BlogMay 15, 2025
How We Built Cue's Real-Time Transcription Pipeline
A look under the hood at how Cue delivers sub-200ms voice-to-text with context-aware corrections.
Mrigesh ParasharRead
Release notes, behind-the-scenes, and thoughts on voice-first computing.
A look under the hood at how Cue delivers sub-200ms voice-to-text with context-aware corrections.
Transcribe without an internet connection. Your voice stays on your Mac.
Auto-corrections now understand context. Plus, support for 8 new languages.
You speak at 150 WPM. You type at 40. The math is obvious — so why aren't more people voice-typing?
The first public release of Cue. Talk anywhere, text appears.