Detect AI-generated voice, images, and video with a single API call. POST a file or URL and get back a verdict, confidence score, and the signals that drove it, average response under 2 seconds.
SOC 2 In Progress · 60s file purge · Keys hashed at rest
A single base URL and the same auth, response shape, and error semantics across every media type. Detect cloned voices, AI-generated images, face swaps, and lip-sync manipulation with one integration.
Upload via multipart, or pass us a public/signed URL. We'll fetch, scan, score, and purge, all within 60 seconds of the verdict.
| Parameter | Type | Description |
|---|---|---|
| media_url | string | HTTPS URL to the file. Either media_url OR multipart upload required.required* |
| media_type | enum | voice, image, or video. Inferred from MIME if omitted. |
| callback_url | string | Webhook for async jobs. We POST the verdict here when done. |
| strict_mode | boolean | Lower confidence threshold. Increases recall, may reduce precision. Default false. |
| retain | boolean | Keep the file for 30 days for audit. Default false (60s purge). |
Same call, same shape. Auth, retries, exponential backoff, file streaming, and webhook signature verification handled for you.
Built on the same infrastructure that handles thousands of detections every month for paying customers, banks, newsrooms, fact-check desks, and KYC teams.
Uptime SLO. Multi-region active-active. Status page at status.deepfakedetector.ai.
Median end-to-end latency for voice and image. Video scales with duration, ~1× realtime.
File purge after verdict by default. SOC 2 In Progress. retain=true for 30-day audit holds.
Rate limits scale by plan, from 60 to 300 requests per minute. Burst allowance for known clients.
Everything developers ask before they integrate.
A deepfake detection API lets you programmatically check whether media is AI-generated. Deepfake Detector's API analyzes voice, images, and video and returns a clear verdict with a confidence score, so you can automate media verification inside your own products and workflows.
Yes. Deepfake Detector detects face swaps, lip-sync manipulation, and fully AI-generated video, alongside voice and image detection, one AI video detection API with the same integration as every other media type.
A structured JSON response with a verdict, an AI confidence score, and a request ID for traceability, plus flagged segments for voice and video, and metadata for images.
Starter, Business, and Enterprise plans all include API access. Your monthly detections are shared between the web app and the API, so you can use them wherever your workflow lives.
Every request is authenticated with a Bearer API key. Keys are hashed at rest and shown only once at creation, and every call returns a request ID for auditing.
Yes. Deepfake Detector works as a synthetic media detection API and media forensics API, one API family for detecting AI-generated content across voice, image, and video.
Free tier includes 50 detections/month in the web app, no card required. API access starts on the Starter plan, with usage shared across the web app and API.