> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.resemble.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.resemble.ai/_mcp/server.

# Quick Start

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

## Set Up Your Environment

1. [Create a Resemble account](https://app.resemble.ai/users/sign_up) if you have not already and enable Deepfake Detection access.
2. Generate an API key from the [Account → API](https://app.resemble.ai/hub/api) page.
3. Set your API key and the path to a local audio, image, or video file smaller than 150 MB:

```bash
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`:

```bash
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:

```bash
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](/guides/detect/first-detection).

## Next Steps

* [Authentication](/getting-started/authentication): learn how API keys work across the platform.
* [Detect Agents](/detect/agents): investigate media, identity, and evidence with managed workflows.
* [Streaming Audio Detection](/guides/detect/streaming-audio): analyze live audio over a WebSocket.
* [API Reference](/api-reference/deepfake-detection/list-detections): review the detection request and response schemas.

If you run into issues, email [support@resemble.ai](mailto:support@resemble.ai) and include request IDs, timestamps, and sample payloads when possible.