... quickly. Words flicker. Silence becomes text. The model completes a cutoff with something plausible. The final half-second of audio is especially dangerous because the model has just enough signal to guess, but not enough signal to know. So Juno treats live transcription as two separate objects: committed text - Stable enough to show as real speech. tail text -Useful as preview, but still provisional. The interesting part is the boundary between them. Juno

... Raise your hand if you've Googled a symptom at 2am and convinced yourself it was something terrible That's exactly why we built the AI symptom checker in Juno. What's the wildest thing you've ever self-diagnosed? Comment from Luca Daprano(@luca_daprano): I avoided looking into symptoms for the longest time because every search online felt overwhelming. Too much fear, too much conflicting information. Juno