#voice-to-text
7 episodes
#5460: Four Small Models, One Android Phone: Does It Actually Work?
A chained on-device dictation pipeline — VAD, ASR, cleanup — and why "it feels smooth" isn't the same as knowing it works.
#4477: Structuring Raw Voice Prompts at Scale
How to decompose messy voice dictation into clean, routable components for AI workflows.
#4157: Prompt Engineering Is a Misnomer — Managing Ambiguity in AI
Why the best AI outputs come not from tighter prompts, but from knowing where to leave room for surprise.
#2332: Voice-to-Task: Building the Claude Task Planner
How does a voice note turn into a completed task? Dive into the architecture and tradeoffs of building a Claude-powered task execution system.
#1540: Why Gnome 50 is Breaking Your Voice-to-Text Tools
Explore the engineering battle to bring low-latency AI voice input to Linux while navigating the strict security of Wayland and GNOME 50.
#99: The Mic That Hears You from Across the Desk
Tired of headsets? Herman and Corn explore professional microphone setups for seamless, high-accuracy AI voice dictation from a distance.
#58: Clean Audio, Messy Reality: Noise Removal for Voice-to-Text
Fussy baby, clean audio? We dive into noise removal for voice-to-text. Discover why cleaner audio can transcribe worse.