Real-Time-Voice-Cloning

It's not on the same level in terms of emotion, but I believe the research https://github.com/CorentinJ/Real-Time-Voice-Cloning was based on is mostly oriented around Chinese first (and then English). It seems to work well enough if you and the voice you're cloning speak the same language though I haven't tested it much.

every single voice cloning project I'm sure you could have used google https://elevenlabs.io/app/voice-lab https://app.resemble.ai/users/sign_in https://github.com/neonbjb/tortoise-tts https://coqui.ai/blog/tts/open_xtts it was even possible 5 years ago https://github.com/CorentinJ/Real-Time-Voice-Cloning

Clone a voice in 5 seconds to generate arbitrary speech in real-time Trending on Github

There's this that can differentiate speakers https://github.com/CorentinJ/Real-Time-Voice-Cloning

Man, based on how often Alexa misunderstands me or tries to upsell me on some feature after I get what I want from it, mine is going to sound really pissed off. I also can’t imagine speaking to my Grandma/pa the way I speak to Alexa either, so that’s food for thought. Jests aside, this is already possible with ML and a large enough data set. There’s nothing state of the art to see here, right? Just implementing existing tech at Enterprise scale/telling the masses? For examples, see 15.ai or https://github.com/CorentinJ/Real-Time-Voice-Cloning. There’s another commercialized service similar to the latter example here I saw recently but I can’t recall the name. I wish the article had some more technical details.

https://github.com/CorentinJ/Real-Time-Voice-Cloning this one maybe?

From README: > This repository is forked from Real-Time-Voice-Cloning which only support English. https://github.com/CorentinJ/Real-Time-Voice-Cloning

I'm the author of FakeYou.com, so I have a little experience in this area. (We used to train GlowTTS models ourselves before turning it over to our users, which has had mixed results in terms of quality.) This appears to be a repackaging of RealTimeVoiceCloning [1], albeit with a few additions, such as GSTs. No matter what the repo claims, your results will depend on high quality data. Lots of it, and with ample fine tuning. Demo videos are absolutely cherry picked. If you're picking this up for a project, HiFi-Gan is pretty much the best vocoder right now. Tacotron still produces great results, though there are lots of other interesting model architectures. [1] https://github.com/CorentinJ/Real-Time-Voice-Cloning

Cool article, I do like the extensibility provided via the unix philosophy. Another thing you can do nowadays is use off-the-shelf deep neural networks to do tts eg https://github.com/NVIDIA/tacotron2 https://github.com/mozilla/TTS https://github.com/CorentinJ/Real-Time-Voice-Cloning https://github.com/coqui-ai/TTS They're not all easy to setup however

Having played around with flite a decade ago, and at that time feeling that it was already then nowhere close to the fidelity of other speech synthesis examples. I find it surprising that there still isn't anything better than festival/flite? It sounded then like a clunky robot, and still does today. Surely some of the many research projects have released their work as open source? Work like, say https://arxiv.org/abs/1806.04558 [paper] https://github.com/CorentinJ/Real-Time-Voice-Cloning [repo]

do it : https://github.com/CorentinJ/Real-Time-Voice-Cloning

This reminded me; People seem way too comfortable / in the dark when it comes to voice-cloning, which, with the added data of general speech-patterns, is likely to become a major issue wrt political/legal issues. see: https://github.com/CorentinJ/Real-Time-Voice-Cloning (think it made its rounds here on HN before) Conceptually, even though it currently is a market-strategy where the benefits are as you point out. In the longer term this could be argued as an uncomfortable seat of power to whoever sits on the user-data. (without bringing up too much of that issue here... might be time to generate obfuscation of voice similarly to the obfuscation of google-searching which I've seen on here earlier=)

I've recently seen these two software on HN that maybe of some help: deepfake for voice: https://github.com/CorentinJ/Real-Time-Voice-Cloning Reproducing emotional voices: https://www.sonantic.io/