Dev Recreates AirPods Subvocal Speech-to-Text in 9 Minutes With One Prompt

Developer joeblau recreated the subvocal (silent speech-to-text) feature for AirPods Pro in just 9 minutes using a single prompt, open-sourcing it as Subvox. The original poster noted that in the AI era, such products can be replicated almost instantly.

2026-10-31 ~ 2026-11-02 · 2 related posts

• Subvox: one-prompt, 9-minute rebuild of silent-speech recognition using AirPods Pro motion data — seatedro · 2026-10-31
• Dev recreates 'subvocal' for AirPods Pro 3 with one prompt in 9 minutes, open-sourced — _AustinCalvert_ · 2026-11-02