This repository is an implementation of Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis (SV2TTS) with a vocoder that works in real-time. Feel free to check my thesis if you're curious or if you're looking for info I haven't documented. Mostly I would recommend giving a quick look to the figures beyond the introduction.

SV2TTS is a three-stage deep learning framework that allows to create a numerical representation of a voice from a few seconds of audio, and to use it to condition a text-to-speech model trained to generalize to new voices.

Video demonstration (click the picture):

28/01/21: Flask implementation of voice clone toolbox.

11/01/21: Result save support added. (See This Repo)

13/11/19: I'm now working full time and I will not maintain this repo anymore. To anyone who reads this:

• If you just want to clone your voice (and not someone else's): I recommend our free plan on Resemble.AI. Firstly because you will get a better voice quality and less prosody errors, and secondly because it will not require a complex setup like this repo does.
• If this is not your case: proceed with this repository, but be warned: not only is the environment a mess to setup, but you might end up being disappointed by the results. If you're planning to work on a serious project, my strong advice: find another TTS repo. Go here for more info.

20/08/19: I'm working on resemblyzer, an independent package for the voice encoder. You can use your trained encoder models from this repo with it.

06/07/19: Need to run within a docker container on a remote server? See here.

25/06/19: Experimental support for low-memory GPUs (~2gb) added for the synthesizer. Pass --low_mem to demo_cli.py or demo_toolbox.py to enable it. It adds a big overhead, so it's not recommended if you have enough VRAM.

Python 3.6 or 3.7 is needed to run the toolbox.

• Install PyTorch (>=1.0.1).
• Install ffmpeg.
• Run pip install -r requirements.txt to install the remaining necessary packages.
• Also install Flask with pip using command pip install Flask

Download the latest here.

Run the server by following given command.

python server.py

You will see a window as shown below. Some text.

Copy the given url and paste in browser. I recommend you to please use incognito / guest versions of browsers as browsers saves caches and you may hear old audios after uploading and while listening cloned voices. (Work is needed to be done on not saving caches in server.py code).

Browse the audio mp3 or wav file, for which you want to create an utterance. Note: Audios will be overwrited if they have same names. Note: Audios will uploaded in static folder.

Type the text for which you want to create audio..

Click on Upload Button. Example Uploads are shown below

Listen The Difference Between Two Audios Enjoy It. Generated Output is saved in static folder named "output.wav". This file is overwrited with every new experiment. You can add some random numbers or date time to make it unique in file "server.py" at line 113 fpath = "static/output.wav". (Example: fpath = "static/output"+somerandomstuff+".wav"). Output preview is shown below.

Do Not Abuse this code. I modified this code for educational purposes, polishing my skills over python and presenting information in unique ways. Note: Never click upload button without browse audio selection and text. It will give unexpected outputs.

You can see the debug information in console where server is running for letting know what is happening at background as shown below;