tazo/labs blog

  1. Ask what the moment needsVoice AI agents decide every few hundred ms: respond, wait, yield or escalate. Why most get it wrong, and what an audio-native decision model changes.
  2. Speculative tool calling: the next big thing in voice AITool calls are where voice agent latency goes. Speculative tool calling starts safe lookups while the caller is still talking, without changing behavior.
  3. The missing piece in the voice AI stack: decision modelsVoice AI stacks have great models for STT, LLM and TTS. The layer that decides when to speak is still a silence timer. Why it needs a decision model.