⚡ Machines That Hear · Day 15

Fast or Accurate?

When you talk to an assistant, should it wait for your whole sentence before answering, or start figuring it out as you speak? That's a real engineering choice, and it changes how fast and smart your app feels. Let's race the two ways.

↓ start the race
🏷️ The pro wordAnswering as you speak is streaming (online) ASR — it emits partial hypotheses and cares about latency. Waiting for the whole clip is batch (offline) ASR. Live captions & assistants use streaming; transcribing a saved recording can use batch. (ASR = Automatic Speech Recognition.)
🏁 Lab · The Latency Race

Streaming vs Batch

Press Speak. Streaming shows words the instant it hears them (low latency). Batch waits for you to finish, then shows everything at once. Watch the timers — and try a longer sentence!

Sentence:

⚡ Streaming (live)

🐢 Batch (waits)

See it? Streaming shows the first word almost instantly; batch makes you wait for the whole sentence. For a chatty assistant, that responsiveness matters a lot!
🧠 Boss Build · Pick the Mode

Streaming or batch for the job?

Correct: 0 / 3
🚀 Beyond the Basics

How the pros really do it

Our race was a simulation of the idea. Here are the real models engineers actually reach for:

🐢

Batch models

Whisper is the famous one — it reads the whole clip. ✅ Top accuracy. ⚠️ Waits until you finish, so higher latency.

Streaming models

Special designs (RNN-Transducer, streaming Conformer) emit words as you speak. ✅ Low latency for live captions/assistants. ⚠️ Slightly less accurate.

🎯

Neural endpointing

A model that decides "you're done talking now" better than a silence timer — so replies feel natural, not cut-off or slow.

🏷️ Pro names to look upWhisper (batch) · RNN-T / Conformer (streaming) · Vosk (streaming, open-source you can run today).

🎉 Day 15 Complete!

You learned the streaming vs batch trade-off and why latency matters — the difference between an assistant that feels instant and one that makes you wait.

Day 16: Tiny Audio, Big Tradeoffs →
Tomorrow: how computers shrink sound — and how shrinking too much wrecks it. Meet sample rate, bit depth & codecs. 🎛️
AI Adventure · Machines That Hear · Day 15 — made for young inventors 🚀