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

171–180 of 229 posts

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

#171

Post by dur-randir »

magicalhippo wrote: post #138
thedangler wrote: post #104

Earlier quoted context omitted.

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…

https://github.com/sdbds/flash-attention-for-windows/release... - FA2 binaries for you

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

#172

Post by cwillu »

aprilthird2021 wrote: post #154
rdtsc wrote: post #48

Earlier quoted context omitted.

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”.

> as anything digital can be brushed off as “that’s not evidence, it could be AI generated”. This won't change anything about Western style courts which have always required an unbroken chain of custody of evidence for evidence to be admissable in court

Court account for a vanishingly small proportion of most people's lives.

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

#173

Post by _kb »

pseudosavant wrote: post #73
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:…

Remarkable tech that is now accessible to almost anyone. My cloned voice sounded exactly like me. The uses for this will be from good to bad and everywhere in-between. A deceased grandmother reading "Good Night Moon" to grandkids, scamming people, the ability to create podcasts with your own voices from just prompts.

It's a good thing governments (https://www.ato.gov.au/online-services/voice-authentication) and banks (https://www.anz.com.au/security/how-we-protect-you/voice-id/) haven't gone all in on using voice as an authentication mechanism.

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

#174

Post by _kb »

simonw wrote: post #115
fridder wrote: post #107

Earlier quoted context omitted.

Admittedly I have not dove into it much but, I wonder if we might finally have a usecase for NFTs and web3? We need some sort of way to denote items are persion generated not AI. Would certainly be easier than trying to determine if something is AI generated

How would NFTs/web3 help differentiate between something created by a human and something that a human created with AI and then tagged with their signature using those tools?

In a live conversation context you can mention the term NFTs/web3 and if the far end is human they'll wince a little.

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

#175

Post by redwall_hp »

echelon wrote: post #71
DANmode wrote: post #69

Earlier quoted context omitted.

> People that couldn't sing will make music. I was with you, until But, yeah. Life will go on.

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…

We've had Yamaha Vocaloid for over two decades now, and Synthesizer V is probably coming up on a decade too now. They're like any other synth: MIDI (plus phonemes) in, sound out. It's a tool of musical expression, like any other instrument.

Hatsune Miku (Fujita Saki) is arguably the most prolific singer in the world, if you consider every Vocaloid user and the millions of songs that have come out of it.

So I don't think there's any uncharted territory...we still have singers, and sampled VST instruments didn't stop instrumentalists from existing; if anything, most of these newcomer generative AI tools are far less flexible or creatively useful than the vast array of synthesis tools musicians already use.

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

#176

Post by anotherevan »

Is there any way to take a cloned voice model and plug into Android TTS and/or Windows?

I have a friend with a paralysed larynx who is often using his phone or a small laptop to type in order to communicate. I know he would love it if it was possible to take old recordings of him speaking and use that to give him back "his" voice, at least in some small measure.

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

#177

Post by redwall_hp »

volkercraig wrote: post #103
javier123454321 wrote: post #86

Earlier quoted context omitted.

Yes, the flipside of this is that we're eroding the last bit of ability for people to make a living through their art. We are capturing the market for people to live off of making illustrations, to making background music, jingles, promotional videos, photographs, graphic design, and funnelling those earnings to NVIDIA. The question I keep asking is whether we care to value as a society for people to make a living th…

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…

Tin Pan Alley is the historical industry from before recording: composers sold sheet music and piano rolls to publishers, who sold them to working musicians. The ASCAP/BMI mafia would shake down venues and make sure they were paying licensing fees.

Recorded music and radio obviously reduced the demand for performers, which reduced demand for sheets.

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

#178

Post by cookiengineer »

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…

> We're going to be okay.

> And there will be incredible benefits that come out of this.

Your username is echelon.

I just wanted to point that out.

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

#179

Post by sumedh »

dsrtslnd23 wrote: post #130
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

Are you using an API proxy to route GLM into the Claude Code CLI? Or do you mean side-by-side usage? Not sure if custom endpoints are supported natively yet.

This works: $ZAI_ANTHROPIC_BASE_URL=xxx $ZAI_ANTHROPIC_AUTH_TOKEN=xxx

  alias "claude-zai"="ANTHROPIC_BASE_URL=$ZAI_ANTHROPIC_BASE_URL ANTHROPIC_AUTH_TOKEN=$ZAI_ANTHROPIC_AUTH_TOKEN claude"
Then you can run `claude`, hit your limit, exit the session and `claude-zai -c` to continue (with context reset, of course).

Someone gave me that command a while back.

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

#180

Post by parentheses »

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:…

I got some errors trying to run this on my MBP. Claude was able to one-shot a fix.

``` Loaded speech tokenizer from ~/.cache/huggingface/hub/models--Qwen--Qwen3-TTS-12Hz-1.7B-VoiceDesign/snapshots/0e711a1c0aa5aad30654426 e0d11f67716c1211e/speech_tokenizer Fetching 11 files: 0%| | 0/11 [00:00https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instr.... This will lead to incorrect tokenization. You should set the `fix_mistral_regex=True` flag when loading this tokenizer to fix this issue. ```

Post reply on HN