Clone a voice in 5 seconds to generate arbitrary speech in real-time (by CorentinJ)


Basic Real-Time-Voice-Cloning repo stats
11 days ago

CorentinJ/Real-Time-Voice-Cloning is an open source project licensed under GNU General Public License v3.0 or later which is an OSI approved license.

Real-Time-Voice-Cloning Alternatives

Similar projects and alternatives to Real-Time-Voice-Cloning based on common topics and language

  • GitHub repo Real-Time-Voice-Cloning

    Clone a voice in 5 seconds to generate arbitrary speech in real-time (by shawwn)

  • GitHub repo pyenv

    Simple Python version management

  • GitHub repo gpt-2

    Code for the paper "Language Models are Unsupervised Multitask Learners"

  • GitHub repo silero-models

    Silero Models: pre-trained speech-to-text, text-to-speech models and benchmarks made embarrassingly simple

  • GitHub repo mellotron

    Mellotron: a multispeaker voice synthesis model based on Tacotron 2 GST that can make a voice emote and sing without emotive or singing training data

  • GitHub repo TTS

    🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production (by coqui-ai)

  • GitHub repo nni

    An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.

NOTE: The number of mentions on this list indicates mentions on common posts. Hence, a higher number means a better Real-Time-Voice-Cloning alternative or higher similarity.


Posts where Real-Time-Voice-Cloning has been mentioned. We have used some of these posts to build our list of alternatives and similar projects - the last one was on 2021-04-07.
  • Voice Cloning App | 2021-04-07
    I've been looking for something like this for a while. Previous best I could find was but it worked quite poorly on a lot of test data I used. Can you advise on what a minimal training set might be (eg. If we used a phonetic pangram would it be sufficient?). Thanks for the effort anyway - I'll test tomorrow and feedback if I have anything to input!
  • What would you do if you were in this position🤔🤔 | 2021-03-27
    Of course they'd claim that it does advanced voice fingerprinting and will only open the door if it recognizes your voice. Never mind the 0.1% claimed but 1% actual false acceptance rate (meaning 1% of randomly selected people get let in if they say "open door"), never mind that anyone could just record you saying that and replay it, or synthesize a close enough voice based on a 5 second speech sample...
  • Does anyone know any Unity channels that teach programming on pro levels? | 2021-03-26
    - one of my favourite channels is 2 minute papers, which summarizes graphics and current AI research papers in short, mind-blowing videos. These are like 3-6 minutes but link to the paper which will go deep and technical (and then you can start exploring the academic literature on the topic) and these often have links to their code on github (you might be amazed what you can find - e.g. you wanna learn how to clone a human voice w/ 5s of input data? It's here)
  • Tacotron
    Most github stuff seems to be based on one that is here , this one is about the best for testing as it uses short audio files and runs very quickly (try the Colabs they work okay) but I found it limited compared to proper jobs in the previous linked tutorial. the male voice has an Irish twang that comes through in all cases.
  • Ask HN: Why can’t I play Zork by voice, narrated by Stephen Fry? Why? | 2021-03-20
  • What if Eminem wrote "My Name Is" in 2021? | 2021-03-13
    Hours worth of data, ouch. That's gotta be a pain. Is there any reason you used Tacotron2 instead of SV2TTS?
  • I built an Ai McKenna... let me know if you’d like to speak to him.
  • First time using Python. I'm trying to use something from GitHub. I have zero programming experience. ...Help?
  • Where can I find an online resource of voice cloning? is the easiest to use and the best, I would say. It is the commercialized version of but it has a decent free tier.
    You can try
  • Discours de Macron qui vrille | 2021-02-27
  • Help getting into Vocal synthesis
    I've been using this
  • Cost for a voice skin?
    I can do the coding myself. It looks like there are some FOSS projects with pretrained models that only need a few seconds of audio for new voices.
  • What Are The Minimum Specs For Ai Speech Synthesis
    BTW, I'm using the Real Time Voice Cloning Project by CorentinJ not Tacotron by itself:
  • Text to speech offline software, for transcribing medical examinations | 2021-02-13
    You will proably be able to do that with Real Time Voice Cloning. It is free and opensource. Read instruction on how to install it (in best case you have experience with Python, that would make it alot easier for you). As for the Greek Speech data, you can find pretrained models here. If you have some experience with Python, you just need to install some dependencies and also the requirements txt of the master branch in github. Then just start the demo toolbox py with Python.