Tag
4 articles
ElevenLabs unveils a new AI music model that allows users to switch genres mid-track without affecting the rest of the composition.
Stability AI has released Stable Audio 3, a family of fast latent diffusion models for audio generation and editing. The open-weight models are optimized for both CPU and GPU environments, with strong performance on benchmark tests.
Google launches Gemini 3.1 Flash Live, an upgraded AI audio model that makes synthesized speech more natural and reliable. The update enhances real-time audio processing capabilities for virtual assistants and content creation tools.
Learn how Google's Lyria 3 Pro music generation model represents a major advancement in AI audio synthesis using transformer architectures and sequence modeling techniques.
