Qwen3-TTS family is now open sourced: Voice design, clone, and generation • Hacker News Board

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

#11

Post by TylerLives » Thu, Jan 22, 2026, 4:19 PM UTC

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?

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

#12

Post by throwaw12 » Thu, Jan 22, 2026, 4:23 PM UTC

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?

Dario said not nice words about China and open models in general:

https://www.bloomberg.com/news/articles/2026-01-20/anthropic...

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

#13

Post by throwaw12 » Thu, Jan 22, 2026, 4:24 PM UTC

amrrs wrote: post #9

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.

Have you tried the new GLM 4.7?

yes I did, not on par with Opus 4.5.

I use Opus 4.5 for planning, when I reach my usage limits fallback to GLM 4.7 only for implementing the plan, it still struggles, even though I configure GLM 4.7 as both smaller model and heavier model in claude code

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

#14

Post by pixl97 » Thu, Jan 22, 2026, 4:25 PM UTC

devttyeu wrote: post #3

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?

Also like some popular youtubers and popular speakers.

Hmm, wonder where they got their training data from?

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

#15

Post by mortsnort » Thu, Jan 22, 2026, 4:26 PM UTC

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.

They were just waiting for someone in the comments to ask!

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

#16

Post by genewitch » Thu, Jan 22, 2026, 4:29 PM UTC

it isn't often that tehcnology gives me chills, but this did it. I've used "AI" TTS tools since 2018 or so, and i thought the stuff from two years ago was about the best we were going to get. I don't know the size of these, i scrolled to the samples. I am going to get the models set up somewhere and test them out.

Now, maybe the results were cherrypicked. i know everyone else who has released one of these cherrypicks which to publish. However, this is the first time i've considered it plausible to use AI TTS to remaster old radioplays and the like, where a section of audio is unintelligible but can be deduced from context, like a tape glitch where someone says "HEY [...]LAR!" and it's an episode of Yours Truly, Johnny Dollar...

I have dozens of hours of audio of like Bob Bailey and people of that era.

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

#17

Post by htrp » Thu, Jan 22, 2026, 4:31 PM UTC

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?

subbed audio training data (much better than cc data) is better

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

#18

Post by thedangler » Thu, Jan 22, 2026, 4:44 PM UTC

Kind of a noob, how would I implement this locally? How do I pass it audio to process. I'm assuming its in the API spec?

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

#19

Post by WarmWash » Thu, Jan 22, 2026, 4:45 PM UTC

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.

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

#20

Post by vlovich123 » Thu, Jan 22, 2026, 4:48 PM UTC

throwaw12 wrote: post #12

TylerLives wrote: post #11

Earlier quoted context omitted.

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

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 unstable US political machine.