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

141–150 of 229 posts

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

#141

Post by mikenew »

bigyabai wrote: post #56
nunodonato wrote: post #53

Earlier quoted context omitted.

I've been using GLM 4.7 with Claude Code. best of both worlds. Canceled my Anthropic subscription due to the US politics as well. Already started my "withdrawal" in Jan 2025, Anthropic was one of the few that was left

I'm in the same boat. Sonnet was overkill for me, and GLM is cheap and smart enough to spit out boilerplate and FFMPEG commands whenever it's asked. $20/month is a bit of an insane ask when the most valuable thing Anthropic makes is the free Claude Code CLI.

I've recently switched to OpenCode and found it to be far better. Plus GML 4.7 is free at the moment, so for now it's a great no-cost setup.

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

#142

Post by harshreality »

u8080 wrote: post #117
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.

https://www.youtube.com/watch?v=diboERFAjkE pretty much this

That's a reupload of Cybergem's video. https://www.youtube.com/watch?v=-gGLvg0n-uY

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

#143

Post by indigodaddy »

quinncom wrote: post #109
indigodaddy wrote: post #8

How does the cloning compare to pocket TTS?

Pocket TTS is much smaller: 100M parameters versus 600–1800M.

Ah right so I guess qwen3-tts isn't going to work for cpu-only like pocket TTS can(?)

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

#144

Post by indigodaddy »

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

Simon how do you think this would perform on CPU only? Lets say threadripper with 20G ram. (Voice cloning in particular)

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

#145

Post by aussieguy1234 »

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.

I could say the same about grok (although given there are better models for my use cases I don't use it). What part of divisive politics are you talking about here?

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

#147

Post by numpad0 »

jacquesm wrote: post #59
overfeed wrote: post #50

Earlier quoted context omitted.

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.

Volume is easy: they have far more people, it is quality that counts.

Yeah, and if anything it's US defying massive disadvantage in headcount is what is odd, not the other way around.

  1: https://en.wikipedia.org/wiki/List_of_countries_and_dependencies_by_population

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

#148

Post by patrickdavey »

javier123454321 wrote: post #106
volkercraig wrote: post #103

Earlier quoted context omitted.

This feels like one of those tropes that keeps showing up whenever new tech comes out. At the advent of recorded music, im sure buskers and performers were complaing that live music is dead forever. Stage actors were probably complaining that film killed plays. Heck, I bet someome even complained that video itself killed the radio star. Yet here we are, hundreds of years later, live music is still desirable, plays st…

umm, I don't know if you've seen the current state of trying to make a living with music but It's widely accepted as dire. Touring is a loss leader, putting out music for free doesn't pay, stream counts payouts are abysmally low. No one buys songs. All that is before the fact that streaming services are stuffing playlists with AI generated music to further reduce the payouts to artists. > Yet here we are, hundreds of…

But this is different? Wholesale copying of copyrighted works and packaging it up and allowing it to be generated. It's not remotely reasonable

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

#149

Post by wahnfrieden »

numpad0 wrote: post #146
wahnfrieden wrote: post #25

How is it for Japanese?

The demo page only has three samples for Japanese, and one of it pronounces taskete as itsukete (???), so...

Thanks. All modern TTS for Japanese are useless failures.

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

#150

Post by simonw »

indigodaddy wrote: post #144
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

Simon how do you think this would perform on CPU only? Lets say threadripper with 20G ram. (Voice cloning in particular)

No idea at all, but my guess is it would work but be a bit slow.

You'd need to use a different build of the model though, I don't think MLX has a CPU implementation.

Post reply on HN