Essays on product philosophy, real-time transcription, and the future of spoken context.
Essay
September 19, 2026Zhen
Both turn speech into text. The difference is what happens between speaking and final text — continuous finalization, stable output, global context, contextual correction, and speaking one language while writing another.
Essay
August 13, 2026Zhen
Why we extended the Voice Context Layer from understanding speech to participating in live business conversations — and what makes a missed call expensive.
Video
June 17, 2026Zhen
Both tools can transcribe speech in real time. The difference is what real-time output is designed to do.
Audio
June 12, 2026Zhen
Full audio on why readable captions matter — and what changes when live speech becomes easy to follow.
Essay
June 4, 2026Zhen
A better way to evaluate real-time captions and live speech delivery systems beyond raw accuracy.
Essay
April 8, 2026Zhen
Why speech has remained hard to read, return to, and build on, and why the Voice Context Layer matters.