Skip to main content
ToolPotion
AI Advisor
Submit a Tool (Free)

VeriSpoof

AI AppsAI Content DetectorsDetecting AI-generated images#11Free (Open-Weight) · Windows, macOS, Linux

VeriSpoof is an audio language model designed for speech deepfake forensics. It detects deepfakes, verifies their source, describes channel characteristics, and explains its decisions with verifiable lines. Achieving a 2.14% pooled EER on Speech-DF-Arena, it ranks first among open-weight detectors, offering a unified solution for comprehensive audio analysis and deepfake identification.

Visit Website
Share
VeriSpoof screenshot
VeriSpoof screenshot

VeriSpoof is a pioneering audio language model developed for advanced speech deepfake forensics. It provides a comprehensive solution for determining whether speech is a deepfake, identifying the system that generated it, assessing if two recordings share a common source, analyzing channel effects, and explaining its conclusions in a transparent, verifiable manner. This single, unified audio LLM (Large Language Model) operates beyond simple real or fake classifications, offering detailed insights into the origin and manipulation of audio.

Read More

The model has demonstrated exceptional performance, achieving a 2.14% pooled Equal Error Rate (EER) across 14 Speech-DF-Arena sets, positioning it as the top-ranked open-weight detector. Its architecture is built around an audio LLM that processes recordings into utterance and frame tokens, which are then read by a MiniCPM5-2B model with LoRA. Unlike traditional systems, VeriSpoof does not rely on separate task heads; instead, every answer is a sentence whose likelihood directly serves as the score, allowing for flexible thresholding at any operating point.

VeriSpoof's grounding is a core strength, with each line of its rationale independently checked against waveform measurements, logged conditions, labeled spans, and generator metadata. This ensures that observations, channel status, localization of synthesized segments, and source profiles are rigorously validated. The system also incorporates counterfactual training, where decisions are trained to follow stated evidence, even when localization is intentionally reversed, ensuring robust and logically consistent reasoning.

Intended primarily for research in deepfake detection, source tracing, and explainable forensics, VeriSpoof provides a powerful tool for auditing audio verdicts. It is recommended that its scores be combined with other evidence and human review for final forensic decisions. The project includes both a Base and a Plus model, with VeriSpoof-Plus demonstrating superior performance across various evaluation metrics and datasets. The weights and code for VeriSpoof are released under a CC BY-NC 4.0 license, while its base models, MiniCPM5-2B and Qwen3-ASR-1.7B, operate under Apache-2.0.

  • CategoryAI Content Detectors
  • Pricing ModelFree (Open-Weight)
  • DeploymentLocal (Inference Package)
  • PlatformsWindows, macOS, Linux

  • Speech Deepfake Detection: Identifies whether speech is a deepfake.

  • Source Verification: Determines which system generated the deepfake.

  • Source Attribution: Ascertains if two recordings originate from the same generator.

  • Channel Description: Analyzes and describes the channel effects on audio.

  • Explainable Decisions: Provides short, verifiable lines explaining its conclusions.

  • Grounded Rationale: Each claim is checked against waveform measurements and dataset labels.

  • High Accuracy: Achieved 2.14% pooled EER on Speech-DF-Arena, ranking #1 among open-weight detectors.

  • Unified Audio LLM: One model handles all forensic questions without separate task heads.

  • Score-Based Answers: Answers are sentences whose likelihood serves as the score.

  • Counterfactual Testing: Allows replacing stated localization to re-evaluate decisions.

  • Offline Inference: Supports running real test recordings offline.

  • Open-Weight Model: Available for research and development.

  • Multilingual Captions: Film demonstrations include Chinese and English captions.

  • Research-Oriented: Designed for deepfake detection, source tracing, and explainable forensics research.

  • Auditable Verdicts: Four lines to a verdict that can be audited.

  1. Input Audio: Provide a single audio recording or a pair of recordings to the model.

  2. Process with LLM: The audio components convert the input into utterance and frame tokens for the LLM.

  3. Receive One-Step Answer: Obtain an immediate answer regarding deepfake status or source similarity.

  4. Review Grounded Rationale: Examine the detailed, line-by-line explanation for the model's decision.

  5. Verify Claims: Check each claim in the rationale against waveform measurements and dataset labels.

  6. Conduct Counterfactual Tests: Optionally, modify parameters like localization and re-run the model to observe decision changes.

  • Deepfake Detection Research
  • Audio Source Tracing
  • Explainable Forensics
  • Audio Channel Analysis
  • Synthetic Speech Analysis
  • Benchmarking Deepfake Detectors

VeriSpoof Reviews

Loading...

Popular AI Tools Like VeriSpoof

Resemble AI offers a comprehensive Generative AI security platform for enterprises. It provides multimodal deepfake detection across audio, image, and video, alongside secure…

AI Content ModerationFinance & Banking

Ranked #238 in AI Apps

View Tool

Offers a comprehensive Generative AI security platform for enterprises. It provides multimodal deepfake detection across audio, image, and video, alongside secure…Resemble AI offers a comprehensive Generative AI security platform for enterprises. It provides multimodal deepfake detection across audio, image, and video, alongside secure…

FeaturedAI Content ModerationFinance & Banking
Ranked #238 in AI Apps

Sensity AI provides a forensic-grade deepfake detection solution for videos, images, and audio. It offers multilayer analysis, cloud and on-premise deployment, and detailed…

AI Content Detectors

Ranked #8 for Detecting AI-generated images

View Tool

Provides a forensic-grade deepfake detection solution for videos, images, and audio. It offers multilayer analysis, cloud and on-premise deployment, and detailed…Sensity AI provides a forensic-grade deepfake detection solution for videos, images, and audio. It offers multilayer analysis, cloud and on-premise deployment, and detailed…

AI Content Detectors
Ranked #8 for Detecting AI-generated images

Detectify is a leading AI detection tool that analyzes text, images, and audio for authenticity. It safeguards against plagiarism and deepfakes, ensuring the originality of your…

AI Content Detectors
View Tool

Leading AI detection tool that analyzes text, images, and audio for authenticity. It safeguards against plagiarism and deepfakes, ensuring the originality of your…Detectify is a leading AI detection tool that analyzes text, images, and audio for authenticity. It safeguards against plagiarism and deepfakes, ensuring the originality of your…

AI Content Detectors
See the Top 250 AI Apps

DeepfakeDetection.io offers a free AI-powered tool for detecting deepfakes in images, videos, and voices. It provides fast and accurate authenticity verification, helping users…

AI Content DetectorsMedia & Entertainment

Ranked #85 for Journalists

View Tool

Offers a free AI-powered tool for detecting deepfakes in images, videos, and voices. It provides fast and accurate authenticity verification, helping users…DeepfakeDetection.io offers a free AI-powered tool for detecting deepfakes in images, videos, and voices. It provides fast and accurate authenticity verification, helping users…

AI Content DetectorsMedia & Entertainment
Ranked #85 for Journalists

TruthScan offers enterprise-level AI detection solutions to identify AI-generated text, images, voice, and deepfakes. Trusted by universities, corporations, and government…

AI Content DetectorsFinance & Banking

Ranked #9 for Detecting AI-generated images

View Tool

Offers enterprise-level AI detection solutions to identify AI-generated text, images, voice, and deepfakes. Trusted by universities, corporations, and government…TruthScan offers enterprise-level AI detection solutions to identify AI-generated text, images, voice, and deepfakes. Trusted by universities, corporations, and government…

AI Content DetectorsFinance & Banking
Ranked #9 for Detecting AI-generated images

Witness

AI Apps

Witness is a free AI tool for detecting deepfakes in images, videos, and voice. It offers a Chrome extension, web app, and mobile access, providing quick analysis with confidence…

Security & Privacy

Ranked #71 in Security & Privacy

View Tool

AI Apps

Free AI tool for detecting deepfakes in images, videos, and voice. It offers a Chrome extension, web app, and mobile access, providing quick analysis with confidence…Witness is a free AI tool for detecting deepfakes in images, videos, and voice. It offers a Chrome extension, web app, and mobile access, providing quick analysis with confidence…

Security & Privacy
Ranked #71 in Security & Privacy

AI Image Detector cross-checks four independent AI detection models under a published weighted-vote rule and reports a graded conclusion instead of a single made-up percentage. It…

AI Content DetectorsPublishing & Journalism
View Tool

Reality Defender provides robust deepfake detection solutions for enterprises, platforms, and institutions, enabling them to identify AI-generated and manipulated media in real…

AI Content DetectorsFinance & Banking

Ranked #4 for Detecting AI-generated images

View Tool

Provides robust deepfake detection solutions for enterprises, platforms, and institutions, enabling them to identify AI-generated and manipulated media in real…Reality Defender provides robust deepfake detection solutions for enterprises, platforms, and institutions, enabling them to identify AI-generated and manipulated media in real…

AI Content DetectorsFinance & Banking
Ranked #4 for Detecting AI-generated images
1 of 8