Yeah would be interesting to see if it can be used with other software as well

Hello, I want to make a text-to-sound conversion model for Farsi, which videos should I watch now, where can I contact you?

What is the device with microphone, button and led round light is on your table? Can you please give some more details?

New nvidia minicomputer (jetson if I'm not mistaken) which was released just recently is a good replacement for regular bulky PC with full sized GPU card.

Can I use it for German?

what is language suport and can help me for give me inforation about modle support language arabic

@ThorstenMueller I am facing this error please help me: PS C:\Users\Apple Compter\tts> pip install TTS--0.22.0 Defaulting to user installation because normal site-packages is not writeable ERROR: Could not find a version that satisfies the requirement TTS--0.22.0 (from versions: none) ERROR: No matching distribution found for TTS--0.22.0

is there any way to run this in python code?

Coqui appears to have folded now. Confusingly there is a community run fork that is sorted but its docs look very similar to the original.

دوستت دارم

Hello Torsten I have heard that some languages in Piper TTS sound pretty bad for example the Swedish model like that when you train a new voice like when you find tune from the existing checkpoint mall that exists it sounds quite bad and such is that true because the default Swedish NST voice sounds very monotone but when you find tune from that will it sound like me or will it sound different just with the pronunciation errors and when you find two from scratch How many hours of speech do you need I have an RTX 40 6016 GB card so is that good for AI training and the thing is also that do I need to set up Linux and Windows at the same time and fiddle around with complicated stuff because it’s just easier to have a Windows set up And not worry about Windows for Linux so can I just do it with a command

This is exactly what I was looking for. Unfortunately, after I installed "tts" using "pip install tts --use-deprecated=legacy-resolver" and resolved some dependency issues, I encountered a "Bus error." Installing "tts" without additional flags causes it to take a long time because pip tries to resolve all required package versions. I tried everything, even attempting to install it with "pip install tts --no-deps" to install only the "tts" package. However, after running "tts --list_models," I still get a "Bus error." The version I have installed is 0.22.0. I am trying to install it in a Python virtual environment, of course.

It is a nice and useful video. Thank you. I am looking at various options right now.

The voice quality is OK, but not great. Did you ever figure out a way to make it better?

What's the best TTS for use in an Apple and Android app locally (ie no server connecting)?

Wow, that's great, thanks for showing this! Subscribed :)

Hello Thorsten, can you have a check and review of PopPop AI text to speech?

tried getting this to work on my own, couldn't came here, watched this twice and it's up and running. Thank you @ThorstenMueller

can piper switch between voices? previously i have used mimic3 server and requested texts with different specific voices, can piper do the same or is it limited to the voice you start server with? Nevermind, i've found where i can make a few adjustments to the script to pass in a speaker together with a text.

okay sehr schön. Im Piper adon funktioniert es. In einer Automation sagt eine weibliche Stimme: set public URL in configuration. Muss da noch was rein geschrieben werden in der Config.yaml?

As a Ghanaian i'm happy to hear TTS in Twi and Ewe and Hausa

I tried this morning and the cloned voices are the best I have never used. I wonder if I can use the cloned voices in some way with Home Assistant through I don´t know know..piper might be ? I can´t find if this is possible to do with this software, it is only tts ? is possible to synthesise a dataset with this ? Thanks

that's really really good quality for open source

I like the shirt

Bär-er nicht Bier-er-Token. just fyi

hey @ThorstenMueller, great work as always! one thing that caught my eye: you mention that the code is released under MIT licence, which is right. But i think its also important to note that usually inference code and models have different licences (which you covered on other videos!). Here the model itself has a different licence: at 3:13 you can see it on top middle and in the text under it, that the model files are CC-BY-NC-4.0 licenced, which means no commercial use. This means you can not use generated voices for anything commercial like voice overs for youtube channels or in companies. It would be great to have this information as well in your videos, since people using this in any commercial environment or a simple monetized youtube channel can bring you in trouble if the owner enforces the licence. It would be great if you could make a video with an overview of fully open and free TTS/cloning models, that allow also commercial use.. i havent seen such a list anywhere and im sure lots of people would be interested.

Is online Huggingface better than local?

coqui tts is shutting down

first time to see the channel and the video. was talking about this app with a friend of mine who told me about it yesterday while we were in lunch break. Now i'm interested LOL . thanks for the guide

can we use it for making KZbin videos and monetize it ? i mean is legal

OMG, you are life saver for me!! Awesome!!

I tired this out on a rtx 3600 12gb model and it's fast. Quicker than speaking, maybe 2x faster to process than to listen to. Sounds really good to me.

can we run piper tts in gpu using cuda ?

This error originates from a subprocess, and is likely not a problem with pip. error: subprocess-exited-with-error im getting this error please help someone

Hello Thorsten, thanks for your great channel. I came about these videos which shows how one can train F5 with different languages kzbin.info/www/bejne/i4CXpqaXhNSdr9U kzbin.info/www/bejne/iIK7eX6Faqtsnsk As you are experienced with training of speech models, I am wondering how much hours material would be required to train a German language model in good quality and what things should be considered in regards to training data. In the referenced youtube video the creator simply takes audiobooks. Can one expect to get a good quality model in this way?

Hi Thorsten, thank you for another excellent tutorial. I have installed f5 on a Raspberry Pi 5 and it generates very good quality output but to be expected it is very slow. I am trying to understand how f5 works, does it take a standard model and modify it in some way using the ref_text & audio before generating the desired output (gen_text)? Is there an intermediate stage that could be executed separately? Thanks Ernie

How much time it took to train one model??? And how powerfull is your system?

If anybody is encountering errors when installing TTS, try pip install coqui-tts (tts is deprecated as of november 2024)

I went down this rabbithole myself last year. Alas! Have I watched this 6min video I would've saved lotsa disk space and time (weeks). Cheers! ✌

Hi, Thorsten, the community thrives because of people like you - thanks for your work!

thanks! it is faesabel to do all of that trought scripted pyton code?

the greetin comes from hessen in germany right? :D funny intro and exactly what i am searching for :) abo

What GPU do you have on your computer?

May I ask what gpu you are using, or if it is using a gpu?

For anyone coming recently, the tts repo isn't maintained anymore according to an issue post on the github. It results in an error when running 'pip install tts'. This fork worked for me instead: 'pip install coqui-tts'

is there a way to use this with nvidia gpu on windows to speed up performance?

can this be deployed and hosted on a server?

I tried it and it works but it did not sound like me. Nothing close to what you did. Not a fan at this time it really should have done better. Thanks for sharing you got my thumbs up...

great stuff!

Haha the F5 joke😂. The progress is amazing, right? Still waiting for german support for F5... Anyway in english it is now already easy to create synthetic voice datasets for piper for example, just an idea😊