Speech & Audio

Voice AI, speech recognition, and audio processing

7 episodes

#2183: Making Voice Agents Feel Natural

Turn-taking, interruptions, and latency are destroying voice AI UX—and the fixes are deeply technical. Here's what's actually happening underneath.

speech-recognitionconversational-ailatency
Audio Processing

#1809: The TTS Developer's Dilemma: Size vs. Speed

Stop guessing. We break down the critical trade-offs between model size, latency, and sample rate for production-ready voice apps.

text-to-speechgpu-accelerationedge-computing
Text-to-Speech

#1808: The 82M Parameter Voice That Beat Billion-Dollar AI

How a model the size of a tweet outperforms billion-dollar giants in the race for perfect AI speech.

open-source-aismall-language-modelstext-to-speech
Text-to-Speech

#1800: The Engineering of Urgent Sound

Why some sounds make your skin crawl: the science of emergency alerts.

audio-processinghuman-computer-interactionemergency-preparedness
Audio Processing

#1778: Audio Is the New "Read Later" Graveyard

Why listening to AI conversations beats reading dense PDFs, and how serverless GPUs make it cheap.

audio-processingserverless-gpurag
Text-to-Speech

#1752: Whisper Small Beats Whisper Large in Speed & Accuracy

A 4GPU benchmark on Ubuntu shows the 1.5B parameter Whisper Large is slower and less accurate than the tiny Whisper Small.

speech-recognitiongpu-accelerationlatency
Speech-to-Text

#1724: YouTube's Invisible AI Dubbing Machine

How does YouTube translate a video with one click? We explore the tech behind auto-dubbing, from sandwich models to voice cloning.

speech-to-speechvoice-cloningmultimodal-ai
Text-to-Speech