π£ "A free to use, offline working, high quality german TTS voice should be available for every project without any license struggle"
Joined March 2021
- Tweets 669
- Following 171
- Followers 479
- Likes 883
150 Photos and videos
Pinned Tweet
17 Mar 2021
Hello π, nice that you're here π.
I'm a voice/TTS enthusiast sharing his voice with the community.
β
23 hours "normal" dataset
β
"Emotional" dataset (ππ²π₯΄π€π₯±)
β
Pretrained TTS models
β€ for a π on Github.
github.com/thorstenMueller/dβ¦
8
6
20
6 Apr 2025
π₯ Check out my new YouTube video! First impressions of open source TTS: Kokoro, Fish, Llasa & Spark. π€
Discover the latest in voice tech: youtu.be/mZgLVVNvoEk?si=tj_bβ¦
#opensource #tts #voicetech
1
6
330
ThorstenVoice retweeted
24 Jan 2025
Wave of LLM based TTS about to come π€©
24 Jan 2025
HOLY SHITT! Llasa TTS - Llama 3.2 fine-tune with ultra realistic audio π₯
> supports voice cloning in English Chinese
> trained on 250K hours of audio
> 1B, 3B model (8B soon)
> emotional speech (happy, angry, sad, whisper)
> open weights & works with transformers/ vllm
1
1
6
361
9 Jan 2025
"Dr. Smith paid $1,234.56 at 3:30pm"
TTS π€: has mental breakdownπ
Tired of your AI voice butchering numbers & abbreviations? Got a fix for that!
New tutorial: How to make ANY TTS (even good old espeak!) speak like a human β youtu.be/-99WPCIlq-s
#TTS #TextToSpeech #VoiceAI
132
19 Dec 2024
Open voice tech enthusiasts, rejoice! π Finding 'living room compatible' hw has always been a challengeβbut with @home_assistant Voice (Preview Edition), we're closer than ever! π
Check out my Thorsten-Voice YouTube channel for tutorials and tips π.
youtube.com/playlist?list=PLβ¦
2
1
483
ThorstenVoice retweeted
18 Dec 2024
βΌοΈ Do you have a teen who codes in your life? Have them join Hack Club's High Seas!
We're excited to sponsor this challenge by providing Home Assistant Greens to buy with earned Doubloons! π
Find the details here ππΌ ends Jan 31!
highseas.hackclub.com
highseas.hackclub.com
1
3
29
6,666
ThorstenVoice retweeted
17 Dec 2024
Pst. You, yeah you.
Have you hit that π on our YouTube channel to get notifications? We're pretty sure there's something happening on Thursday... π§
Link in reply ππΌ
ALT An updated graphic for our Voice: Chapter 8 live stream teasing the hardware we are announcing. The background image is a cropped photograph of the side of the device - the blue and purple/pink lighting was used for the product photoshoot and it's lightly edited. Text overlay on the bottom left says What's new in Voice Chapter 8 The Home Assistant logo is in the top left of the image.
4
6
65
9,186
7 Nov 2024
ποΈ Create your personal AI voice clone with just 10s of audio input!
I uploaded a step-by-step tutorial on F5 TTS - the free, locally voice cloning tool that'll blow your mind π€― on my "Thorsten-Voice" channel.
Check it out here π
youtu.be/ASFoTNpkM8o?si=5fSFβ¦
#TextToSpeech #AIVoice
2
6
227
20 Oct 2024
π Thorsten-Voice turns 5! ποΈ
To celebrate, I'm gifting the community ALL voice datasets in their original 44kHz quality - now in one place on @huggingface!
Higher quality, easier access - same CC0 license π
Get it here: huggingface.co/datasets/Thorβ¦
#TTS #OpenSource #AI
ALT Showing www.Thorsten-Voice.de logo with text "Celebrating 5 years" and est. october 2019.
2
17
657
ThorstenVoice retweeted
15 Oct 2024
190ms TTFB π
14 Oct 2024
Today weβre introducing our latest Text-To-Speech model, Play 3.0 mini. Itβs faster, more accurate, handles multiple languages, supports streaming from LLMs, and itβs more cost-efficient than ever before.
Try it out here:
play.ht/playground/?utm_sourβ¦
2
1
8
1,045
ThorstenVoice retweeted
12 Oct 2024
Let's goo! F5-TTS π
> Trained on 100K hours of data
> Zero-shot voice cloning
> Speed control (based on total duration)
> Emotion based synthesis
> Long-form synthesis
> Supports code-switching
> Best part: CC-BY license (commercially permissive)π₯
Diffusion based architecture:
> Non-Autoregressive Flow Matching with DiT
> Uses ConvNeXt to refine text representation, alignment
Synthesised: I was, like, talking to my friend, and sheβs all, um, excited about her, uh, trip to Europe, and Iβm just, like, so jealous, right? (Happy emotion)
The TTS scene is on fire! π
64
237
1,984
465,232
13 Oct 2024
3 steps to run @huggingface "Parler TTS" AI Voice on your local machine. New tutorial video out now π!
My step-by-step technical tutorial is now available on my "Thorsten-Voice" youtube channel.
youtu.be/1X2LxAGn9tU
1
7
555
1 Oct 2024
I couldn't agree more πππ». Thanks @home_assistant for bringing privacy aware voice enthusiasts together π.
30 Sep 2024
π£οΈ September 30th is #InternationalTranslationDay, and we want to celebrate the Language Leaders. They are helping us build an open-source, privacy-focused voice assistant that anyone can run.
Thanks to all your hard work helping us over the Year of Voice and beyond! π»ππ»
ALT Image created by graphic artist Clelia Rella. Using the Home Assistant brand green and blue palettes on a light gray background, several speech bubbles of varying shapes and sizes say "thank you" in 13 languages. From the top the languages are English, German, Portuguese, Chinese, Romanian, Italian, French, Russian, Ukrainian, Dutch, Hawai'ian, Japanese, and Spanish. The Home Assistant logo and name are in the top left corner.
4
127
13 Aug 2024
π₯NEW VIDEO: "State of free text to speech | 2024.08".
First look audio samples of new cool #opensource #tts #ai projects and voices on my Thorsten-Voice #youtube #channel π₯³.
β‘οΈ youtu.be/B23Bgrukb9w
1
4
144
13 Aug 2024
Feat #ChatTTS, #MARS5 TTS by @useCamb_AI , MetaVoice by @metavoiceio , Parler TTS by @huggingface , Toucan TTS by @Uni_Stuttgart π.
Thank you all for providing cool #opensource #voice #Technology πππ.
1
143
ThorstenVoice retweeted
10 Jul 2024
hey so i now live in leipzig and am looking to connect with linguists or people working on NLP/ASR. or just other cool people. im so bored!! (i speak english, german, dutch, and spanish)
twitter do your thing please??
2
13
29
3,834
3 Jul 2024
Boom! Automatic voice dataset creation on raw audio using Whisper STT π.
youtu.be/YKeCmx8RTa0?si=PoDmβ¦
2
105
29 Jun 2024
π₯ Automatically voice dataset creation on raw audio voice input π₯. Running fully local as python script using whisper stt. Take existing voice audio for high quality voice cloning π₯³.
github.com/thorstenMueller/Aβ¦
1
5
135
22 Jun 2024
Guude π, new video online on my Thorsten-Voice channel π .
"Voice dataset LJ Speech". What is it? How it's used for voice cloning and high class TTS, close look to it's structure and more.
youtu.be/8JPCB6CiaQg
#tts #voice #tech #technology #voice #python #speech #ai #ml
6
133
14 Jun 2024
Gude π, new "Thorsten-Voice" video online! π₯ βBoost AI performance using @nvidia CUDA!β. The video includes a TTS performance comparison on cpu vs. gpu using @coqui_ai TTS πΈ Recorded in my totally new setup π₯³.
youtu.be/al3kEf7Vc0w
2
2
547