The /sad-talker API endpoint triggers the sad-talker workflow. This API turns your photos into talking videos using the Aicado AI platform.

Insert line aboveInsert line belowDelete

This API endpoint is accessed using the POST method.

When you make a request to this endpoint, you should include the following query parameters:

<aside> 💡

Go to this page to find out how to get the Access Token.

</aside>

Body Params

Name Type Required? Description
source_image_url string Required URL of the source image
driven_audio_url string Optional URL of the driven audio
pose_style integer Optional The style of the pose
face_model_resolution number Optional The resolution of the face model Default value: "256"

Possible values: "256", "512" | | expression_scale | number | Optional | The scale of the expression Default value: 1 | | face_enhancer | string | Optional | The type of face enhancer to use

Possible values: "gfpgan" | | still_mode | boolean | Optional | Whether to use still mode. Fewer head motion, works with preprocess ‘full’. | | preprocess | string | Optional | The type of preprocessing to use Default value: "crop"

Possible values: "crop", "extcrop", "resize", "full", "extfull" | | response_webhook_url | string | Optional | The webhook URL to receive response updates. |

Responses

Code Examples