Inputs
Note: The
audio parameter is optional. If provided, its duration must be between 1.5 and 60 seconds. If omitted, the model will automatically generate audio.
Outputs
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub
Source fingerprint (SHA-256):
1eb775421209047ad06ffc210c6588c64fd39a8828a69d6fcc2b79360df311e3