Our Patented AI Voice "DNA" Signatures are minted and utilized for Human Authentication

Empowering communication with verified AI Voice DNA Signatures.
Protecting your unique voice frequencies is our priority. Always Listening.

State of the art Voice Authentication

Advanced Deepfake Detection

Seamless Integration for Enterprises

Unlock the Power of Voice Authentication and Deepfake Detection

In an increasingly digital world, trust and security are paramount. Voice authentication and deepfake detection offer groundbreaking solutions to protect your identity, safeguard sensitive data, and ensure the authenticity of your interactions.

Industry Specific Use Cases

Voice Factor Authentication (VFA)

Say goodbye to traditional authentication methods like fingerprints, Face ID, or passwords. Our technology leverages voice as a secure, convenient, and hands-free alternative. Whether in industrial environments or offices, employees can authenticate themselves quickly and efficiently with just their voice, reducing the risk of shared credentials or physical access cards being compromised.

Spoken OTP (One-Time Password)

No more typing or remembering codes from an SMS or email. With spoken OTP, users simply say their one-time password aloud, and our system verifies both their identity and the legitimacy of their voice. This innovation not only streamlines the authentication process but also detects and prevents deepfake attempts, ensuring secure transactions and access.

Register and Log In via Voice

Simplify onboarding and authentication with voice-based registration and login. Users no longer need to type long email addresses or create complicated passwords. Instead, their voice serves as both their username and password, making the process faster, more intuitive, and secure.

Password/Account Recovery

Forgot your password? No problem. With our voice-based account recovery, users can regain access to their accounts securely and quickly by verifying their voice. This eliminates the need for lengthy recovery forms, email confirmations, or identity verification questions, ensuring a seamless user experience.

VR/OCULUS and Vision Pro

Navigating virtual environments often makes traditional input methods cumbersome. Our technology allows users to access their apps and accounts on VR platforms like Oculus and Vision Pro using just their voice. This ensures effortless and secure authentication in immersive environments where keyboards and other tools are impractical.

Call Center Authentication and Deepfake Detection

Enhance the security of call centers with our dual functionality of voice authentication and deepfake prevention. Customers can verify their identity effortlessly through their voice, while our system actively monitors for any signs of deepfake attempts. This ensures both convenience and robust fraud protection for businesses handling sensitive information.

Unlock Doors With Voice Commands

Transform how users interact with their environment by enabling voice-activated access to devices and physical spaces. Whether unlocking doors, controlling smart home devices, or managing secure systems, our technology ensures that only authorized individuals have control, offering unparalleled convenience and security.

Automated Chatbots

Redefine customer interaction with voice authentication for chatbots. Instead of asking users for sensitive information like dates of birth, addresses, or pet names, our system verifies identities through voice analysis. This not only enhances security but also improves user trust and simplifies interactions, making chatbots more user-friendly and secure.

Deepfake Detection

Our revolutionary deepfake detection system identifies synthetic voices within seconds using a multi-judge approach. This cutting-edge technology analyzes a wide range of parameters and aspects across various AI generative platforms to detect and prevent all types of deepfake voices. By staying ahead of advancements in deepfake generation, we provide robust security and reliability for voice authentication and beyond.

Sign Documents via DocuVoice

Experience a groundbreaking way to sign documents with your voice. Our first-of-its-kind solution enables users to create legally binding voice signatures, eliminating the need for traditional hand-drawn signatures, keyboard-typed initials, or fingerprints. By securely linking your hand signature to your unique voice signature, we provide unparalleled protection for your documents and agreements. In an era where hackers can easily forge typed names or initials, this innovative technology ensures your identity remains secure.

OpenSesme

We’re excited to invite you to try our revolutionary Open Sesme app—the first of its kind! This groundbreaking app lets you register, log in, and recover your account using only your voice—no need to type a single letter on a keyboard.

With Open Sesme, you can:

Experience the future of authentication today-effortless, secure, and voice-first!

about us

Our Story

At Sound Genetics, Inc. (SGI), we’ve redefined the way sound is analyzed and understood. Our journey began over 20 years ago with a focus on phonemes—the smallest units of speech essential for reading. In 2018, we discovered a breakthrough opportunity to digitize phonemes, thanks to Anwar Almojarkesh, a brilliant acoustical engineer developing technology to classify tiny sounds. His expertise led us to file and secure two U.S. patents, establishing a foundation for our innovative approach.

Our proprietary technology doesn’t rely on standard voice recognition. Instead, we analyze sound by tracking frequency oscillations, transitions, and unique patterns—much like distinguishing between the nuanced effects of gunshots, doorbell chimes, or even glass breaking. This detailed analysis enables us to extract unprecedented insights from audio. Today, SGI offers state-of-the-art voice authentication (99%+ accurate) and deepfake detection tools.

Our flagship app, Open Sesme, is the world’s first platform allowing registration with voice alone, eliminating the need for keyboards. Our solutions are device-agnostic, seamlessly integrating into any platform globally.

We’re actively exploring use cases for our advanced audio analytics, voice biometrics, and security innovations, including voice signatures for documents and deepfake detectors to safeguard systems. Let’s discuss how we can collaborate to harness the power of sound.

The Team

Brad Diskin

Brad Diskin

CEO & Co-Founder

Previously CEO of UROK Learning – Nationwide education company, teaching non readers to read via Phoneme Assessment and structured phonological training

Anwar Almojarkesh

Anwar Almojarkesh

CTO & Co-Founder

Multi-decade entrepreneur at the forefront of sound analysis & technology • CEO & Founder Innovation Factory - a mobile phone-based sound recognition platform for alerts in your environment, such as sirens, alarms, etc. • Tasked by the UK Government to use public safety microphones to spot & stop graffiti in real time - a multi-billion-a-year problem in the UK. Built on a novel non-speech sound platform.

Business Advisors

John Whaley

John Whaley

Co-Founder Inception Studio

John Whaley is a three-time cybersecurity founder (Moka5, UnifyID, Redcoat AI) and the founder of Inception Studio, a nonprofit accelerator for AI-native founders. He is also an Adjunct Lecturer in the CS department at Stanford University. He received his PhD from Stanford and BS and MEng from MIT.

Mike Morris

Mike Morris

Co-Founder Inception Studio

Mike Morris, a Silicon Valley veteran with 25+ years of experience, founded Redcoat AI and Inception Studio. He contributed to VMware’s growth from startup to 20,000 employees and led engineering at Netcitadel and UnifyID, both acquired by major firms.

Patents

US PATENT

Systems And Methods For Pre-filtering Audio Content Based On Prominence Of Frequency Content – Us 11,735,202 B2 · Issued Aug 22, 2023

WIPO PATENT

Systems And Methods For Pre-filtering Audio Content Based On Prominence Of Frequency Content Pct/us2020/014559 · Issued Jul 30, 2020

US PATENT

SYSTEMS AND METHODS FOR PRE-FILTERING AUDIO CONTENT BASED ON PROMINENCE OF FREQUENCY CONTENT – 12,106,766 B2 · Issued Oct 01, 2024

contact us

Phone

+1 (619) 889-4961

Address

2261 Market Street STE 5782, San Francisco, CA 94114

Email

support@soundgenetics.com

Scroll to Top