![Thorsten-Voice](/img/default-banner.jpg)
- 146
- 553 464
Thorsten-Voice
Germany
Registrace 12. 11. 2013
Guude! (hi, nice to see you) đ,
i'm Thorsten đ.
You like open source, privacy aware and local running voice technology? Me too đ. You'll find cooking recipe like tutorials on TTS, STT, Voice Assistants, AI, ML and way more cool stuff here. So, hop on and join my amazing community đ„°.
#opensource #voice #cloning #technology #news #tutorial #local #privacy #tech #tts #stt #voiceassistant #raspberrypi #smarthome #homeassistant
* My project website: www.Thorsten-Voice.de
* Me on GitHub: github.com/thorstenMueller
i'm Thorsten đ.
You like open source, privacy aware and local running voice technology? Me too đ. You'll find cooking recipe like tutorials on TTS, STT, Voice Assistants, AI, ML and way more cool stuff here. So, hop on and join my amazing community đ„°.
#opensource #voice #cloning #technology #news #tutorial #local #privacy #tech #tts #stt #voiceassistant #raspberrypi #smarthome #homeassistant
* My project website: www.Thorsten-Voice.de
* Me on GitHub: github.com/thorstenMueller
State of free text to speech | 2024.08
Free #TTS with #Mars5 #Parler #MetaVoice #Toucan and #ChatTTS. First look and comparison video on voice cloning and more.
Thanks to you great #opensource text to speech projects and @HuggingFace for providing cool spaces to play around with đ€.
And thank you "VB" for pointing to these cool projects on LinkedIn đ:
www.linkedin.com/posts/vaibhavs10_text-to-speech-ecosystem-has-been-booming-activity-7214677769450926080-uPAj?
Chapters for better navigation:
00:00 Intro
01:30 ChatTTS
10:43 Mars5
21:33 MetaVoice
28:35 Parler TTS
36:53 Toucan
43:25 Summary & Outro
ChatTTS:
---
* chattts.com/
* github.com/2noise/ChatTTS
* huggingface.co/spaces/Dzkaka/ChatTTS
Mars5:
---
* www.camb.ai/
* github.com/Camb-ai/MARS5-TTS
* 6b1a3a8e53ae.ngrok.app/
MetaVoice:
---
* themetavoice.xyz/
* github.com/metavoiceio/metavoice-src
* huggingface.co/spaces/mrfakename/MetaVoice-1B-v0.1
Parler:
---
* github.com/huggingface/parler-tts by @HuggingFace
* huggingface.co/spaces/parler-tts/parler_tts
Toucan:
---
* github.com/DigitalPhonetics/IMS-Toucan
* huggingface.co/spaces/Flux9665/MassivelyMultilingualTTS
* huggingface.co/spaces/Flux9665/ThisSpeakerDoesNotExist
Additional great open source tts alternatives and tutorials on my channel:
Piper TTS:
---
Tutorial playlist:
* czcams.com/video/Z1pptxLT_3I/video.html&pp=gAQBiAQB
Coqui TTS:
---
Tutorial playlist:
* czcams.com/video/HojuVmW5LUI/video.html&pp=gAQBiAQB
---
- www.Thorsten-Voice.de
- github.com/thorstenMueller/Thorsten-Voice/
Thanks to you great #opensource text to speech projects and @HuggingFace for providing cool spaces to play around with đ€.
And thank you "VB" for pointing to these cool projects on LinkedIn đ:
www.linkedin.com/posts/vaibhavs10_text-to-speech-ecosystem-has-been-booming-activity-7214677769450926080-uPAj?
Chapters for better navigation:
00:00 Intro
01:30 ChatTTS
10:43 Mars5
21:33 MetaVoice
28:35 Parler TTS
36:53 Toucan
43:25 Summary & Outro
ChatTTS:
---
* chattts.com/
* github.com/2noise/ChatTTS
* huggingface.co/spaces/Dzkaka/ChatTTS
Mars5:
---
* www.camb.ai/
* github.com/Camb-ai/MARS5-TTS
* 6b1a3a8e53ae.ngrok.app/
MetaVoice:
---
* themetavoice.xyz/
* github.com/metavoiceio/metavoice-src
* huggingface.co/spaces/mrfakename/MetaVoice-1B-v0.1
Parler:
---
* github.com/huggingface/parler-tts by @HuggingFace
* huggingface.co/spaces/parler-tts/parler_tts
Toucan:
---
* github.com/DigitalPhonetics/IMS-Toucan
* huggingface.co/spaces/Flux9665/MassivelyMultilingualTTS
* huggingface.co/spaces/Flux9665/ThisSpeakerDoesNotExist
Additional great open source tts alternatives and tutorials on my channel:
Piper TTS:
---
Tutorial playlist:
* czcams.com/video/Z1pptxLT_3I/video.html&pp=gAQBiAQB
Coqui TTS:
---
Tutorial playlist:
* czcams.com/video/HojuVmW5LUI/video.html&pp=gAQBiAQB
---
- www.Thorsten-Voice.de
- github.com/thorstenMueller/Thorsten-Voice/
zhlĂ©dnutĂ: 4 813
Video
Automate Voice Dataset Creation Using Whisper AI
zhlĂ©dnutĂ 1,2KPĆed mÄsĂcem
Easy tutorial on creating a structured voice dataset on raw audio data using Python and Whisper by OpenAI for speech recognition. #ai #whisper #tts #voice #data #python 00:00 Intro 01:10 Set up python virtual environment 03:00 Working with "the magic" script :) 07:00 Run voice dataset generation with Whisper AI STT 07:58 Checking results 09:45 Outro * github.com/thorstenMueller/Audio-to-Voice-D...
TTS Voice Dataset | LJSpeech | Voice Cloning
zhlĂ©dnutĂ 1,4KPĆed 2 mÄsĂci
Close look to ljspeech voice dataset and it's structure for tts voice cloning. The ljspeech voice dataset is widely supported by tts voice cloning software. Videos is describing the structure and how you can create it for your personal voice clone. 00:00 Intro 02:23 LJSpeech info and download 04:15 LJSpeech in research (Google Scholar) 05:17 Close look to the voice dataset file structure 06:25 ...
Unlock AI Superpowers with NVIDIA CUDA: Boost Performance in Python!
zhlĂ©dnutĂ 953PĆed 2 mÄsĂci
Boost your AI performance by using NVIDIA CUDA on Windows. Step by step tutorial on how to use CUDA with Python / pytorch and performance comparison with Coqui TTS. #performance #nvidia #python #ai #machinelearning #tts Please subscribe to my channel đ. czcams.com/users/ThorstenMueller Thanks dear @MightyReiti for your inspiration and support on my new recording setup â€ïž. 00:00 Intro 01:55 What...
Home Assistant â€ïž Voice - Tutorial 05 - Wyoming protocol
zhlĂ©dnutĂ 3KPĆed 5 mÄsĂci
Home Assistant â€ïž Voice - Tutorial 05 - Wyoming protocol
Home Assistant â€ïž Voice - Tutorial 04 - Piper TTS
zhlĂ©dnutĂ 4KPĆed 5 mÄsĂci
Home Assistant â€ïž Voice - Tutorial 04 - Piper TTS
Home Assistant â€ïž Voice - Tutorial 03 - Conversation / NLP
zhlĂ©dnutĂ 1,2KPĆed 6 mÄsĂci
Home Assistant â€ïž Voice - Tutorial 03 - Conversation / NLP
Home Assistant â€ïž Voice - Tutorial 02 - Text Assist
zhlĂ©dnutĂ 1,2KPĆed 6 mÄsĂci
Home Assistant â€ïž Voice - Tutorial 02 - Text Assist
Home Assistant â€ïž Voice - Tutorial 01 - Basic setup & demo entities
zhlĂ©dnutĂ 3KPĆed 6 mÄsĂci
Home Assistant â€ïž Voice - Tutorial 01 - Basic setup & demo entities
Running a local Piper TTS server with Python on Linux
zhlĂ©dnutĂ 4,9KPĆed 6 mÄsĂci
Running a local Piper TTS server with Python on Linux
đ„ Voice interview Michael Hansen | HA | Raspberry | Piper | Rhasspy
zhlĂ©dnutĂ 1,6KPĆed 6 mÄsĂci
đ„ Voice interview Michael Hansen | HA | Raspberry | Piper | Rhasspy
Local voice cloning with 6 seconds audio | Coqui XTTS on Windows
zhlĂ©dnutĂ 35KPĆed 8 mÄsĂci
Local voice cloning with 6 seconds audio | Coqui XTTS on Windows
đ©đȘ KĂŒnstliche Sprachausgabe uff Hessisch | Kostenlos und OHNE CLOUD !
zhlĂ©dnutĂ 905PĆed 9 mÄsĂci
đ©đȘ KĂŒnstliche Sprachausgabe uff Hessisch | Kostenlos und OHNE CLOUD !
TEXT TO SPEECH | Piper TTS on Windows đ AI voice 10x faster Realtime!
zhlĂ©dnutĂ 21KPĆed 9 mÄsĂci
TEXT TO SPEECH | Piper TTS on Windows đ AI voice 10x faster Realtime!
XTTS FAQ | Interview with Josh Meyer from Coqui AI
zhlĂ©dnutĂ 1,9KPĆed 9 mÄsĂci
XTTS FAQ | Interview with Josh Meyer from Coqui AI
Python virtual environment / venv | Windows, Linux & Mac OS X
zhlĂ©dnutĂ 2,3KPĆed 11 mÄsĂci
Python virtual environment / venv | Windows, Linux & Mac OS X
Free voice recording for BEST voice cloning | Piper-Recording-Studio | Windows
zhlĂ©dnutĂ 7KPĆed 11 mÄsĂci
Free voice recording for BEST voice cloning | Piper-Recording-Studio | Windows
Is Mycroft Mark 2 the better Alexa?! | Private | Voice Assistant
zhlĂ©dnutĂ 3,1KPĆed rokem
Is Mycroft Mark 2 the better Alexa?! | Private | Voice Assistant
Create your AI digital voice clone locally with Piper TTS | Tutorial
zhlĂ©dnutĂ 41KPĆed rokem
Create your AI digital voice clone locally with Piper TTS | Tutorial
Increase Text to Speech pronunciation quality with eSpeak | Tutorial
zhlĂ©dnutĂ 10KPĆed rokem
Increase Text to Speech pronunciation quality with eSpeak | Tutorial
Talk locally (no ChatGPT) with your documents đ | PrivateGPT + Whisper + Coqui TTS
zhlĂ©dnutĂ 6KPĆed rokem
Talk locally (no ChatGPT) with your documents đ | PrivateGPT Whisper Coqui TTS
Raspberry Pi | Local TTS | High Quality | Faster Realtime with Piper TTS
zhlĂ©dnutĂ 24KPĆed rokem
Raspberry Pi | Local TTS | High Quality | Faster Realtime with Piper TTS
Thorsten-Voice TTS in Windows nutzen | DDC / VITS
zhlĂ©dnutĂ 4,4KPĆed rokem
Thorsten-Voice TTS in Windows nutzen | DDC / VITS
Thorsten-Voice TTS in Linux nutzen | DDC / VITS / Piper
zhlĂ©dnutĂ 2,8KPĆed rokem
Thorsten-Voice TTS in Linux nutzen | DDC / VITS / Piper
Thorsten-Voice TTS in Mac OS X nutzen | DDC / VITS
zhlĂ©dnutĂ 1,3KPĆed rokem
Thorsten-Voice TTS in Mac OS X nutzen | DDC / VITS
Freie "Thorsten" Stimme in HOME ASSISTANT lokal nutzen | Text-to-Speech/TTS | Tutorial
zhlĂ©dnutĂ 3,5KPĆed rokem
Freie "Thorsten" Stimme in HOME ASSISTANT lokal nutzen | Text-to-Speech/TTS | Tutorial
Thorsten-Voice TTS in Raspberry Pi OS nutzen | Piper
zhlĂ©dnutĂ 1,3KPĆed rokem
Thorsten-Voice TTS in Raspberry Pi OS nutzen | Piper
End of home automation/smarthome AND voiceassistant software?!
zhlĂ©dnutĂ 399PĆed rokem
End of home automation/smarthome AND voiceassistant software?!
Local âChatGPTâ Chatbot talk with LLaMA/GPT4ALL + Coqui TTS đ€Ż | Install Tutorial
zhlĂ©dnutĂ 9KPĆed rokem
Local âChatGPTâ Chatbot talk with LLaMA/GPT4ALL Coqui TTS đ€Ż | Install Tutorial
Tutorial: Free diskspace by remove Coqui TTS models (Windows/Linux/Mac OS X)
zhlĂ©dnutĂ 1,3KPĆed rokem
Tutorial: Free diskspace by remove Coqui TTS models (Windows/Linux/Mac OS X)
Funktioniert bei mir nicht. Python ist installiert wird aber in der Kommandozeile nicht gefunden. Finde den Fehler nicht woran das liegen könnte.
Hallo Thorsten, schönes Video! Klappt das auch mit srt oder sbv Dateien? VG Anton
thanks Thorsten, greetings from buenos aires, argentina
das shirt đ scheiĂ encoding, fĂŒhl ich
Hallo Thorsten, ich muss Dir dreifach DANKEN. 1. Habe mit Piper genau die AI Anwendung gefunden die ich schon lange gesucht habe. 2. Danke fĂŒr Deine super Piper Stimme und vielen danke fĂŒr Deine Arbeit und BemĂŒhungen. 3. Habe nun selber ein CZcams Kanal und verwende dafĂŒr Deine Stimme :-) NatĂŒrlich erwĂ€hne ich Dich in jedem Video. Siehe @MundusInfo | www.youtube.com/@MundusInfo
Thank you, Man, for this wonderful infermation
You're very welcome đ.
Can I hire you for a few hours? I need help with a project thatâs deeply personal and I would like to go the local hosting route.
Feel free to contact me here (with some additional info). www.thorsten-voice.de/en/contact/
i have to record 12,000 wav of my voice samples??
No, i did many recordings. But if you train / finetune an existing model you might be able to get good results with 500-1000 recordings already.
What's the speed of espeak?
You mean as a phonemizer or their robotic (mbrola) voices? Either way it is really super fast (on small compute devices).
Yes as a phonemizer. A LLM that can turn text into phonics would be interesting. I can't find a good collection of phonics sound samples. Which could be used for experimenting.
Arduino talkie is fun. And software 'praat' might be worth looking at.
I'm not sure if theres is requirements.txt anymore in recent versions of PrivateGPT, i'd like to see an up to date tutorial :D
Thanks for the video! Any suggestions on introducing better natural pauses within the text to slow down voice? It doesn't seem to respond much to commas and periods.
Imho the Piper TTS project is working on ssml support which should be helpful for that. But i am unsure on their roadmap.
@@ThorstenMueller thank you!
Not sure where I went wrong. echo 'Welcome to the world of speech synthesis!' | ./piper.exe --model en_US-lessac-medium.onnx --output_file welcome.wav has no output on windows it does something for a second but no output in the shell or in the folder. I have powershell open inside of the directory that I extracted the zip file to. ./piper.exe --help does work
Look in the comments, someone mentions for the latest updates you also need to add -config (and config file)
So i want to ask about a tool that can extract from a person. Like for example if i want a person with their specific language and they can use their voice. The tool will allow to record the voice first and automatically extract it. Once that happens, that voice can be converted into AI Generated voice on that same voice and accent in just few words. From this, we can test if we type a few words from text to speech. That specific custom generated AI voice that is extracted will convert the speech to the exact voice and accent itself. Is there a specific tool for that?
I wonder which one is better for training a Spanish model. I want to convert books to audio with s better voice than Android. Any guidance?
Sehr gut erklÀrt. Ich hatte von dem video jedoch erhofft, nicht nur einen einzelnen speech zu erstellen, sondern mein eigenes model abzuspeichern, so dass es dann z.B. unter tts --list_models auftaucht oder ich es zumindestens bei --model_name angeben kann. Ist das auch möglich?
I am bigger how i learn ai voice cloning and accent
How I learn voice cloning and voice accent
Hi. thank you for your videos. I'm kinda new to this so I don't know much about all this. is there any "good" tts for people that have AMD gpus and are using windows? if there is, can you connect them to something like koboldAI and how?
H Thorsten, thanks for this fantastic tutorial. What I don't understand (I'm not a LINUX specialist): I'm running Home Assistant as an operating system on a Raspberry Pi 4B. How di I install the Coqui TTS server in this case?
Do you have an installation video for a compatible version of Coqui TTS? I have a newer version of Coqui XTTS, but it doesn't have models such as Slovak. Assuming it is legacy?
FAZ UMA VERSĂO ATUALIZADA DO COQUI TTS NO COLAB E DEIXA O LINK DO COLAB PRA GENTE SEGUIR AS ORIENTAĂĂES, POIS AGORA ESTA DESATUALZADA E NAO FUNCIONA MAIS, OBRIGADO @ThorstenMueller
MAN I LOVE YOU
Thank you đ„°
could you do a video about how to train TTS for our native languages. there are videos but those videos are now old and there are some updates. we would really appreciate if you do for both linux and windows
What are the minimum specification required to run this?? 1GB ram of raspberry Pi 4b enough??
My tests have been some times ago, but imho i got acceptable/good performance results (depending on use case) on my Raspberry Pi 3b.
Nice German accent. đ
ThĂ€nk ju đ
Thank you for going over these models! I really enjoyed it! I have a question about Parler TTS. I want to train in on languages like Arabic that don't use English letters, do you think that could be possible? I tried using Common Voice as an example but failed
Thanks for your nice feedback đ. I'm not sure about their support for languages with non Latin letters, like Arabic. I will take a closer look to training a model from scratch using Parler TTS with my german "Thorsten-Voice" german dataset - maybe i'll find something on this process for Arabic language.
@@ThorstenMueller Thank you so much! Looking forward to it!
Is it possible for two speakers can you help us to find two speakers supported models?
What do you mean by "two speakers"? Do you mean switching between two different voices in one sentence?
@@ThorstenMueller yes your right.
My man!!!!!! Fank yoe very moch
I stupidly though Parler would speak French language but it doesn't seem to...
As the name is sounding a little bit french (at least for my german ears) i understand your thought :-). According their space "trained using 45k hours of narrated English audiobooks" the available model in english only. But imho you can use their project to create a tts voice for any language. But i'll try to find out when working on Parler TTS detail video.
Best open source library for fine-tuning custom voices? Im currently using alltalktts and the models come out decent, just wondering if there is anything better.
Thanks for your hint for "AllTalk TTS". I've heard this a few times but not taken a closer look. You think it's worth a closer look?
@@ThorstenMueller 100% it includes a ton of documentation and helpful tips, the installer is just one click. Fine tuning a model is a breeze...they walk you through the process step by step.
Is there any way we can push this trained model to huggingface? Like once we give the audio sample and next time when pushed to huggingface hub we only need to pass the text to generate the audio with respective voice?
Do you mean the actual model or a space to use the model out of the box?
Hallo Thorsten und ein herzhaftes Mopn, Moin, aus dem Norden und Danke fĂŒr dieses Video! BezĂŒglich deiner Frage, was ich als Bestandteil deiner geplanten Folgen zu den jeweiligen TTS-Systemen gern hören/sehen wĂŒrde: FĂŒr mich (und wahrscheinlich auch viele andere) wĂ€re interessant, wie sich die jeweiligen Modelle in lokale Desktop-Anwendungen (wie etwa Open-WebUI, Text-Genneration-WebUI., LM-studio, Koboldcpp, etc.) einbinden lassen, bzw. ob das ĂŒberhaupt möglich ist. Da du dich in deinen Videos hĂ€ufig mit der Thematik lokal laufender Annwendungen auseinandersetzt, dĂŒrfte dies wohl sowieso ein naheliegendes Thema sein... Hello Thorsten! Greetings from the north of Germany and many thx for this video! Regarding your question about what I'd like to see covered in the upcoming videos about the the different TTS-models, that you're planning to create: I guess it's not only me who would be interested in how it will be possible (or if, anyway) to integrate those TTS-engines into desktop-apps running LLM's locally like: Open-WebUI, Text-Generation-WebUI (Oobabooga), LM-Studio, Koboldcpp, etc. Since running TTS locally seems to be the topic of several of the videos we find on your channel, this might be something that is close to you anyway...
Guude, bzw. Moin in den Norden đ. ich habe deine Anmerkungen mal in meinen "Katalog" fĂŒr die Detail-Videos aufgenommen - vielen Dank dafĂŒr.
Thank you so much for your effort in this, it really helped me â€
Thanks for your very nice feedback and you're welcome đ.
Whole video is pretty pointless, can't find out which one is better, cloning your foreign accent doesn't help much too and the programming language/OS isn't useful (would be better to know if it uses CPU/CUDA/METAL and how fast is its inference)... Try cloning the voice of the Professor in Futurama. Your T-shirt sums it up.
That was mean Yoooo
It's not as pointless as ur comment
1:39 I don't really care how some TTS sounds. Most importantly I care how easy is it to use. I currently use TTS to convert dialog heavy stories into audio. So I need support for multiple voices for a single audio file, or at least a way to generate the text of multiple people at once. Currently I use a rust program, which uses piper. It can convert a multi person text document into speech. I specify the voices in a separate markdown inspired file. When generating the speech a second time, only the edited segments are regenerated. If I edit the parameters of a voice, only the segments using this voice are regenerated.
IMHO Piper TTS has SSML support on their project roadmap. This should make things easier to switch between voices in one sentence by adjusting XML based tags.
developers who are do open source... they don't know they might change someone live into better living... i got blind friend it is never been so happy moment for her listening humanlike speech... she said maybe someday she could get a emotional speech driven by context paragraph it read, she said imagine if she reading (listening) a novel with automatic switching voice and emotionally accurate referred by the story...
Thanks for your feedback. I agree that open source can change the world to the good. I'm pretty optimistic that emotional speech will come (in nearer future) which your blind friend can hopefully use for novel tts reading.
@@ThorstenMueller yes, what a beautiful future already.
I remember back in 1995, using the MAC TTS for the first time at the age of 12. That sense of wonder and awe... you took me back there... Thank you Thorsten!
đ€ - you're very welcome đ.
I'd like to hear more about 'integration' or TTS... for reading text...not just for amusing myself, by cloning my voice.
Is PiperTTS still the best to do training?
Right now i'd say yes. But this might change if i tested "Parler TTS" and "Toucan TTS" with their training features.
@@ThorstenMueller Thanks, I will take a look at them as well
I loved this type of content Thorsten. You made it so easy for me to test some TTS models I wanted to for using in some home automation projects. You are the best Thorsten, thank you so much đ đđ
Wow, thanks for your amazing feedback đ„°.
This is great, I installed for my home assistant! Do you know how I could use it for twitch chat tts?
Thanks for your feedback đ. Not yet, but using Piper for Twitch is on my (long) TODO list.
Can Piper use the GPU of the M1 processor?
Good question đ€. I am not sure about that.
I have a voice in .pth.. how can I use it in piper? how can I convert making the .onnx + .json file?
Is your .pth file from a Coqui TTS training? If so you can't (imho) convert it to Piper model structure (onnx).
Can I still use this toturial? since Coqui is shut down. Plus can I use it for cloning Urdu language?
Honestly i'm not sure on the future of XTTS (model, code and huggingface space) cause of their shutdown. But right now code and space is still available so it should still work as described but please let me know if you experience bigger problems.
--- hallo, bitte das tutorial nochmal auf deutsch. weil das wĂŒrde mich wirklich sehr interessieren. aber englsich verstehe ich kein wort.
Hallo, helfen dir vielleicht zunĂ€chst die automatisch auf Deutsch ĂŒbersetzen Untertitel?
@@ThorstenMueller die sind immer aus bei mir. weil ich beim lesen dem video nicht volgen kann. daher bringt mir das nicht wirklich was.
2% help for noob like me... cant find any other video that works for me
does this work on Windows?
I didn't try it yet, but i don't see a problem why it should not work on Windows. Did you try it and run into problems?
I have learned many things from you . And I have trained 3 model in Persian language . Thanks â€
Thanks a lot for your great feedback. Happy that my videos helped you on creating your 3 persian models đ.
How to use or convert an existing PyTorch model in .pth format? I used w-okada voicechanger to export it to .onnx, but Piper throws me an error. ValueError: Required inputs (['feats', 'p_len', 'pitch', 'pitchf']) are missing from input feed (['input', 'input_lengths', 'scales', 'sid'])