DuckDuckGoose DeepDetector vs Pella Research
DuckDuckGoose DeepDetector
duckduckgoose.aiPella Research
pellaresearch.comSide by side
| Figure | DuckDuckGoose DeepDetector | Pella Research |
|---|---|---|
| Price from | — | — |
| Free plan | — | — |
| Free trial | Yes | — |
| Open source | — | — |
| Web | Yes | Yes |
| API | Yes | Yes |
| Self-hosted | Yes | — |
| Plans published | 0 | 0 |
| Spec score · AI Deepfake Detection Tools | 8.1 (#7) | 7.2 (#16) |
| Free access | The site links to a free Phocus signup, and its technology page says it offers limited free trials; it does not state trial duration. | Pella states that accredited journalists and academics can receive a free API tier. |
| Headquarters | The maker's about page identifies the Netherlands as its founding location but does not specify a headquarters. | Amsterdam, Netherlands |
| Purpose | DeepDetector analyzes images and videos to detect AI-generated media, face swaps, and other manipulations. | Pella Research studies synthetic speech and builds models to detect it in real-world audio. |
In their own words
DuckDuckGoose DeepDetector
DuckDuckGoose DeepDetector analyzes images and videos for AI-generated media, face swaps and other manipulations, with web, API and self-hosted options. It is positioned for identity verification, KYC onboarding, insurance claims, border control and media forensics. Its forensic classifiers examine facial and temporal inconsistencies as well as GAN and diffusion fingerprints. Results include a manipulation heatmap, confidence score and forensic evidence for review. The company describes an API and SDK that can sit alongside existing KYC, document verification or liveness providers. Its documented API flow uploads a file through a presigned S3 URL, starts an analysis request and polls for the result. The maker says data can remain in the EU or the service can be deployed fully on-premise. For direct media checks, Phocus is a web platform for images, video and audio, with an exportable audit trail. DeepDetector is paid, with pricing on request.
Pella Research
Pella Research studies synthetic speech and builds models for detecting it in audio. Its research examines vocoder artifacts, spectral statistics, and prosodic cues. A browser demo accepts an uploaded or recorded voice clip and returns a verdict without signup; the site says audio is not stored. The REST detection API returns calibrated authenticity scores and per-segment analysis, with access reviewed after a request, typically within 24 hours. Pella offers the API to journalists, platforms, researchers, and institutions, and lists a free tier for accredited journalists and academics. Published evaluation sets track new voice-cloning systems with documented provenance and no train/test leakage. Pella says models are trained and tested with phone-line compression, background noise, and re-encoding. It reports pellav2 results of 95.82% accuracy, 0.959 F1, and 57 ms latency in the August 2026 Podonos benchmark, plus 93.6% accuracy on m4a files with errors leaning toward false positives. pellav2 is described as open weights under the MIT license.