9🌍MusicHub - Text to Music Stream Generator

Facebook MusicGen-Small Model - Generate and stream music with model https://huggingface.co/facebook/musicgen-small

Prompt

Audio length in seconds

10 30

Streaming interval in seconds

Lower = shorter chunks, lower latency, more codec steps

0.5 2.5

Seed for random generations

0 10

Generated Music

Examples

Prompt	Audio length in seconds	Streaming interval in seconds	Seed for random generations

Pages:

How It Works:

MusicGen is an auto-regressive transformer-based model, meaning generates audio codes (tokens) in a causal fashion. At each decoding step, the model generates a new set of audio codes, conditional on the text input and all previous audio codes. From the frame rate of the EnCodec model used to decode the generated codes to audio waveform.