←
ThorstenVoice669 posts
ThorstenVoice avatar

ThorstenVoice

@ThorstenVoice

🗣 "A free to use, offline working, high quality german TTS voice should be available for every project without any license struggle"

◷ Joined March 2021▧ 150 Photos and videos
ThorstenVoice avatar
ThorstenVoice@ThorstenVoice·17 Mar 2021

Hello 👋, nice that you're here 🙂. I'm a voice/TTS enthusiast sharing his voice with the community. ✅ 23 hours "normal" dataset ✅ "Emotional" dataset (😄😲🥴😤🥱) ✅ Pretrained TTS models ❤ for a 🌟 on Github. github.com/thorstenMueller/d…

Rishikesh (ऋषिकेश) avatar
⟳ ThorstenVoice retweeted
Rishikesh (ऋषिकेश)@ai_rishikesh·24 Jan 2025

Wave of LLM based TTS about to come 🤩

HOLY SHITT! Llasa TTS - Llama 3.2 fine-tune with ultra realistic audio 🔥 > 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

0:13
ThorstenVoice avatar
ThorstenVoice@ThorstenVoice·19 Dec 2024

Open voice tech enthusiasts, rejoice! 🎉 Finding 'living room compatible' hw has always been a challenge—but with @home_assistant Voice (Preview Edition), we're closer than ever! 👏 Check out my Thorsten-Voice YouTube channel for tutorials and tips 😊. youtube.com/playlist?list=PL…

Home Assistant avatar
⟳ ThorstenVoice retweeted
Home Assistant@home_assistant·17 Dec 2024

Pst. You, yeah you. Have you hit that 🔔 on our YouTube channel to get notifications? We're pretty sure there's something happening on Thursday... 🧐 Link in reply 👇🏼

Post attachment
Vaibhav (VB) Srivastav avatar
⟳ ThorstenVoice retweeted
Vaibhav (VB) Srivastav@reach_vb·12 Oct 2024

Let's goo! F5-TTS 🔊 > 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)🔥 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 she’s all, um, excited about her, uh, trip to Europe, and I’m just, like, so jealous, right? (Happy emotion) The TTS scene is on fire! 🐐

0:07
ThorstenVoice avatar
ThorstenVoice@ThorstenVoice·1 Oct 2024

I couldn't agree more 😍👏🏻. Thanks @home_assistant for bringing privacy aware voice enthusiasts together 😊.

🗣️ 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! 🍻🙏🏻

Post attachment