Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Qwen3-TTS family is now open sourced: Voice design, clone, and generation

qwen.ai

Post reply on HN
Print view View original

131–140 of 229 posts

Re: Qwen3-TTS family is now open sourced: Voice design, clone, and generation

#131

Post by simonw »

I got this running on macOS using mlx-audio thanks to Prince Canuma: https://x.com/Prince_Canuma/status/2014453857019904423

Here's the script I'm using: https://github.com/simonw/tools/blob/main/python/q3_tts.py

You can try it with uv (downloads a 4.5GB model on first run) like this:

  uv run https://tools.simonwillison.net/python/q3_tts.py \
    'I am a pirate, give me your gold!' \
    -i 'gruff voice' -o pirate.wav

Re: Qwen3-TTS family is now open sourced: Voice design, clone, and generation

#132

Post by echelon »

DANmode wrote: post #116
echelon wrote: post #71

Earlier quoted context omitted.

There are plenty of electronic artists who can't sing. Right now they have to hire someone else to do the singing for them, but I'd wager a lot of them would like to own their music end-to-end. I would. I'm a filmmaker. I've done it photons-on-glass production for fifteen years. Meisner trained, have performed every role from cast to crew. I'm elated that these tools are going to enable me to do more with a smaller b…

What happens to lyricless electronica if suddenly every electronic artist has quality vocal-backing? Oh no . Maybe we did frig this up.

More choices for artists is not a bad thing.

Re: Qwen3-TTS family is now open sourced: Voice design, clone, and generation

#133

Post by simonw »

KolmogorovComp wrote: post #126
simonw wrote: post #33

If you want to try out the voice cloning yourself you can do that an this Hugging Face demo: https://huggingface.co/spaces/Qwen/Qwen3-TTS - switch to the "Voice Clone" tab, paste in some example text and use the microphone option to record yourself reading that text - then paste in other text and have it generate a version of that read using your voice. I shared a recording of audio I generated with that here: https:…

Hello, the recording you posted does not tell much about the cloning capability without an example from your real voice.

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

That's not really rational considering the internet is full of examples of my voice that anyone could use though. Here's a recent podcast clip: https://www.youtube.com/watch?v=lVDhQMiAbR8&t=3006s

Re: Qwen3-TTS family is now open sourced: Voice design, clone, and generation

#134

Post by gcr »

simonw wrote: post #131

I got this running on macOS using mlx-audio thanks to Prince Canuma: https://x.com/Prince_Canuma/status/2014453857019904423 Here's the script I'm using: https://github.com/simonw/tools/blob/main/python/q3_tts.py You can try it with uv (downloads a 4.5GB model on first run) like this: uv run https://tools.simonwillison.net/python/q3_tts.py \ 'I am a pirate, give me your gold!' \ -i 'gruff voice' -o pirate.wav

This is wonderful, thank you. Another win for uv!

Re: Qwen3-TTS family is now open sourced: Voice design, clone, and generation

#135

Post by doug713705 »

echelon wrote: post #65
javier123454321 wrote: post #41

Earlier quoted context omitted.

This is terrifying. With this and z-image-turbo, we've crossed a chasm. And a very deep one. We are currently protected by screens, we can, and should assume everything behind a screen is fake unless rigorously (and systematically, i.e. cryptographically) proven otherwise. We're sleepwalking into this, not enough people know about it.

We're going to be okay. There are far more good and interesting use cases for this technology. Games will let users clone their voices and create virtual avatars and heroes. People will have access to creative tools that let them make movies and shows with their likeness. People that couldn't sing will make music. Nothing was more scary than the invention of the nuclear weapon. And we're all still here. Life will go…

> Nothing was more scary than the invention of the nuclear weapon. And we're all still here.

Except that building a nuclear weapon was not available to everyone, certainly not to dumb people whose brain have been feeded with social media content.

Re: Qwen3-TTS family is now open sourced: Voice design, clone, and generation

#136

Post by gcr »

imiric wrote: post #129
mohsen1 wrote: post #76

Earlier quoted context omitted.

With a good harness I am getting similar results with GLM 4.7. I am paying for TWO! max accounts and my agents are running 24/7. I still have a small Claude account to do some code reviews. Opus 4.5 does good reviews but at this point GLM 4.7 usually can do the same code reviews. If cost is an issue (for me it is, I pay out of pocket) go with GLM 4.7

Your GitHub profile is... disturbing. 1,354 commits and 464 pull requests in January so far. Regardless of how productive those numbers may seem, that amount of code being published so quickly is concerning, to say the least. It couldn't have possibly been reviewed by a human or properly tested. If this is the future of software development, society is cooked.

You may not like it but this is what a 10x developer looks like. :-)

Re: Qwen3-TTS family is now open sourced: Voice design, clone, and generation

#137

Post by magicalhippo »

dsrtslnd23 wrote: post #125
magicalhippo wrote: post #74

Earlier quoted context omitted.

The HF demo space was overloaded, but I got the demo working locally easily enough. The voice cloning of the 1.7B model captures the tone of the speaker very well, but I found it failed at reproducing the variation in intonation, so it sounds like a monotonous reading of a boring text. I presume this is due to using the base model, and not the one tuned for more expressiveness. edit: Or more likely, the demo not expo…

Any idea on the VRAM footprint for the 1.7B model? I guess it fits on consumer cards but I am wondering if it works on edge devices.

The demo uses 6GB dedicated VRAM on Windows, but keep in mind that it's without FlashAttention. I expect it would drop a bit if I got that working.

Haven't looked into the demo to see if it could be optimized by moving certain bits to CPU for example.

Re: Qwen3-TTS family is now open sourced: Voice design, clone, and generation

#138

Post by magicalhippo »

thedangler wrote: post #104
magicalhippo wrote: post #74

Earlier quoted context omitted.

The HF demo space was overloaded, but I got the demo working locally easily enough. The voice cloning of the 1.7B model captures the tone of the speaker very well, but I found it failed at reproducing the variation in intonation, so it sounds like a monotonous reading of a boring text. I presume this is due to using the base model, and not the one tuned for more expressiveness. edit: Or more likely, the demo not expo…

How did you do this locally? Tools? Language?

I just followed the Quickstart[1] in the GitHub repo, refreshingly straight forward. Using the pip package worked fine, as did installing the editable version using the git repository. Just install the CUDA version of PyTorch[2] first.

The HF demo is very similar to the GitHub demo, so easy to try out.

  pip install torch torchvision --index-url https://download.pytorch.org/whl/cu128
  pip install qwen3-tts
  qwen-tts-demo Qwen/Qwen3-TTS-12Hz-1.7B-Base --no-flash-attn --ip 127.0.0.1 --port 8000
That's for CUDA 12.8, change PyTorch install accordingly.

Skipped FlashAttention since I'm on Windows and I haven't gotten FlashAttention 2 to work there yet (I found some precompiled FA3 files[3] but Qwen3-TTS isn't FA3 compatible yet).

[1]: https://github.com/QwenLM/Qwen3-TTS?tab=readme-ov-file#quick...

[2]: https://pytorch.org/get-started/locally/

[3]: https://windreamer.github.io/flash-attention3-wheels/

Re: Qwen3-TTS family is now open sourced: Voice design, clone, and generation

#139

Post by TheAceOfHearts »

dsrtslnd23 wrote: post #127
TheAceOfHearts wrote: post #57

Interesting model, I've managed to get the 0.6B param model running on my old 1080 and I can generated 200 character chunks safely without going OOM, so I thought that making an audiobook of the Tao Te Ching would be a good test. Unfortunately each snippet varies drastically in quality: sometimes the speaker is clear and coherent, but other times it bursts out laughing or moaning. In a way it feels a bit like magical…

do you have the RTF for the 1080? I am trying to figure out if the 0.6B model is viable for real-time inference on edge devices.

Yeah, it's not great. I wrote a harness that calculates it as: 3.61s Load Time, 38.78s Gen Time, 18.38s Audio Len, RTF 2.111.

The Tao Te Ching audiobook came in at 62 mins in length and it ran for 102 mins, which gives an RTF of 1.645.

I do get a warning about flash-attn not being installed, which says that it'll slow down inference. I'm not sure if that feature can be supported on the 1080 and I wasn't up for tinkering to try.

Re: Qwen3-TTS family is now open sourced: Voice design, clone, and generation

#140

Post by KolmogorovComp »

simonw wrote: post #133
KolmogorovComp wrote: post #126

Earlier quoted context omitted.

Hello, the recording you posted does not tell much about the cloning capability without an example from your real voice.

Given how easy voice cloning is with this thing I chickened out of sharing the training audio I recorded! That's not really rational considering the internet is full of examples of my voice that anyone could use though. Here's a recent podcast clip: https://www.youtube.com/watch?v=lVDhQMiAbR8&t=3006s

Thanks, so it’s in the [pretty close but still distinguishable] range.
Post reply on HN