ElevenLabs releases Turbo 2.5 model
The model supports 32 languages, including Mandarin, and can provide…
Multimedia processing
Emilia, an open source, multilingual, high-quality voice dataset
CUHK (Shenzhen), in conjunction with the Institute of Acoustics of…
DETECT-2B: Audio Deep Forge Detection Tools
The sub-model of etect-2B consists of a frozen audio representation…
StreamVC: Real-time low-latency speech conversion
StreamVC can generate resulting waveforms from input signals with low…
RenderNet Al launches video face-changing feature
Net Al is a powerful image generation tool focused on…
The artificial intelligence company hopes to revolutionize the way conversations are redubbed into different languages
Flawless is an AI-driven film production studio that hopes you…
Stability AI launches two new features of Stable Assistant
Stability AI has announced two innovative features for its user-friendly…
Kyutai launches new open source AI voice assistant Moshi
Kyutai, an independent non-profit AI research laboratory in France, has…
Odyssey: Provides film-level AI video generation and editing tools
High-quality geometry generation: Generates fine 3D geometry for building realistic…
Generating singing and speaking videos based on a single image and audio input
Compared with EMO, this project is open source It can…
Translation API released by Apple
Apple’s new translation API does not require networking and completely…
Difffutoon: Render any realistic video directly into high-definition anime style
Colab notes are provided and you can run them directly…