domains / families / media / audiocraft

audiocraft

separate

PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text descriptions, create sound effects, or perform melody-conditioned music generation.

When to use

• Need to generate music from text descriptions
• Creating sound effects and environmental audio
• Building music generation applications
• Need melody-conditioned music generation
• Want stereo audio output
• Require controllable music generation with style transfer
• **MusicGen**: Text-to-music generation with melody conditioning
• **AudioGen**: Text-to-sound effects generation

When not to use

• longer commercial music generation
• text-to-speech with music/sound effects
• spectogram-based music generation
• raw audio generation with lyrics

Skill page

Source