core practice · system design prompt
Design exercise: Voice & Audio Systems
Capture, codecs, streaming, speech recognition, synthesis, turn detection, noise handling, latency, and conversational UX. Implement designOutline() returning non-empty values for: audioPipeline, turnDetection, latencyBudget. Each value must name a concrete mechanism or decision.
The mechanism
Voice systems are real-time pipelines. Audio framing, endpointing, ASR, reasoning, TTS, interruption, and playback each consume the latency budget.
Expected evidence
A design outline with audioPipeline, turnDetection, latencyBudget plus an explicit failure mode or trade-off.
Try this drill in the practice workspace →
Hints when you need them
- Name the failure mode before selecting the mechanism.