AI Reports · Amazon · 2026-10-22 · Blog / commentary
Stream low-latency speech from AI agents using Kokoro TTS on Amazon SageMaker AI
Voice agents often wait for the agent's full response before starting speech synthesis, adding latency that users feel directly. The post shows how to stream each sentence to a hosted Kokoro-82M text-to-speech model on Amazon SageMaker AI as soon as the agent produces it, so audio playback can begin before the full response is finished. It also covers the two transports for getting that audio back to a browser—Server-Sent Events or a unified binary transport—and what each costs in practice.