The startup develops a biometric authentication engine that utilizes voiceprint technology to recognize and authenticate users based on their unique voice signatures. This solution enables secure command authentication across various communication devices and web services, enhancing user verification for businesses.
Funding
$660K raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
Founders
Product
Problem
Traditional authentication methods relying on passwords or PINs can be cumbersome, easily forgotten, and vulnerable to social engineering or credential theft. As voice-enabled devices and services become more prevalent, there's a growing need to verify the identity of the speaker to prevent unauthorized access and fraud. The rise of sophisticated voice synthesis technologies and deepfakes further exacerbates these security concerns.
Solution
Whispeak provides a biometric authentication engine that uses voiceprint technology to identify and authenticate users based on their unique voice signatures. The solution offers both voice biometric authentication and voice synthesis detection capabilities. For authentication, users enroll by recording their voice, which is then converted into a unique voiceprint. During authentication, the user's voice is compared against their enrolled voiceprint, providing a secure and frictionless way to verify identity. To combat the threat of deepfakes, Whispeak's voice synthesis detection technology analyzes audio to determine if it is genuine or artificially generated. This helps prevent identity theft and fraud attempts that leverage synthetic voices.
Target Audience
The primary target audience includes call centers, banks, insurance companies, automotive manufacturers, media outlets, and any organization that requires secure and convenient user authentication or needs to verify the authenticity of audio content.
Features
- Voice biometric authentication using proprietary voiceprint technology
- Voice synthesis detection to identify deepfake audio
- Enrollment process requiring only a short voice recording (max 12 seconds)
- Authentication process requiring only a few seconds of speech (max 3 seconds)
- Integration with existing authentication protocols via OIDC and SAML
- RESTful API for easy integration into various applications and platforms
- Deployment options: SaaS, on-premise, and embedded SDK
- GDPR compliance and adherence to CNIL recommendations for biometric data storage
- High authentication accuracy with a low false acceptance rate
- Multi-factor authentication support by combining voice biometrics with other factors