You're looking at a specific version of this model. Jump to the model overview.

riffgen /auto-tune:3e08ac02

Input schema

The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.

Field Type Default value Description
audio_file
string
URL or path to the audio file to be pitch-corrected
autotune_style
None
balanced
Auto-tune style/intensity preset. Changing this will update the defaults for correction strength, adaptive, and smoothing, but you can override them below.
scale
None
closest
Musical key/scale to use for pitch correction. If set to 'closest', will use chromatic correction.
correction_strength
number
0.8
Strength of pitch correction (0.0 to 1.0). Defaults to the style preset, but you can override.
adaptive_strength
boolean
True
Whether to adapt correction strength based on voice confidence. Defaults to the style preset, but you can override.
smooth_transitions
boolean
True
Whether to smooth transitions between voiced/unvoiced segments. Defaults to the style preset, but you can override.
plot
boolean
False
Whether to generate a pitch correction visualization plot
output_format
None
wav
Output format for generated audio.

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema
{'format': 'uri', 'title': 'Output', 'type': 'string'}