind of sounds like me, but I like it much better than listening to my real voice.”

“one of it pronounces taskete as itsukete”

“Given how easy voice cloning is with this thing I chickened out of sharing the training audio I recorded!”

“I got this running on macOS using mlx-audio thanks to Prince Canuma”

“Some of the demos arguably sounded way better than a lot of indie voice-acting.”

“Many voices clone better than 11labs, while admitedly lower bitrate”

“one of their examples (the final Age Control example) is prompted to have American English as an accent, but sounds like an Australian”

“it's a miracle and a bit ironic that the Chinese would be the ones to release a plethora of capable open source models”

“There are some samples. If you have GPU you might want to fork and improve this, but otherwise slow, but usable on CPU as well.”

“The normal speech voices are fine (lower than the anime ones on the page.) i agree that the first few are very infantile.”

“It’s uncanny good. I prefer it to pocket”

“this one is certainly one of the better ones in terms of voice cloning quality I've heard”

“The 0.6B would inject some of that into the generated audio”

“I'm elated that these tools are going to enable me to do more with a smaller budget.”

“Unfortunately each snippet varies drastically in quality”

“If you want to try out the voice cloning yourself you can do that”

“The real value I see is being able to clone a voice and change timbre and characteristics of the voice”

“it isn't often that tehcnology gives me chills, but this did it.”

“do most of the english audio samples sound like anime voices?”