---
format: "aidr-story-markdown/v1"
id: "439157ba5b17730b4f5383cb569ec1d7a766c49519e982fcf449a06da57b505a"
canonical_url: "https://aidr.today/439157ba?lang=en"
title: "Stream low-latency speech from AI agents using Kokoro TTS on Amazon SageMaker AI"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-22T17:45:58.000Z"
category: "Tools"
topics: ["amazon","inference","devtools"]
source_urls: ["https://aws.amazon.com/blogs/machine-learning/stream-low-latency-speech-from-ai-agents-using-kokoro-tts-on-amazon-sagemaker-ai/"]
summary: "A post describes how to stream sentences from a Kokoro-82M text-to-speech model on Amazon SageMaker AI to a browser using Server-Sent Events or a unified binary transport, reducing latency for voice agents."
---

# Stream low\-latency speech from AI agents using Kokoro TTS on Amazon SageMaker AI

> [Open the canonical story](<https://aidr.today/439157ba?lang=en>)

**Published:** 2026-10-22T17:45:58.000Z
**Category:** Tools
**Topics:** amazon, inference, devtools

## Summary

A post describes how to stream sentences from a Kokoro\-82M text\-to\-speech model on Amazon SageMaker AI to a browser using Server\-Sent Events or a unified binary transport, reducing latency for voice agents\.

## Sources

- [Story source](<https://aws.amazon.com/blogs/machine-learning/stream-low-latency-speech-from-ai-agents-using-kokoro-tts-on-amazon-sagemaker-ai/>)