Skip to content

Instigo5483/Checker-AI

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Checker AI

A multimodal AI content detection pipeline that analyses audio, video, and text to determine whether content was generated by an AI or created by a human.

How it works

Checker AI runs three independent analysis modules in parallel and combines their scores using a weighted confidence matrix:

Module Weight What it checks
Audio 45% Voice cloning, synthetic pitch, unnatural silence patterns
Visual 35% Deepfake artifacts, spatial anomalies, generative blending
Text 20% Sentence burstiness, LLM filler phrases, lexical diversity

The final result is a single prediction with a percentage score.

Requirements

  • Node.js 18+
  • FFmpeg installed on your system (sudo apt install ffmpeg / brew install ffmpeg)

Installation

git clone https://github.com/your-username/checker-ai.git
cd checker-ai
npm install

Configuration

Create a .env file in the project root:

GEMINI_API_KEY=your_gemini_api_key_here
ELEVENLABS_API_KEY=your_elevenlabs_api_key_here   # optional
AUDIO_CLASSIFY_ENDPOINT=http://localhost:8000/classify-audio  # optional

Get your free Gemini API key at aistudio.google.com.

Never commit your .env file. It is already listed in .gitignore.

Usage

Analyse a video file:

node pipeline.js --file ./video.mp4

Analyse text:

node pipeline.js --text "Paste your text here"

Analyse a video and its transcript together:

node pipeline.js --file ./video.mp4 --text "The transcript of the video"

Get raw JSON output (for integrations):

node pipeline.js --text "Some text" --json

Example output

┌─────────────────────────────────────────┐
│         CONTENT ANALYSIS RESULT         │
├─────────────────────────────────────────┤
│ Prediction: [ AI ]  Very Likely AI      │
│ AI Score:   ████████░░  78% AI          │
├─────────────────────────────────────────┤
│ Checked:    Audio, Video, Text          │
└─────────────────────────────────────────┘

What we found:
  • Voice pitch is unnaturally consistent
  • Facial warping patterns associated with deepfakes
  • Writing style closely matches AI-generated text

Prediction scale

Score Verdict
85 – 100% Almost Certainly AI
65 – 84% Very Likely AI
50 – 64% Likely AI
35 – 49% Likely Human
15 – 34% Very Likely Human
0 – 14% Almost Certainly Human

Offline mode

All modules fall back to local heuristics when no API key or endpoint is available, so the pipeline always produces a result even without credentials.

License

MIT — see LICENSE

About

Multimodal AI content detection pipeline — analyses audio, video, and text to predict whether content was AI-generated or human-made.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors