infery
← All models

Stable Audio 2.5

stable-audio-25-audio-to-audio

Text to Speechby Stability AI

Generate high quality music and sound effects using Stable Audio 2.5 from StabilityAI

Details

Accepts
audio

Pricing

Price
25 cr / clip

Prices in credits (1 credit = $0.01).

Data schema

Input

FieldTypeDescription
seed
promptrequiredstringThe prompt to guide the audio generation
strengthnumberSometimes referred to as denoising, this parameter controls how much influence the `audio_url` parameter has on the generated audio. A value of 0 would yield audio that is identical to the input. A value of 1 would be as if you passed in no audio at all.
audio_urlrequiredstringThe audio clip to transform
sync_modebooleanIf `True`, the media will be returned as a data URI and the output data won't be available in the request history.
total_secondsThe duration of the audio clip to generate. If not provided, it will be set to the duration of the input audio.
guidance_scalenumberHow strictly the diffusion process adheres to the prompt text (higher values make your audio closer to your prompt).
num_inference_stepsintegerThe number of steps to denoise the audio for
mask_endintegerThe end point of the audio mask
mask_startintegerThe start point of the audio mask
seconds_totalThe duration of the audio clip to generate. If not provided, it will be set to the duration of the input audio.

Output

FieldTypeDescription
seedintegerThe random seed used for generation
audioThe generated audio clip