Detectif.ai

We ranked #1 in audio Deepfake detection benchmarks. While being bootstrapped. Got our first funding since. We're on the way to build the trust layer of the internet. Mark this post.

@tarini_axory @ChristinaG325 @sdianahu @ycombinator @maxkolysh

YC’s RFS this time highlights exactly what we’ve been doing at @DetectifAI Last time we spoke to the partners (@ChristinaG325 @sdianahu) but couldn’t get in past that (Also we have rev-maxxed since then) any @ycombinator alums thoughts on our application, any advice is great

@tarini_axory @ChristinaG325 @sdianahu @ycombinator 🫆

A phone call used to mean trust. Now it could be AI. @DetectifAI is building the next layer of cybersecurity for the AI era Not another chatbot Not another AI wrapper Foundational models built to detect audio deepfakes It started with something personal. Tarini's grandfather lost thousands of dollars to a simple deepfake. That moment became the reason to build. @tarini_axory had already been in machine learning since grade six Nearly a decade studying how AI works She saw where the technology was headed - and what was missing Fraud has existed for a very long time Cybersecurity has existed for a very long time Deepfake detection is that same discipline extended into the AI world. Today, DetectifAI serves clients across banking, finance, security, telecoms, and OEMs An API that integrates into existing enterprise infrastructure And on mobile, it goes even deeper - into the OEM layer itself. Which makes the vision tangible. You answer a call. Your phone gives you a rolling update on whether that voice is likely AI or a real human Detection during the call. Not after the money is gone. The scale comes from where it's deployed. A single OEM integration can unlock protection for millions of people. And deepfake detection is only the first step. The larger vision is an anti-fraud landscape that helps people navigate scam calls, robocalls, and anything that falls under the purview of fraud. The next generation of AI companies won't just build intelligence They'll build trust 🎙️ @tarini_axory, Founder & CEO, @DetectifAI on @Fondocom @thestartpod Full ep: fondo.ai/4fepl6g

@tarini_axory 🫆

Fullhouse v1 V2 coming soon;) @DetectifAI x Gensync x Vantalabs

@tarini_axory 🫆

We're hosting a lil something for only the best people in town 😉 (Link in the first comment)

@aigrantsindia @tarini_axory @aiweekendsxyz @innercircle_so @jarvislabsai @whycshow @Detectif_ai 🌕

.@tarini_axory missed our with $5k in GPU email 👀 Can someone let her know :D PS: We are sending out more emails tonight✉️ Thx to friends @aiweekendsxyz @innercircle_so @jarvislabsai for picking them @whycshow 🎭 @Detectif_ai is building foundational audio deepfake detection

RT @tarini_axory: I turned down a Nvidia job offer to bet on this... ...generative audio has a compliance problem coming. Regulators are c…

Our audio deepfake detection: AUC 0.96. EER 1.97%. fully bootstrapped. every competitor we beat has raised millions. @JoshConstine and Manohar Kamath came in as our first investors shortly after we published. spoke to @Analyticsindiam today about how we got here - full interview in comments. round is open. 20% allocated. @DetectifAI

@brycent just covered @DetectifAI I gave him 10 mins. he got it. 🧵

We just benchmarked every major audio deepfake detection baseline model Here's how they ranked overall: 🥇 @DetectifAI™ v2 : 80.6 🥈 RawNet2 : 74.3 🥉 DetectifAI™ v1 : 60.7 4. Wav2Vec2 : 57.5 5. WavLM : 56.0 6. 6. Siamese : 24.5

This was the first version of @Detectif_AI™. Tested on ASVspoof 2019 LA. First ever benchmarking. Since then, we've changed, grown and learnt a lot. Lot more coming soon. Stay tuned.

Catch us @Detectif_ai tomorrow at @fdotinc - let's discuss your voice authentication needs!

introducing detectif(dot)ai Protect yourself and your family from deepfake scams instantly know if a call is actually from your loved ones

DetectifAI is now backed by the ElevenLabs Grants program. This support helps us accelerate work on detecting AI-generated and manipulated media, starting with audio deepfakes. More soon.

Continuing to expand pilots with media and cybersecurity teams as synthetic media and AIGC fraud become critical infrastructure risks.

Axory AI builds our own proprietary multimodal detection models for video, audio, images, and documents. No generic LLM detectors. Fully explainable, audit-ready, and compliance aligned.

Grateful to receive First Position at the IIC Regional Innovation Exhibition 2025. Recognized by: @AICTE_INDIA @EduMinOfIndia 's Institutions Innovation Council Centre for Technology Innovation & Entrepreneurship