Free AI Text-To-Speech Voice Cloning – TTS With Any Voice! – Easy AI Voice Cloning – TorToiSe TTS

#ai #aitutorial #aivoice #aivoices #tts #texttospeech #texttovoice #aivoice #aivoices #tortoisetts

Clone any voice with TorToiSe TTS (AI Voice Cloning) for free. Learn how to easily train an AI model from any voice, so that you can control the ai voice with text-to-speech.

The voice-over for this video has been created with the same technique.

Links:

Wiki with detailed instructions

Download Python
Find it in the Windows Store app on your PC

Download GIT

Download CUDA Drivers

Download FFMPEG

Download Audacity

Commands to install the AI Voice Cloning package (TorToiSe TTS):

BTW I'm still trying to improve the audio quality of the AI voice that I control with my own voice.

Thank you for all the support everyone!

// Update
I heard from several people now that this also works well on Windows 10. Not sure why it said it’s Windows 11 only at first

My other videos about AI voice-cloning:

Offline method to make your own voice sound like any voice (currently the best overall quality):

My PC components:

(Disclosure: As an Amazon Associate, I earn from qualifying purchases. Clicking on and purchasing products through these links won't cost you any extra. They help support this channel and allow me to continue providing valuable content)

Chapters:

00:00 Introduction
00:22 Overview
01:12 Easy Install of Python via Windows Store
01:45 Check if Python is installed
02:05 Install GIT for Windows
02:25 Check if GIT is installed
02:39 Install CUDA Toolkit
03:06 Check if CUDA Toolkit is installed
03:32 Install FFMPEG to PATH
05:04 Check if FFMPEG is installed to PATH
05:16 Install TorToiSe TTS (AI Voice Cloning)
06:58 Prepare Input Audio
08:53 Train Voice model in TorToiSe TTS
11:06 Use the trained Model in TorToiSe TTS
12:11 TorToiSe TTS Preset Comparison
13:04 TorToiSe TTS Seed Comparison
13:33 TorToiSe TTS Emotions Comparison
13:59 Summary
14:42 Voice Generation Bugs

[UNCQNOWN]

when i typed start.bat
Function return PEP 484 type hint "typing.NoReturn" invalid in this type hint context (i.e., "typing.NoReturn" valid only as non-nested return annotation).
Press any key to continue . .

how

[xemy]

This is one of the most well structured tutorials I've seen, and of course the voice sounds excellent. Cheers!

[sabrinahafenberg]

I'm glad for this tutorial. At first I got some error problems, but when I tried it again it worked out really fine! Thank you very much for this tutorial, this is going to help me so much. It's so sad to see that you only have 600 subscribers, you deserve more. But very happy to see no dislikes on this video! 👍

[mohamedsalahoshi]

Ohh my god, took very long time to do it but after all, it was worth it, the problem is many people don't have that much patience to go through with all, but thank you very much your effort is appreciated.❤❤

[dheluxeTV]

This method is very clear. thank you very much.

[studioopinions]

That's impressive! Thanks for sharing. Terry

[OldSeaDoggy]

Pretty cool and a good tutorial. I did have an issue the the install bombing the first time so I deleted the install and started over and it went well without red error messages. Tested with the default voice and it worked. Now on to training some new voices. Currently in the middle of training with Sylvester Stallone's voice as a learning process.

[christopherquine]

imo the tts voice was great. very neutral and easy to follow. Your voice is great too don't get me wrong :)

[darkreader]

Wow! I could not tell at first that this voice was AI generate. Your tutorial also has very step by step detailed process, liked and subscribed.
Could you please share the voice data that you used in this video so that we can use it without needing to retrain? I have previously trained some voices but they were not as good as yours.

[personalgao]

I was looking for this video for a long time.
Thanks for the effort. Great video, will do a re-install today.
I want to know if there is a place to download more voices to use. Without training everything by myself.
Thanks in advance.

[topvideos]

Your voice cloning setup appears to be running smoothly. Could you share your system configuration, is your laptop or a desktop PC

[DimMakVigilanteGaming-vmcc]

This is really cool! I got it to work for a minute but then my computer crashed. I am wondering, do i have to redo everything again to get it to work everytime i shut my computer down or if it crashes?

[thibobultynck]

Clear and good instructions. 😮 does someone know if this is also possible on M1 or M2 macs?

[fixelheimer]

Hi. Thanks for the tutorial. It really worked well. After training with around 8 mins audio and your settings (and baking my PC for ~45 mins ^^ ), I got a pleasing result. As the vid is now 1 month old I wonder though, if you have updated your workflow or new suggestions. Although the training setting was slightly changed by the "validate configuration" process (some value from 8 to 7, does it change things you cannot change yourself inside the training settings?) because of VRAM. But then it only used ~12GB in the process (I ve got 24GB). I've got to dive more into the program, but I wonder how much better RVC might be, as you've said yourself? This is already good. Does the quality of the training data have a huge impact on the output quality or is not big, because of the diffusion and just the abstract characteristics of the voice are the base of what's then put into the new model? So many questions and lota more hehe, Thanks again for the well done tutorial!

[cedermannen]

Great content! Please do more text-to-speach with different languages and for Mac users without Nvidia GPU ⭐

[Jinx_]

Meta has launched its own TTS model named voicebox, (not realising it fearing its consequences).But they have a github repository named meta tts . You should make a video on this

[yasserabbass]

Great video, can you share the trained model used to create this video

[solidiux]

Got my voice cloned and it works like charm..btw any idea how can I get this voice I just made work with my assistant? I need to pass the text from the assistant somehow to the tts and make it generate the audio files.. I have already figured out how to play the generated files.

[DOHANEWSUPDATES]

PytorchStreamReader failed reading zip archive: failed finding central directory, i am getting this error, how to solve this ? please help me

[fixelheimer]

I recently trained a model for RVC to clone a singer (I personally know) and it worked quite well. I've seen people use TTS produced audio and put it through RVC to get a better more realistic voice. Now my question: TTS can be trained in many languages, is RVC language specific or could I train a voice in TTS, let it speak a text and then send it through RVC, when I have trained a model there (with the same training material) ? Have you tried to combine the 2 techniques?