Introducing AudioCraft: Meta AI's Innovative Generative AI for High-Quality Audio & Music
Today Meta AI is sharing details on AudioCraft, a new family of generative AI models built for generating high-quality, realistic audio & music from text. AudioCraft is a single code base that works for music, sound, compression & generation — all in the same place.
AudioCraft consists of three models: MusicGen, AudioGen & EnCodec.
Today's release includes an improved version of EnCodec enabling higher quality music generation with fewer artifacts + pretrained AudioGen models for generating environmental sounds and effects.
Meta AI is publicly releasing AudioCraft for research purposes and to further understanding of the technology. Responsible innovation can’t happen in isolation. Opening up our research and resulting models helps ensure that everyone has equal access.
AudioCraft is an important step forward in generative AI research. We believe the simple approach we developed for audio generation will have a meaningful impact on future technologies and how we interact with them — we can’t wait to see what people create with it.