> ## Documentation Index
> Fetch the complete documentation index at: https://omnicron.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Music Generation

> Music Generation using the **meta/musicgen** AI Model.

### Query

<ParamField query="model" type="string" default="meta/musicgen" required>
  The model to be used;
</ParamField>

### Body

<ParamField body="prompt" type="string" required>
  A description of the music you want to generate.
</ParamField>

<ParamField body="model_version" type="string" default="stereo-melody-large">
  Model to use for generation
</ParamField>

<ParamField body="input_audio" type="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.
</ParamField>

<ParamField body="duration" type="int" default="8">
  Duration of the generated audio in seconds.
</ParamField>

<ParamField body="continuation" type="bool" default="False">
  If `True`, generated music will continue from `input_audio`. Otherwise, generated music will mimic `input_audio`'s melody.
</ParamField>

<ParamField body="continuation_start" type="int" default="0">
  Start time of the audio file to use for continuation.
</ParamField>

<ParamField body="continuation_end" type="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.
</ParamField>

<ParamField body="multi_band_diffusion" type="boolean" default="False">
  If `True`, the EnCodec tokens will be decoded with MultiBand Diffusion. Only works with non-stereo models.
</ParamField>

<ParamField body="normalization_strategy" type="string" default="peak">
  Strategy for normalizing audio.
</ParamField>

<ParamField body="top_k" type="int" default="250">
  Reduces sampling to the k most likely tokens.
</ParamField>

<ParamField body="top_p" type="float" default="0.0">
  Reduces sampling to tokens with cumulative probability of p. When set to `0` (default), top\_k sampling is used.
</ParamField>

<ParamField body="temperature" type="float" default="1.0">
  Controls the 'conservativeness' of the sampling process. Higher temperature means more diversity.
</ParamField>

<ParamField body="classifier_free_guidance" type="int" default="3">
  Increases the influence of inputs on the output. Higher values produce lower-varience outputs that adhere more closely to inputs.
</ParamField>

<ParamField body="output_format" type="string" default="mp3">
  Output format for generated audio.
</ParamField>