Real-Time-Voice-Cloning
glados-voice-assistant
Our great sponsors
| Real-Time-Voice-Cloning | glados-voice-assistant | |
|---|---|---|
| 57 | 6 | |
| 34,802 | 170 | |
| - | - | |
| 5.3 | 8.5 | |
| 3 days ago | about 1 month ago | |
| Python | C | |
| GNU General Public License v3.0 or later | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Real-Time-Voice-Cloning
- Emil Sutovsky says Karyakin made a deep-fake prank call to him pretending to be the Ukrainian Sports Minister
-
"...An elegant tool for a more civilized age.”
Starting with github:Real-Time-Voice-Cloning, using just the Daniels speech from the short clip here I had it generate this clearly flawed generated sample which still has some of the timbre of his voice. I'm guessing a larger sample may work better, given the success that many other voices have had. If we fed in the full corpus of Knight Rider, St. Elsewhere, etc. there's certainly plenty of content available. Probably best to skip 1776, though.
-
Can Ai Clone anyones voice with just a few recordings yet?
I was doing some text-to-speech research and came upon this today: https://github.com/CorentinJ/Real-Time-Voice-Cloning
-
RealTalk: We Recreated Joe Rogan's Voice Using Artificial Intelligence
Here's a great open source project you could follow yourself and try at home..
-
I'm really starting to enjoy this. My Vehicle Damage System causes so much destruction.
oh for sure, there have already been commercial games released exploring such technology.. and you can go clone your voice right now on github w/ mit licensed tech if you want. nvm, today's commercial offerings can even add emotion convincingly to their synthesized speech.
- 我佛，打游戏碰到个东北b，我拉他进语音想骂他来着，好家伙这逼样的一秒十骂，带着口音的东北话给我骂晕过去了，在他面前我完全没有战斗力。。。
- How to clone someone’s voice with AI?
-
I synthesized Eddy's voice
Hello! Using this amazing software I took 7 seconds of Eddy's voice (from their lofi video and from their bubble tea video consecutively) and got my 2 favorite results: https://youtu.be/XisqpQmbf1Y. Which is better? If you want them to say anything else you can comment and ill pick my favorites.
- Jack Rhysider Voice Cloning
-
Clone a voice in 5 seconds to generate arbitrary speech in real-time
I'm the author of FakeYou.com, so I have a little experience in this area.
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.
If you're picking this up for a project, HiFi-Gan is pretty much the best vocoder right now. Tacotron still produces great results.
glados-voice-assistant
-
Make your own custom wakeword and other FOSS voice assistant solutions
GLaDOS Voice Assistant
-
I finished the Text-To-Speech module of my GLaDOS Voice Assistant. No better way to celetrate it, than make her read the Bee Movie script 🍿👀
For those asking you should check his YouTube channel for more info, a link to the project is: https://github.com/Nerdaxic/GLaDOS-Voice-Assistant
Give the GitHub repo a follow to stay updated as the project progresses! It works, but there is still lot to do to get this to be commercial quality software instead of a bodge :D
- GLaDOS Teaches You How To Synthesize Dimethyltryptamine (ForwardTacotron + HiFiGAN)
- Nerdaxic / GLaDOS-Voice-Assistant
-
Is GLaDOS supposed to be glossy white or matt white? I'm almost finished with my voice assistant project, but can't decide on the surface finish.
Find it here: https://github.com/nerdaxic/GLaDOS-Voice-Assistant
What are some alternatives?
TTS - 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
NeMo - NeMo: a toolkit for conversational AI
DeepFaceLab - DeepFaceLab is the leading software for creating deepfakes.
TTS - :robot: :speech_balloon: Deep learning for Text to Speech (Discussion forum: https://discourse.mozilla.org/c/tts)
gpt-2 - Code for the paper "Language Models are Unsupervised Multitask Learners"
RHVoice - a free and open source speech synthesizer for Russian and other languages
MockingBird - 🚀AI拟声: 5秒内克隆您的声音并生成任意语音内容 Clone a voice in 5 seconds to generate arbitrary speech in real-time
Conv-TasNet - A PyTorch implementation of Conv-TasNet described in "TasNet: Surpassing Ideal Time-Frequency Masking for Speech Separation" with Permutation Invariant Training (PIT).
tacotron2 - Tacotron 2 - PyTorch implementation with faster-than-realtime inference
silero-models - Silero Models: pre-trained speech-to-text, text-to-speech and text-enhancement models made embarrassingly simple
FastSpeech2 - An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"
Real-Time-Voice-Cloning - Clone a voice in 5 seconds to generate arbitrary speech in real-time