Skip to content

Kling Video

POST/v1/run

Kling Video Video To Audio by KwaiVGI - advanced AI model for video-to-audio. Delivers high-quality results with fast inference, suitable for both creative and production workflows.

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 kwaivgi/kling-video/video-to-audio.

Default: kwaivgi/kling-video/video-to-audio

Optional<string>video

The video URL to extract audio from. Only .mp4/.mov formats are supported. File size does not exceed 100MB. Video duration between 3.0s and 20.0s.

Optional<string>background_music_prompt

Background music prompt. Cannot exceed 200 characters.

Default: intense car race

Optional<boolean>asmr_mode

Enable ASMR mode. This mode enhances detailed sound effects and is suitable for highly immersive content scenarios.

Default: false

Optional<string>sound_effect_prompt

Sound effect prompt. Cannot exceed 200 characters.

Default: Car tires screech as they accelerate in a drag race

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: video-to-audio

stringexecution_moderequired

Execution mode declared by the model registry.

Default: async