Data Machina #249
Data Machina
Multiple generative AI music models and applications have emerged in the past year, including Facebook's MusicGen, Stability AI's Stable Audio 2.0, Google MusicFX, and Suno AI V3, enabling users to create music from text prompts. Stable Audio 2.0 generates full tracks up to three minutes in length at 44.1kHz stereo quality, while Suno V3 produces two-minute radio-quality music from text in seconds. These tools allow musicians, producers, and general users to create royalty-free music with varying levels of controllability and quality, with Udio being noted as particularly trending in the music generation community.
Why it matters
GenAI Music. MusicGen. MusicFX. Stable Audio 2. Suno V3. Udio. Rerank3 Model. Parler TTS. nanoLLaVA VL Model. Text2SQL DuckDB-NSQL-7B. aiXcoder-7B
