Sign in
latestOpenAPI 3.0.02026-07-248574216.0 KB

726b2a637ae8

Text2Audio

Text2Sound

The Text2Sound service helps generate an music/sound based on the prompt introduced as input by the user.

post/text2sound

Request body

promptstring required

The prompt for the music/sound generation.

durationnumber nullable

The duration for the generated audio in seconds Note these ranges from vendors: ElevenLabs: 0.5-22. Kling: 3-10. Auto if omitted.

loopboolean

Create looping audio. The usage of this param is not guarantteed as limited number of models do support this. (For example: Supported by ElevenLabs only.)

model'urn:air:elevenlabs:model:elevenlabs:elevenlabs-sound-effects-v2@1' | 'urn:air:kling:model:kling:kling-text-to-audio@1' nullable

Optionally choose a specific AI model to use for this audio generation. If not specified, a default model will be applied. Please note that the default model may change over time as Picsart continues to improve performance and accuracy. Any change to the default will be made only after thorough testing and validation to ensure it delivers better results. If you require consistent behavior or wish to evaluate different models on your own, we recommend explicitly setting this parameter.

Example request

{
  "duration": 3
}

Response

Accepted.

status'success' | 'error' | 'processing'
inference_idstring nullable