POST
v1
/
replicate
/
musicgeneration

​
Query

model
string
default: "meta/musicgen"required

The model to be used;

​
Body

prompt
string
required

A description of the music you want to generate.

model_version
string
default: "stereo-melody-large"

Model to use for generation

input_audio
file

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
int
default: "8"

Duration of the generated audio in seconds.

continuation
bool
default: "False"

If True, generated music will continue from input_audio. Otherwise, generated music will mimic input_audio’s melody.

continuation_start
int
default: "0"

Start time of the audio file to use for continuation.

continuation_end
int
default: "0"

End time of the audio file to use for continuation. If -1 or None, will default to the end of the audio clip.

multi_band_diffusion
boolean
default: "False"

If True, the EnCodec tokens will be decoded with MultiBand Diffusion. Only works with non-stereo models.

normalization_strategy
string
default: "peak"

Strategy for normalizing audio.

top_k
int
default: "250"

Reduces sampling to the k most likely tokens.

top_p
float
default: "0.0"

Reduces sampling to tokens with cumulative probability of p. When set to 0 (default), top_k sampling is used.

temperature
float
default: "1.0"

Controls the ‘conservativeness’ of the sampling process. Higher temperature means more diversity.

classifier_free_guidance
int
default: "3"

Increases the influence of inputs on the output. Higher values produce lower-varience outputs that adhere more closely to inputs.

output_format
string
default: "mp3"

Output format for generated audio.

Was this page helpful?

v1/replicate/musicgeneration