Skip to content

Stable Audio Open

POST/v1/run

Stable Audio Open is stability-ai's AI audio generation model. Produce high-quality music tracks, sound effects, and audio landscapes from natural language prompts.

Request body

Submit an async generation request. The model field selects the model; other fields are model-specific input parameters.

stringmodelrequired

Model identifier. Set to stability-ai/stable-audio/open.

Default: stability-ai/stable-audio/open

stringpromptrequired

The prompt to generate audio from

Optional<integer>seconds_start

The start point of the audio clip to generate

Range: 0 to 47

Default: 0

Optional<integer>seconds_total

The duration of the audio clip to generate

Range: 0 to 47

Default: 30

Optional<integer>steps

The number of steps to denoise the audio for

Range: 2 to 1000

Default: 100

Response Schema

The submit endpoint returns an accepted generation task. Poll the result endpoint with the returned id for terminal outputs or errors.

Optional<string>error

Error message if the task failed. Empty on success.

stringidrequired

Unique identifier for the generation task.

Optional<string>model

Model ID used for the prediction.

Optional<array>outputs

Array of generated content. Empty when status is not completed.

stringstatusrequired

Status of the task: pending, running, completed, failed, or timeout.

Allowed values: pending, running, completed, failed, timeout

Model capabilities

array<string>capability_tagsrequired

Capabilities declared by the model registry.

Default: text-to-audio

stringexecution_moderequired

Execution mode declared by the model registry.

Default: async