AI Briefing#text-to-audio
The latest AI and developer news about #text-to-audio, with the original source and a short summary.
The latest AI and developer news about #text-to-audio, with the original source and a short summary.
WavFlow presents a method for generating high-quality audio directly in the raw waveform space without latent compression.
Stable Audio 3 has been released as a model family for variable-length audio generation and editing.
ElevenLabs' longform text-to-audio editor Studio is now open to free users as well.
Studio has added a new UI and voice controls, making long-form narration work faster.
Foley Control attaches only a small video cross-attention to a frozen T2A model to learn video synchronization.
Stability AI has partnered with Arm to unveil 'Stable Audio Open Small,' a lightweight audio generation model that can run on-device on smartphones and similar devices.
ARC post-training generates 12 seconds of 44.1kHz stereo audio in 75ms on an H100.
Stable Audio Open, an open-weight text-to-audio model trained on Creative Commons data, has been released.