mastodon 4.7.2Guude! I'm an enthusiast on #opensource and #privacy aware voice technology and make tutorial on my #youtube channel.
🔥 Neues Thorsten-Voice TTS Modell am Start 🔥 . Die letzten Monate habe ich an meiner freien KI-Stimme auf Basis von CosyVoice3 gearbeitet.
Mehr Infos und vor allem Audio Beispiele gibt's hier: https://www.thorsten-voice.de/2026/06/29/thorsten-voice-%e2%9d%a4%ef%b8%8f-cosyvoice3/
Es gibt sogar ein Docker Image zum direkt loslegen (ohne Abhängigkeitshölle) 😆
#TTS #TextToSpeech #OpenSource #KI #Docker #CosyVoice #ThorstensVoice
Guude 👋🏼, I wrote about my journey of donating my own Thorsten-Voice as an open dataset including doubts, trust, and what happened afterwards.
Now published by @mozilla@mastodon.social Mozilla Data Collective: https://community.mozilladatacollective.com/on-contributing-my-thorsten-voice-voice-datasets/
Guude 👋 ! My german Thorsten-Voice datasets are all additionally now available on #MozillaDataCollective 😊. Thanks to Robert Pugh for his great support 🤗 .
https://datacollective.mozillafoundation.org/datasets/cmm4de9w500ntmh073nx14k7p
Guude 👋! Voicebox showed up on GitHub 4 weeks ago reaching over 11,000 stars.
It’s a local, open-source voice cloning studio built around Qwen3-TTS. Including multi-track timeline editor, voice profile management, Whisper transcription, and a REST API. Everything runs on your own machine.
I tested it on my M1 MacBook and did an honest walkthrough.
Video: https://youtu.be/y_p4OzDzkYU
I guess I missed something important 😅.
My Thorsten-Voice youtube channel just crossed 1.1 million views.
Thank you all for watching, commenting, and supporting this channel 🙌
This really means a lot 🤗 .
Huge shoutout to all free voice technology enthusiasts and communities out there 👏🏻👏🏻👏🏻. You do an amazing job for let everybody participate in our digital and modern life 🥰.
Happy “I Love Free Software Day" 😊!
(February 14th)
#TTS #STT #Voice #NVDA #VoiceTech #ILoveFreeSoftwareDay #ILoveFS #FreieSoftware #FreeSoftware #FLOSS
I've published a new tutorial about Qwen3-TTS 😎 . It covers an overview, audio samples, running on google colab and do testing on voice design and voice cloning (in english and german) 😊.
Interested? Check it out: https://youtu.be/MOIyC9w1Wi0