Resemble AI

Ten seconds of audio is all it takes to clone a voice. Here's what the law actually protects — and what it doesn't.

Resemble pushed new Chatterbox weights to Hugging Face. Our pipeline started using them without a single config change.

We dig into why AI podcast voices sound too clean—and how TTS is learning to stumble, overlap, and interrupt convincingly.

From espeak's robotic squawk to neural voices with added "ums" — how transformers made speech synthesis human.

Resemble AI sells deepfake detection but open-sourced Chatterbox, a top TTS model. Here's the strategic logic.

We break down the architecture of Chatterbox, the open-source TTS model powering this podcast, and why it remains state of the art.

Why most single-shot TTS models drift over time—and how Chatterbox's cached embedding approach solves it.

How dynamic voice replacement could let listeners choose who narrates each host's lines.

We dissect Resemble AI's Chatterbox to see how its open-source TTS compares to commercial giants like ElevenLabs.

Peek behind the curtain of a 2026 AI podcast, from agentic workflows to maintaining production during global conflict.

Herman and Corn dive into the mechanics of neural text-to-speech, exploring how AI masters human prosody and the "average voice" accent problem.

Invisible watermarks in AI? Is it privacy or protection? We uncover the hidden truth behind AI-generated content.