Resemble AI Blog – Learn All about AI Voices
Proactive Detection Techniques for Watermarking Voice Cloning Output
Watermarking voice cloning output is replacing fragile detection. Learn how proactive signals verify AI audio at scale.
How to Authenticate an Audio Recording That Sounds Real
Wondering how to authenticate an audio recording? Learn the steps to verify audio evidence, detect tampering, and identify AI-generated speech.
More from the blog
Introducing Chatterbox Multilingual: Open Source TTS for 23 Languages
Two months ago, we did something the industry said was impossible. Our team released Chatterbox—an open-source text-to-speech model that outperformed ElevenLabs with 63.75% user preference in blind evaluations. The response was overwhelming. Within weeks, Chatterbox...
Introducing Telephony Optimized Deepfake Detection Model
Resemble AI is raising the bar for inline in-call detection with new support for leading telephony codecs — G.711, G.729, AMR-WB, and Opus — combined with a significant accuracy breakthrough in detecting synthetic and manipulated speech across compressed audio...
Introducing Deepfake Security Awareness Training Platform to Reduce Gen AI-Based Threats
Today, Resemble AI is excited to introduce a groundbreaking approach to cybersecurity: a voice-based deepfake simulation platform designed to help organizations test and harden their defenses against AI-driven social engineering. Early adopters have already reported...
Replay Attacks: The Blind Spot in Audio Deepfake Detection
We're thrilled to announce that groundbreaking research from our team at Resemble AI and collaborators, detailed in the paper "Replay Attacks Against Audio Deepfake Detection," has been accepted for presentation at the prestigious Interspeech 2025 conference! This...
Democratizing Truth: Why We Built a WhatsApp Deepfake Detector Anyone Can Use
The deepfake arms race has created a deeply unfair fight. On one side: increasingly powerful AI creation tools with slick interfaces anyone can use. On the other: detection capabilities hidden behind enterprise paywalls, academic jargon, and technical complexity. It's...
Voice Design: Transforming Text into Unlimited AI Voices
Today, we're thrilled to unveil Voice Design, our most groundbreaking feature yet. Voice Design represents a fundamental shift in how creators approach voice generation by translating simple text descriptions into fully-realized AI voices in seconds.The Power of...
Rapid Voice Cloning 2.0: New Voice Cloning Model with Unmatched Accuracy
Today, Resemble AI announced its latest breakthrough model, Rapid Voice Clone 2.0, enabling users to generate high-quality voice content with just 20 seconds of audio. This powerful tool allows seamless voice generation, editing, and localization, empowering users to...
Introducing State-of-the-Art in Multimodal Deepfake Detection
Today, we present our research on Multimodal Deepfake Detection, expanding our industry-leading deepfake detection platform to support image and video analysis. Our approach builds on our established audio detection system to deliver comprehensive protection across...
Resemble AI Partners with Carahsoft to Bring Voice AI and Deepfake Detection to the Public Sector
We are thrilled to announce our strategic partnership with Carahsoft Technology Corp., The Trusted Government IT Solutions Provider®. This collaboration marks a significant milestone in our mission to bring cutting-edge voice AI technology and advanced deepfake...
