Tech riderRev. 21 Sept 2026

Pella Research

Ch 156.6of 20AI Deepfake Detection Tools

1Runs onAPI, Web
2Media typesaudio
3API accessYes
4Face analysisNo

4 lines stated Written from the maker's own pages: pellaresearch.com

Visit site Alternatives

Overview

Pella Research is ranked #15 of 20 in AI deepfake detection tools on Specifiction. It runs on API, Web.

Compared on AI deepfake detection tools

Free plan: Yespellaresearch.com
Media types: audiopellaresearch.com
API access: Yespellaresearch.com
Face analysis: Nopellaresearch.com

Facts

Product: Pella Research builds models to detect synthetic speech by analyzing vocoder artifacts, spectral statistics, and prosodic cues.pellaresearch.com · 7 Oct 2026
Research and benchmarks: It publishes evaluation sets that track new voice cloning systems, with documented provenance and no train/test leakage.pellaresearch.com · 7 Oct 2026
API: The detection API is a REST endpoint that returns calibrated authenticity scores and per-segment analysis, with access granted on request.pellaresearch.com · 7 Oct 2026
Live demo: The browser demo lets users upload or record a voice clip and receive a verdict without signup; the page says no audio is stored.pellaresearch.com · 7 Oct 2026
API audience: The API is offered to journalists, platforms, researchers, and institutions, and the page lists a free tier for accredited journalists and academics.pellaresearch.com · 7 Oct 2026
Access response: Pella says it reviews API requests and typically responds within 24 hours.pellaresearch.com · 7 Oct 2026
Benchmark result: Pella reports that pellav2 achieved 95.82% accuracy, a 0.959 F1 score, and 57 ms latency in the August 2026 Podonos benchmark.pellaresearch.com · 7 Oct 2026
Benchmark limitation: Pella reports 93.6% accuracy on m4a files and says its errors lean toward false positives.pellaresearch.com · 7 Oct 2026
Real-world conditions: Pella says its models are trained and tested with phone-line compression, background noise, and re-encoding.pellaresearch.com · 7 Oct 2026
Model availability: The site describes pellav2 as open weights under the MIT license and says the public checkpoint reproduces the submitted benchmark score.pellaresearch.com · 7 Oct 2026
Demo limitation: The live demo runs on free shared hardware, and its first request after a quiet period can take up to a minute to wake up.pellaresearch.com · 7 Oct 2026
Intended users: Pella describes its work as serving platforms, journalists, courts, and researchers investigating whether audio is synthetic.pellaresearch.com · 7 Oct 2026
Location: The site lists Amsterdam, Netherlands.pellaresearch.com · 7 Oct 2026
Purpose: Pella Research studies synthetic speech and builds models to detect it in real-world audio.pellaresearch.com · 7 Oct 2026
Research: Its research examines vocoder artifacts, spectral statistics, and prosodic cues left by speech synthesis.pellaresearch.com · 7 Oct 2026
Benchmarks: Pella says its evaluation sets track new voice cloning systems and use documented provenance with no train-test leakage.pellaresearch.com · 7 Oct 2026
Robustness: Pella says its models are trained and tested on audio affected by phone-line compression, background noise, and re-encoding.pellaresearch.com · 7 Oct 2026
Access and support: API access is reviewed on request for journalists, platforms, researchers, and institutions, with a typical response within 24 hours.pellaresearch.com · 7 Oct 2026
Free access: Pella states that accredited journalists and academics can receive a free API tier.pellaresearch.com · 7 Oct 2026
Known failure case: Pella reports 93.6% accuracy on m4a files in that benchmark and says its errors lean toward false positives.pellaresearch.com · 7 Oct 2026
License: The maker lists pellav2 as open weights under the MIT license.pellaresearch.com · 7 Oct 2026