The voice deepfake detector that holds up on real phone lines.
DeepBlocker Detect is the same telephony-tuned model that powers Real-Time Protection, available as a hosted API for fraud, KYC, and identity-verification platforms. Reproducible evaluation, published model card, ~1 s warm inference per call.
Who it's for
- Fraud-prevention platforms scoring inbound calls.
- KYC and identity-verification vendors validating live voice.
- Bank in-house anti-fraud teams adding a voice layer to existing rule engines.
- Telecoms operators offering deepfake-defence as a network service.
Inputs and outputs
| Input audio formats | G.711 µ-law / G.711 A-law / G.722 (8 kHz, mono or stereo) |
| Window length | 4 s |
| Output — fake_prob | float in [0, 1] |
| Output — band | REAL (≤ 0.50) · UNCERTAIN · FAKE (≥ 0.95) |
| Output — per-channel breakdown | For stereo (caller leg + assistant leg) |
Detection performance
| ElevenLabs deepfake mean confidence | 98.5% |
| Deepfake recall | 94.7% |
| False-alarm rate | 4.9% |
| Review-queue load | 0.9% |
| ROC AUC, locked Reporting set | ≥ 0.92 |
Held-out Reporting set, n ≈ 634, SHA-256 pinned, used exactly once. Per-source breakdown and known limitations (notably OpenAI Realtime / GPT-4o-voice) in the model card at /model-card.
Latency, throughput, deployment
- ~1 s warm inference per stereo call. ~17 s cold start.
- Hosted on serverless GPU. Scale-to-zero.
- Calibrated thresholds versioned via secrets — no silent threshold drift.
- Continuous evaluation hooks against production drift.
What the model is honest about
- OpenAI Realtime / GPT-4o-voice currently lands in UNCERTAIN, not FAKE. Documented; on the v6 roadmap.
- Miss rate 10.2% — most slip into UNCERTAIN, not REAL. Conservative by design.
- English only. FR / ES / DE on the v6 roadmap.
- TTS providers we did not train on (Bark, Coqui XTTS-v2, Vall-E, custom voice clones) are not measured.
Reproducibility
The base model (XLSR-Mamba-LA) is MIT-licensed and published with paper. Our fine-tune procedure, augmentation chain, training hyperparameters, and Reporting set SHA-256 are documented in the model card. Available under NDA for technical evaluation.
Commercial
Tiered per-call pricing with sandbox access for technical evaluation. Volume committed pricing for fraud and KYC platforms. Contact sales for a tailored quote and a sandbox key.