How does your phone write down what you say? — Voice
A voice is vibration chopped into tiny pieces, and text is the answer you get by matching each piece with its neighbors.
1 · Think first
AI doesn't hear your words in one go — it chops them into tiny pieces. It writes the sound down as numbers 16,000 times a second, then sweeps over them with a 25-millisecond window.
Each piece on its own is just a "pitch pattern." What you actually said only gets decided by looking at the pieces around it — like the video you saw yesterday, one slot alone doesn't tell you.
Speaking is the same road in reverse. It turns text into a sound pattern, then follows that pattern to stamp out air vibrations more than 16,000 times a second and send them out of the speaker.
2 · Experiment · Split it up
Try it — How "Can you write it down" becomes text — and then sound again
Tap the buttons to change steps. You'll see speech get chopped into pieces, the pieces join into words, and the words turn back into vibrations.
Figure
Speech → text → speech, one full loop
Writing speech down and speaking out loud travel the same road in opposite directions.
3 · Quiz
Quick check
Three questions. Pick an answer and it's marked right away, with the reason why.
Today in one line
Today in one line
A voice is vibration chopped into tiny pieces,
and text is the answer you get by matching each piece with its neighbors.
Learn more
- The day a model that turns speech into text was released for anyone to use — it learned from 680,000 hours of listening — Introducing Whisper (OpenAI, 2022)
- The paper behind that model. It explains writing sound down 16,000 times a second and sweeping over it with a 25-millisecond window — Robust Speech Recognition via Large-Scale Weak Supervision (2022)
- An early study that went the other way, building a voice by stamping out vibrations one point at a time — you can listen to the sound samples yourself — WaveNet: A generative model for raw audio (Google DeepMind, 2016)