The Fix for a Voice Agent's Dead Air Begins at Sentence One
A voice agent can have the answer well underway and still leave the caller in silence: the customer waits five seconds while a long, multi-paragraph response is still being generated. The proposed fix is to stop waiting for the whole response and stream synthesis alongside generation.
Each sentence goes to a hosted Kokoro-82M model as soon as the agent produces it, so playback can begin before the full response is finished. Kokoro-82M has 82 million parameters and is small enough to run cheaply on a single mid-tier GPU instance.
The implementation catch is that closing the session after one response would force a new connection for every sentence, undoing most of the latency gain.
AI-generated discussion · Different perspectives
The useful mental model is a relay handoff: the first sentence's audio starts while later sentences are still being written.
That relay only works if the framing is right. A handler that calls receive_text() fails on every request here because the client's messages arrive as binary frames.