Dev recreates 'subvocal' for AirPods Pro 3 with one prompt in 9 minutes, open-sourced
_AustinCalvert_ · x · 2026-11-02
Quoting a prototype demo of what looks like a subvocal (silent speech) wearable, developer joeblau recreated the feature for AirPods Pro 3 in 9 minutes using a single prompt and shared the source code. The reshare quips that a startup got 'killed before it actually started' — a Big-Co prototype outpaced by a weekend build with off-the-shelf models.
Related event: Dev Recreates AirPods Subvocal Speech-to-Text in 9 Minutes With One Prompt(2 posts)→
More from coding & agent
- DeepSeek Harness Super-agent design: the bottleneck isn't smarter models, it's your attention — sujingshen · 2026-11-02
- tito: the hidden tokenizer bugs breaking RL training, and a Lean-verified fix — VoidAsuka · 2026-11-02
- Build an Agentic Knowledge Graph from Scratch — No Graph DB, No Extraction Model — adnan_hashmi · 2026-11-02
- One Vault, Two Sides: An Obsidian + Claude Agent Workflow for Personal Knowledge — adnan_hashmi · 2026-11-02
- Vercel engineer open-sources Security Audit skill you trigger via @bot reply — brandon_galang · 2026-11-02
- Vercel Labs shipped 95 releases in October, debuts agent-desktop for computer use — evilrabbit_ · 2026-11-02