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

#1

Post by Palmik » Thu, Jan 22, 2026, 1:51 PM UTC

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

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

#2

Post by albertwang » Thu, Jan 22, 2026, 3:30 PM UTC

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

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

#3

Post by devttyeu » Thu, Jan 22, 2026, 3:47 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?

Also like some popular youtubers and popular speakers.

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

#4

Post by rapind » Thu, Jan 22, 2026, 3:57 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?

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

100% I was thinking the same thing.

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

#5

Post by lostmsu » Thu, Jan 22, 2026, 3:58 PM UTC

I still don't know anyone who managed Qwen3-Omni to work properly on a local machine.

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

#6

Post by throwaw12 » Thu, Jan 22, 2026, 4:10 PM UTC

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.

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

#7

Post by thehamkercat » Thu, Jan 22, 2026, 4:11 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?

even the Japanese audio samples sound like anime

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

#8

Post by indigodaddy » Thu, Jan 22, 2026, 4:12 PM UTC

How does the cloning compare to pocket TTS?

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

#9

Post by amrrs » Thu, Jan 22, 2026, 4:14 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.

Have you tried the new GLM 4.7?

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

#10

Post by sampton » Thu, Jan 22, 2026, 4:18 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.

Every time Dario opens his mouth it's something weird.