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

41–50 of 229 posts

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

#41

Post by javier123454321 »

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:…

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.

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

#42

Post by KolmogorovComp »

bityard wrote: post #36
davely wrote: post #28

Earlier quoted context omitted.

I've been using GLM 4.7 alongside Opus 4.5 and I can't believe how bad it is. Seriously. I spent 20 minutes yesterday trying to get GLM 4.7 to understand that a simple modal on a web page (vanilla JS and HTML!) wasn't displaying when a certain button was clicked. I hooked it up to Chrome MCP in Open Code as well. It constantly told me that it fixed the problem. In frustration, I opened Claude Code and just typed "Why…

I've used a bunch of the SOTA models (via my work's Windsurf subscription) for HTML/CSS/JS stuff over the past few months. Mind you, I am not a web developer, these are just internal and personal projects. My experience is that all of the models seem to do a decent job of writing a whole application from scratch, up to a certain point of complexity. But as soon as you ask them for non-trivial modifications and bugfix…

Exactly the same feedback

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

#43

Post by cmrdporcupine »

vlovich123 wrote: post #20
throwaw12 wrote: post #12

Earlier quoted context omitted.

Dario said not nice words about China and open models in general: https://www.bloomberg.com/news/articles/2026-01-20/anthropic...

I think the least politically divisive issue within the US is concern about China’s growth as it directly threatens the US’s ability to set the world’s agenda. It may be politically divisive if you are aligned with Chinese interests but I don’t see anything politically divisive for a US audience. I expect Chinese CEOs speak in similar terms to a Chinese audience in terms of making sure they’re decoupled from the now…

"... for a US audience"

And that's the rub.

Many of us are not.

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

#44

Post by Balinares »

TylerLives wrote: post #11
throwaw12 wrote: post #6

Qwen team, please please please, release something to outperform and surpass the coding abilities of Opus 4.5. Although I like the model, I don't like the leadership of that company and how close it is, how divisive they're in terms of politics.

>how divisive they're in terms of politics What do you mean by this?

They're supporters of the Trump administration's military, a view which is not universally lauded.

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

#45

Post by cmrdporcupine »

mhuffman wrote: post #30
WarmWash wrote: post #19

Earlier quoted context omitted.

The Chinese labs distill the SOTA models to boost the performance of theirs. They are a trailer hooked up (with a 3-6 month long chain) to the trucks pushing the technology forwards. I've yet to see a trailer overtake it's truck. China would need an architectural breakthrough to leap American labs given the huge compute disparity.

I would be happy with an openweight 3 month old Claude

DeepSeek 3.2 is frankly fairly close to that. GLM 4.7 as well. They're basically around Sonnet 4 level.

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

#46

Post by bityard »

albertwang wrote: post #2

great news, this looks great! is it just me, or do most of the english audio samples sound like anime voices?

Well, if you look at the prompts, they are basically told to sound like that.

And if you ask me, I think these models were trained on tween fiction podcasts. (My kids listen to a lot of these and dramatic over-acting seems to be the industry standard.)

Also, their middle-aged adult with an "American English" accent sounds like any American I've ever met. More like a bad Sean Connery impersonator.

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

#47

Post by pseudony »

throwaw12 wrote: post #6

Qwen team, please please please, release something to outperform and surpass the coding abilities of Opus 4.5. Although I like the model, I don't like the leadership of that company and how close it is, how divisive they're in terms of politics.

Same issue (I am Danish).

Have you tested alternatives? I grabbed Open Code and a Minimax m2.1 subscription, even just the 10usd/mo one to test with.

Result? We designed a spec for a slight variation of a tool for which I wrote a spec with Claude - same problem (process supervisor tool), from scratch.

Honestly, it worked great, I have played a little further with generating code (this time golang), again, I am happy.

Beyond that, Glm4.7 should also be great.

See https://dev.to/kilocode/open-weight-models-are-getting-serio...

It is a recent case story of vibing a smaller tool with kilo code, comparing output from minimax m2.1 and Glm4.7

Honestly, just give it a whirl - no need to send money to companies/nations your disagree with with.

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

#48

Post by rdtsc »

javier123454321 wrote: post #41
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:…

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.

That was my thought too. You’d have “loved ones” calling with their faces and voices asking for money in some emergency. But you’d also have plausible deniability as anything digital can be brushed off as “that’s not evidence, it could be AI generated”.

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

#50

Post by overfeed »

WarmWash wrote: post #19
throwaw12 wrote: post #6

Qwen team, please please please, release something to outperform and surpass the coding abilities of Opus 4.5. Although I like the model, I don't like the leadership of that company and how close it is, how divisive they're in terms of politics.

The Chinese labs distill the SOTA models to boost the performance of theirs. They are a trailer hooked up (with a 3-6 month long chain) to the trucks pushing the technology forwards. I've yet to see a trailer overtake it's truck. China would need an architectural breakthrough to leap American labs given the huge compute disparity.

Care to explain how the volume of AI research papers authored by Chinese researchers[1] has exceeded US-published ones? Time-traveling plagiarism perhaps, since you believe the US is destined to lead always.

1. Chinese researcher in China, to be more specific.

Post reply on HN