Detect Your First Deepfake
Submit an audio, image, video, or PDF file to Resemble Detect, wait for the analysis to finish, and read the results. PDFs return a separate result for each analyzed image.
What You Will Build
This walkthrough uses the asynchronous API workflow:
- Submit a local media file.
- Save the detection UUID.
- Poll the detection until it reaches a terminal status.
- Read the result for the submitted media type.
Prerequisites
- A Resemble API token with Deepfake Detection access
- A local audio, image, video, or PDF file smaller than 150 MB
curlandjq
Set your API token and the path to your test file:
1. Submit the Media
Send the file as multipart/form-data:
The API returns immediately while the analysis runs. Save the detection UUID from the response:
Provide exactly one media source per request. In addition to a direct file upload, the API accepts a public url or a token from Secure Upload.
2. Wait for the Result
Poll the detection endpoint until the job is complete or has failed:
Print the completed response:
For production workloads, use a callback_url instead of polling continuously. For a synchronous audio, image, or video request, add the Prefer: wait header when submitting the detection. PDFs always run asynchronously.
3. Read the Verdict
The result fields depend on the media type:
For audio, print a compact summary:
For an image:
For a video, inspect both audio and visual findings. If the request used modality=audio or modality=video, the skipped result object is absent.
For a PDF, inspect the image map and skipped images.
A completed PDF can contain failed or skipped images, or zero analyzable images. Check these counts and the image results together. See the PDF result fields.
Use the returned label and supporting metrics together with your application context. Detection scores should inform a review workflow rather than act as the only basis for a consequential decision.
Troubleshooting
Extend the Workflow
- Use Secure Upload for private media or larger audio, image, and video files. PDFs have a 150 MB limit across all input methods.
- Enable Intelligence to generate a richer description of the content.
- Use Batch Detection when processing multiple audio, image, or video files. Submit each PDF separately.
- Review the complete Submit Detection Job and Get Detection Result contracts.
