Barge-in and turn-taking: how conversational voice systems handle interruption
The reason most voice assistants feel like arguing with a telephone tree.
Nadia Reyes
Section
Features
3 stories in Features.
Streaming text-to-speech: chunking, prosody, and the time-to-first-audio problem
Latency, not voice quality, determines whether streaming TTS feels natural or broken.
Mateo Zola
Running speech models on-device: quantization, memory ceilings, and edge inference tradeoffs
Beatrice Adeyemi