Voice Clones
Identify cloned voices from AI models like ElevenLabs, Play.ht, and custom voice cloning systems
AI voice and audio check
AI Voice and Clone Detector
Upload MP3 or WAV speech to check for voice cloning, synthetic speech, TTS, and audio deepfake signals. Review probability with audio-specific evidence.
What We Detect
Comprehensive voice cloning and synthetic audio detection
TTS Detection
Detect text-to-speech generation from major TTS providers and open-source models
Voice Conversion
Identify voice conversion and voice changer tools
Synthetic Speech
Detect fully synthetic AI-generated speech across multiple languages
Deepfake Audio
Identify audio deepfakes and synthetic impersonations
Signal Analysis
Analyze spectral patterns, timing artifacts, and vocal characteristics
Explainable Evidence
Understand exactly why audio was flagged
Evidence Types
- Timestamp-level confidence scores
- Spectral analysis with anomaly detection
- Vocal characteristic comparison
- Timing and prosody signal analysis
Operational Guidance
- Processing time depends on clip length, format, and encoding
- Async workflows are available for longer audio
- Review confidence together with spectral and prosody evidence
Limitations & Best Practices
Understanding model constraints for optimal results
False Positive Risk
Low-quality audio, strong compression, or background noise may increase false positives.
Adversarial Attacks
Voice anonymization and anti-forensic techniques may reduce detection accuracy.
Generalization Bounds
Performance varies across languages and TTS systems. Evaluate representative speakers, codecs, noise levels, and generators.
API Integration
Get started in minutes with our unified API
curl -X POST https://app.zerotrue.app/api/v1/check \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"input": {
"type": "audio",
"value": "https://example.com/audio.mp3"
},
"is_private_scan": true,
"is_deep_scan": false,
"idempotency_key": "req-123"
}'Frequently Asked Questions
What audio formats are supported?
The free web checker accepts MP3 and WAV files up to 10 MB. Confirm current API formats and limits for production workflows.
How fast is audio detection?
Processing time depends on clip length, format, encoding quality, and scan mode.
Can you detect all TTS systems?
No. New and unfamiliar TTS systems can produce different signals, so coverage should be tested with representative samples.
Does it work on all languages?
Language and speaker characteristics can change detector behavior. Test every required language before relying on the result.
Is my audio data stored?
Retention can depend on the plan and scan mode. Confirm current retention and deletion requirements before submitting sensitive audio.