Metamask
Wallet connect
Model input
model_version
Model to use for generation. If set to 'encode-decode', the audio specified via 'input_audio' will simply be encoded and then decoded.
prompt
A description of the music you want to generate.

input_audio
An audio file that will influence the generated music. If `continuation` is `True`, the generated music will be a continuation of the audio file. Otherwise, the generated music will mimic the audio file's melody.
duration
Duration of the generated audio in seconds. (maximum: 30)
If `True`, generated music will continue `melody`. Otherwise, generated music will mimic `audio_input`'s melody.
continuation_start
Start time of the audio file to use for continuation.
continuation_end
End time of the audio file to use for continuation. If -1 or None, will default to the end of the audio clip.
normalization_strategy
Strategy for normalizing audio.
top_k
Reduces sampling to the k most likely tokens.
top_p
Reduces sampling to tokens with cumulative probability of p. When set to `0` (default), top_k sampling is used.
temperature
Controls the 'conservativeness' of the sampling process. Higher temperature means more diversity.
classifier_free_guidance
Increases the influence of inputs on the output. Higher values produce lower-varience outputs that adhere more closely to inputs.
seed
Random seed. Leave blank to randomize the seed
Audio generation

music-forge

MusicGen generates new music based on text prompts and audio files, allowing for much more efficient creation of high-quality samples. MusicGen's developers conducted a comprehensive empirical study to demonstrate the superiority of the proposed method compared to existing methods using standard text-to-music benchmarks.

1.1k
25,000
Model result
Download