Sublime

Introducing Dialog 1.0 - Ultra-emotional AI Text-To-Speech model Outperforms Elevenlabs on expressiveness and quality 3 to 1 <1% error rate Supports 30+ languages Best in class voice cloning Low latency: 303ms TTFA (Time to First Audio) ___LINEBREAK__... See more

PlayAI x.com

🎶 with @createwithplay https://t.co/sAGEXKKaBW

DK x.com

E

Emma Forster

@tootootusa

J

Joerg Sannwald

@josawa

G

Giannis Kampiotis

@gianniskampiotis

Project Voice Worldwide: DefinedCrowd, the GitHub of AI

youtube.com

What are the top open source TTS models out there? 🤔 Here’s my list so far: XTTS - https://t.co/SubVLvkN7D YourTTS - https://t.co/JJnYv2DPoW FastSpeech2 - https://t.co/RA1wH5TrV1 VITS - https://t.co/tOsW7en1vl TorToiSe - https://t.co/dQHLjizyp7 Pheme - https://t.co/tdg6qFApwQ What... See more

Vaibhav (VB) Srivastav x.com

Thumbnail of www-x-com-philschmid-status-1892599725913768161-d3910d0bc4e24992

Checkout this project if you work with audio recordings from Videos, Podcasts or Calls/Interviews! 🎧 Offmute is an open source project that uses @GoogleDeepMind Gemini 2.0 to transcribe, analyze, and summarize meetings, podcast or calls! It generates structured reports using a multi-stage workflow with smart speaker identification, automatic chunk... See more

Philipp Schmid

x.com

Amphion: Audio, music, and speech generation toolkit https://t.co/SrB20A0rHw

Tom Dörr

x.com