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

haoheliu /audio-ldm:b61392ad

Input

*string
Shift + Return to add a new line

Text prompt from which to generate audio

string

Duration of the generated audio (in seconds). Higher duration may OOM.

Default: "5.0"

number

Guidance scale for the model. (Large scale -> better quality and relavancy to text; small scale -> better diversity)

Default: 2.5

integer

Random seed for the model (optional)

integer

Return the best of n different candidate audios

Default: 3

Output

No output yet! Press "Submit" to start a prediction.