Quick Start

Submit media to Resemble Detect and retrieve an authenticity report through the API.

Set Up Your Environment

1. Create a Resemble account if you have not already and enable Deepfake Detection access.
2. Generate an API key from the Account → API page.
3. Set your API key and the path to a local audio, image, or video file smaller than 150 MB:

export RESEMBLE_API_KEY="YOUR_API_KEY"
export MEDIA_PATH="/path/to/media.mp4"

Submit Your First Detection

Upload the file as multipart/form-data:

curl --silent --show-error --fail-with-body \
  --request POST 'https://app.resemble.ai/api/v2/detect' \
  -H "Authorization: Bearer ${RESEMBLE_API_KEY}" \
  -F "file=@${MEDIA_PATH}"

The request starts an asynchronous analysis. Save the UUID from item.uuid in the response, then retrieve the detection:

export DETECT_UUID="UUID_FROM_THE_RESPONSE"
curl --silent --show-error --fail-with-body \
  "https://app.resemble.ai/api/v2/detect/${DETECT_UUID}" \
  -H "Authorization: Bearer ${RESEMBLE_API_KEY}"

Wait until item.status is completed before reading the verdict. A failed status means the analysis did not finish successfully. Audio results appear in item.metrics, image results in item.image_metrics, and video results can include both audio and visual findings.

For polling examples and a guide to interpreting results, follow Detect Your First Deepfake.

Next Steps

• Authentication: learn how API keys work across the platform.
• Detect Agents: investigate media, identity, and evidence with managed workflows.
• Streaming Audio Detection: analyze live audio over a WebSocket.
• API Reference: review the detection request and response schemas.

If you run into issues, email support@resemble.ai and include request IDs, timestamps, and sample payloads when possible.