Deepfake fraud attempts surged 1,300% between 2024 and 2025 📈 The reason? Synthetic voice is cheap to generate. And most bank fraud stacks are architecturally blind to it. They're built around transaction data - what happened after the call. But the attack has moved. It's happening during the call. The urgency script. The spoofed voice. The social engineering that gets an agent to bypass verification before a single flag gets raised. A transcript won't catch that ❌ Rules won't catch that ❌ You need models that understand voice the way voice actually works - tone, cadence, stress, acoustic anomalies. Not just words. We wrote a practical breakdown of what real-time voice AI detection looks like in banking: where it plugs in, what it scores, and how it shifts intervention from post-wire to mid-call. (Link in caption) If you're building in this space, our API is open.

The most important thing we’re working on at @modulate_ai right now: Moving beyond narrow detection - toward systems that truly can understand risk in context. Real-world threats don’t show up in neat categories. They overlap, evolve, and look different in every conversation. So instead of building for one slice at a time, we’re focused on a unified layer of voice intelligence: one that interprets what’s actually happening, not just flags keywords. That shift is where this becomes genuinely useful👏

We’re @hackernoon Company of the Week 🏆 As CTO of @modulate_ai, moments like this are really about the team. Building Velma - a model that actually understands voice at scale - meant solving problems most teams avoid: data quality, architecture, and real-world accuracy in messy audio. A few signals of what that work has unlocked: 🏅 #1 on @huggingface Speech Arena (98.9% deepfake detection accuracy) 💰 25x better cost efficiency vs foundation models 💻 40M users protected from fraud, harassment, and abuse Proud of what we’ve built! 🛠️

I got deepfaked. Someone cloned my voice and used it in a simulated bank transaction - and I couldn’t tell it wasn’t me. That’s the part that sticks with you. What did catch it? Modulate's Velma flagged it with 99.5% confidence. The gap between what humans can detect and what’s now possible with AI is only getting wider. And we’re not going to out-train billion-dollar labs on instinct alone. We need technology that can meet that level - and defend against it in real time. That’s exactly what we’re building at @modulate_ai

Imagine your CEO’s voice calls your finance team… but it’s fake. Would they notice? Would you? Deepfakes aren’t a future risk - they’re happening right now.