Відео

Couldn't follow you when you were showing code in Collab - was busy gazing at dogs running on a top

Omg dude, I really appreciate your work, and the voice of my AI powered cohost will be amazing because of it, I am very grateful

Hello, Thorsten. I've noticed that UA-cam has been deleting my comments everywhere. It's really frustrating because your channel is my main source for TTS tutorials, and I can't participate in the discussions, whether it's to compliment your work, thank you, or ask questions.

Great content! I teach a class locally on getting better results from ChatGPT, and normalizing inputs makes a huge difference, especially with RAG.

Thanks Thorsten! Good normalisation makes a huge difference and there are plenty of subtle edge cases. It's interesting that even the big companies mess this up at times: in London Google Maps' TTS incorrectly transforms some bus-stop letter codes into expanded abbreviations. So "Stop LT" becomes "Stop Lieutenant"!

I appreciate your work on this, but this is at the Commodore 64 level of computer programming. A tremendous amount of manual labor is required by every individual end user. This approach is for computer nerds, not ordinary computer users who just would like their normal text read properly.

Honestly these are problems that should actually be solved with proper computer programing. We are supposed to be an age of AI but so far it's very weak, extremely poor or totally awful. You are only working in one direction; text to speech, but the problems are equally massive with speech to text. I'm a exclusively Linux user and Linux has been way behind in this area. Only recently have I been able to get decent text to speech out of my computer using a program called, "Speech Note".

Thank you!!!!

i dont really understand about this, but i just want to ask, is it possible to make voice model of Indonesian Language using piper?

Dude, you rule so hard 🤘I have spent well over 12 hours binging your stuff in the last week, on repeat, and I am incredibly excited to have faster-whisper playing nice with piper! Now to give it a custom voice and a mind...l

what is the system requirement to run it locally

Hey man! Im on older machine its Dell optiplex 780 , can i run this on that, the newest version of tts is 0.22(if I'm not wrong) and i tried several hours but didnt work after that i did quit. But i really need it for my youtube videos voice overs can you help me , and a short answer of yes or no for using this as a voice over for youtube!(Even its ipen souce but i really want to make sure)

hello, is there any way to use the model directly on python like xtts v2. Gratefuly

V spricht man in Englisch wie ein deutsches W, win engl. W wie ein deutsches u

I couldn't resist. 😂

Can I build my own assistant with a special wake word and a special interface using rhasppy?

I was giving Piper a try for one of my projects when I stumbled upon your channel. It was a pure joy to watch your excitement. 🙂

Amusingly, when training these on a 4090 the checkpoints blow by so fast you cannot actually load and test them. By the time it tried, the checkpoint it found using *.ckpt was already 3 versions behind and long gone.

Thorsten, installing it all with Pinokio is so much better. Installing everything with Pinokio in the AI world is so much better.

Excellent content, I will give it a try :)

Hi! Thank you for your videos. Can you please tell me in your opinion the best TTS software available for meditation and also personal trainer voices in each gender. I can do some fine tuning but preferably looking for a Simple and cheap option. Any thoughts?

Thank you so much for your video; it’s truly valuable to me. Oh, and I really like your teaching style in the video as well. 😁😁

hello sir

Sadly, none of the reviewed models and frameworks work locally. I have a 2080 Nvidia and tried the frameworks on Umbuntu. All of the frameworks have very poor documentation. Tucan has an issue with the code that is meant to execute finetuning and kept coming up with division by zero errors (I think it has a lower limit on number of samples but not mentioned anywhere in docs). Mars5 needs more than 16GM Vram (but not mentioned anywhere either). ChatTTS does NOT support finetuning, but needs training from scratch. and MetaVoice has a stated 12GB VRam requirement, which meant I did not even try.

DISREGARD: I got a fork and was able to install it! Thank you! I tried to install coqui TTS to Python (version 3.11.1) using VS Code, but receive an error message: "ERROR: ERROR: Failed to build installable wheels for some pyproject.toml based projects (TTS)". Please help! Thank you for the video. Best.

Can you tell me can we use this to data augmentation of low resource language like `URDU`? Non english language or asian languages? Like Urdu, Hindi? as Urdu is under resource language so i want to create a very large dataset of this.

This is pure joy! Do play around with other voices, there are some really good ones.

which ones we can use with Swift CoreML ? Is it possible to make them run swift locally?

It would of been nice to see an example of how it works. Does it respond well? How fast does it respond? There really wasnt anything in the video showing how well it works

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

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