What is Streaming?

Processing audio and text as they arrive.

Streaming processes input and produces output incrementally rather than waiting for a complete unit. It is what allows an agent to begin speaking before the model has finished composing a sentence, and to hear a caller before they stop talking.

This is an industry glossary. A term defined here is not a statement that Drop AI provides it — see the pricing page for what is included.

Time to first token

How long until a model starts producing output.

Latency

The delay before the agent starts replying.

Barge-in

Letting a caller interrupt the agent mid-sentence.

Voice AI

More in this category

Voice agent Conversational AI ASR STT TTS LLM System prompt Function calling Tool use Knowledge base RAG Grounding

Transform every customer conversation.

Start free, or talk to us about what a custom rollout looks like for your team.

Try for Free Contact Sales