Detect Deepfake

Submit a media file for deepfake detection.

HTTP Request

POST https://app.resemble.ai/api/v2/detect

Request Behaviour

By default, the API responds asynchronously, meaning it will return immediately with the below response while processing continues in the background. Results are then delivered via the callback URL or you can use the Get Detection Results endpoint to check the status of the request.

{
    "success": true,
    "item": {
        "uuid": "<uuid>",
        "metrics": {},
        "created_at": "<created_at>",
        "updated_at": "<updated_at>",
        "media_type": "<media_type>"
    }
}

To make the request synchronous and wait for the detection results, include the Prefer:wait header in the request.

Required Parameter

Parameter	Type	Description
url	String*	The publicly accessible URL of the media file to be analyzed for deepfake detection. The media file should be a valid format (wav, mp3, ogg, m4a, flac, mp4, mov, avi, wmv, jpg, jpeg, png, gif, webp).

Optional Parameters for All Media Types

Parameter	Type	Description
callback_url	String	A URL to send the results to when analysis is completed.
visualize	Boolean	Generate visualization of detection results.

Optional Parameters for Audio

Parameter	Type	Description
frame_length	Number	The length of the frames in seconds used for analysis. The default value is 2 seconds. You can adjust this value based on the characteristics of your audio data and the desired analysis granularity. The minimum value is 1 and the maximum value is 4.
start_region	Number	The region to start the analysis in. Value in seconds.
end_region	Number	The region to end the analysis in. Value in seconds.

Optional Parameters for Video

Parameter	Type	Description
frame_length	Number	The length of the frames in seconds used for analysis. The default value is 2 seconds. You can adjust this value based on the characteristics of your audio data and the desired analysis granularity. The minimum value is 1 and the maximum value is 4.
start_region	Number	The region to start the analysis in. Value in seconds.
end_region	Number	The region to end the analysis in. Value in seconds.
max_video_fps	Number	Maximum FPS for video. Video having higher FPS will be downsampled.
max_video_secs	Number	Maximum duration of video to process.

Callback URL

If you've provided a callback_url when submitting a media file, you will receive a POST request to the callback_url with the same payload as the HTTP Response.

HTTP Response

Response for Audio file

{
    "success": true,
    "item": {
        "uuid": "<uuid>",
        "metrics": {
            "image": "",
            "label": "<label>",
            "score": [],
            "certainty": "<certainty>",
            "aggregated_score": "<aggregated_score>"
        },
        "created_at": "<created_at>",
        "updated_at": "<updated_at>",
        "duration": "<duration>",
        "media_type": "audio"
    }
}

Response for Image file

{
    "success": true,
    "item": {
        "uuid": "<uuid>",
        "metrics": {},
        "created_at": "<created_at>",
        "updated_at": "<updated_at>",
        "url": "<url>",
        "duration": "<duration>",
        "media_type": "image",
        "image_metrics": {
            "type": "<type>",
            "image": "<image>",
            "label": "<label>",
            "score": "<score>",
            "children": [
                {
                    "type": "<type>",
                    "label": "<label>",
                    "description": "<description>"
                }
            ]
        }
    }
}

Response for Video file

{
    "success": true,
    "item": {
        "uuid": "<uuid>",
        "metrics": {
            "image": "<image>",
            "label": "<label>",
            "score": [],
            "certainty": "<certainty>",
            "aggregated_score": "<aggregated_score>"
        },
        "created_at": "<created_at>",
        "updated_at": "<updated_at>",
        "duration": "<duration>",
        "media_type": "<media_type>",
        "video_metrics": {
            "image": "<image>",
            "label": "<label>",
            "score": "<score>",
            "children": [
                {
                    "type": "<type>",
                    "score": "<score>",
                    "children": [
                        {
                            "type": "<type>",
                            "score": "<score>",
                            "children": [
                                {
                                    "type": "<type>",
                                    "score": "<score>",
                                    "certainty": "<certainty>",
                                    "posterior": "<posterior>",
                                    "conclusion": "<conclusion>",
                                    "patch_type": "<patch_type>"
                                }
                            ],
                            "certainty": "<certainty>",
                            "posterior": "<posterior>",
                            "conclusion": "<conclusion>"
                        }
                    ],
                    "certainty": "<certainty>",
                    "posterior": "<posterior>",
                    "conclusion": "<conclusion>"
                },
                {
                    "type": "<type>",
                    "score": "<score>",
                    "certainty": "<certainty>",
                    "posterior": "<posterior>",
                    "conclusion": "<conclusion>",
                    "violations": [],
                    "description": "<description>"
                }
            ],
            "treeview": "<treeview>",
            "certainty": "<certainty>",
            "posterior": "<posterior>"
        }
    }
}