audiocraft-audio-generation

Load a pretrained model with MusicGen.get_pretrained('facebook/musicgen-small'), set generation parameters like duration and temperature, then call model.generate() with a list of text descriptions. Save the output tensor as a WAV file at 32kHz using torchaudio.

MusicGen generates music from text descriptions and supports melody conditioning and stereo output at 32kHz. AudioGen generates environmental sounds and sound effects from text at 16kHz. Both are part of Meta's AudioCraft library.

Yes, MusicGen is available in Transformers via MusicgenForConditionalGeneration and AutoProcessor. Note that parameter names differ: use guidance_scale instead of cfg_coef and max_new_tokens instead of duration.

MusicGen-small needs about 4GB VRAM in FP32 or 2GB in FP16, medium needs 8GB/4GB, and large needs 16GB/8GB. For limited memory, use the small model, reduce duration, or enable half precision.

Silent output usually requires normalizing the audio amplitude. Poor quality improves with a larger model, higher cfg_coef for text adherence, lower temperature, and more specific prompts describing genre, instruments, and tempo.

MusicGen typically generates up to 30 seconds of audio per call and cannot produce vocals or lyrics. For longer commercial music, consider Stable Audio; for speech with music, consider Bark.