Jabberjay 🦜

One API. Every state-of-the-art synthetic voice detector.

---

Why Jabberjay?

Synthetic voice detection is a fragmented landscape — state-of-the-art models are scattered across research repositories, each with its own dependencies, input formats, and output conventions. Jabberjay brings them all under one consistent Python API and CLI so you can detect AI-generated speech without wrestling with model internals.

• Eleven model families — ViT, AST, DFArena1B, Spectra0, SpectraAASIST, SpectraAASIST3, Wav2Vec2, HuBERT, WavLM, RawNet2, and a classical baseline
• Unified output — every model returns the same DetectionResult with label, confidence, and scores
• Zero boilerplate — pass a file path, get a verdict; models are downloaded and cached automatically
• Flexible — use strings for quick experiments, enums for IDE autocomplete, or pre-load audio to run multiple models on the same clip

$ jabberjay interview.wav
Bonafide ✔️ (94.1% confidence, model=VIT)

$ jabberjay suspicious.wav -m HuBERT
Spoof ❌ (97.8% confidence, model=HuBERT)

---

Installation

pip install jabberjay

Requires Python ≥ 3.12. Models are downloaded from Hugging Face Hub on first use and cached locally.

---

Quickstart

from Jabberjay import Jabberjay

jj = Jabberjay()
result = jj.detect("audio.wav")

print(result)              # Bonafide ✔️ (94.1% confidence, model=VIT)
print(result.label)        # "Bonafide"
print(result.is_bonafide)  # True
print(result.confidence)   # 0.941

---

Models

Vision Transformer (ViT)

Model	Dataset	Visualisation
MattyB95/VIT-ASVspoof2019-ConstantQ-Synthetic-Voice-Detection	ASVspoof2019	ConstantQ
MattyB95/VIT-ASVspoof2019-Mel_Spectrogram-Synthetic-Voice-Detection	ASVspoof2019	MelSpectrogram
MattyB95/VIT-ASVspoof2019-MFCC-Synthetic-Voice-Detection	ASVspoof2019	MFCC
MattyB95/VIT-ASVspoof5-ConstantQ-Synthetic-Voice-Detection	ASVspoof5	ConstantQ
MattyB95/VIT-ASVspoof5-Mel_Spectrogram-Synthetic-Voice-Detection	ASVspoof5	MelSpectrogram
MattyB95/VIT-ASVspoof5-MFCC-Synthetic-Voice-Detection	ASVspoof5	MFCC
MattyB95/VIT-VoxCelebSpoof-ConstantQ-Synthetic-Voice-Detection	VoxCelebSpoof	ConstantQ
MattyB95/VIT-VoxCelebSpoof-Mel_Spectrogram-Synthetic-Voice-Detection	VoxCelebSpoof	MelSpectrogram
MattyB95/VIT-VoxCelebSpoof-MFCC-Synthetic-Voice-Detection	VoxCelebSpoof	MFCC

Audio Spectrogram Transformer (AST)

Model	Dataset
MattyB95/AST-ASVspoof2019-Synthetic-Voice-Detection	ASVspoof2019
MattyB95/AST-ASVspoof5-Synthetic-Voice-Detection	ASVspoof5
MattyB95/AST-VoxCelebSpoof-Synthetic-Voice-Detection	VoxCelebSpoof

This is the beginning of the README. Read the rest at the original. Read the full README ↗