How tripathi0704/audioartifact works
AudioArtifact is a forensic audio application: a user submits recordings through a Streamlit dashboard, the FastAPI backend analyzes them into time-localized synthetic-speech results, and the dashboard presents evidence and investigation tools. The documented product also includes live screening, speaker matching, batch scans, history, AI assistance, and report generation. The graph reflects sampled backend calls and documented capabilities; several dashboard internals and some capability-specific routes were not shown, so those links are documented or left unverified rather than inferred as source-level calls.
Main entry points: main.py Forensic API · app.py Forensic dashboard · ai_copilot.py Forensic AI · feature_extraction.py Training features
Components 22
Forensic experience
- Forensic dashboard
frontend/app.py - Single scan
frontend/app.py - Live mic test
frontend/app.py - Batch scanner
frontend/app.py - Speaker matcher
frontend/app.py - Timeline results
frontend/app.py
Audio analysis
- Forensic API
backend/main.py - Speech detection
backend/vad_utils.py - WavLM embeddings
backend/main.py - Deepfake scoring
backend/main.py - Voice comparison
backend/main.py - Training features
feature_extraction.py - Model training
train_model.py
Evidence and records
- Acoustic evidence
backend/forensic_utils.py - History service
backend/main.py - Scan history
backend/db.py - Audit certificate
backend/forensic_utils.py - FIR petition PDF
backend/forensic_utils.py
AI intelligence
- Copilot interface
frontend/app.py - Forensic AI
backend/ai_copilot.py
Other components
- Investigator
- Google Gemini
Connections 25
- Investigator → Forensic dashboard: uses
README.md - Forensic dashboard → Single scan: starts scan
README.md - Forensic dashboard → Live mic test: records audio
README.md - Forensic dashboard → Batch scanner: scans files
README.md - Forensic dashboard → Speaker matcher: compares voices
README.md - Single scan → Forensic API: submits audio
frontend/app.py - Forensic API → Speech detection: filters speech
backend/main.py - Forensic API → WavLM embeddings: extracts embeddings
backend/main.py - Forensic API → Deepfake scoring: scores windows
backend/main.py - Forensic API → Acoustic evidence: builds evidence
backend/main.py - Deepfake scoring → Timeline results: returns probabilities
frontend/app.py - Forensic API → Voice comparison: compares recordings
backend/main.py - Speaker matcher → Forensic API: requests match
frontend/app.py - Forensic API → History service: serves history
backend/main.py - History service → Scan history: reads records
backend/main.py - History service → Scan history: saves scans
backend/main.py - Forensic API → Audit certificate: generates certificate
backend/main.py - Investigator → Copilot interface: asks questions
README.md - Copilot interface → Forensic AI: sends context
frontend/app.py - Forensic AI → Google Gemini: requests analysis
backend/ai_copilot.py - Forensic API → Forensic AI: routes AI requests
backend/main.py - Forensic dashboard → FIR petition PDF: downloads petition
frontend/app.py - Training features → Speech detection: filters speech
feature_extraction.py - Training features → WavLM embeddings: extracts embeddings
- Model training → Deepfake scoring: produces detector