在 SageMaker AI 上用 vLLM-Omni 构建实时语音应用（上）
原标题：Build real-time voice applications with vLLM-Omni on SageMaker AI – Part 1
AI 摘要
AWS 发布教程，介绍如何在 Amazon SageMaker AI 上使用 vLLM-Omni 深度学习容器部署 Qwen3-TTS 文本转语音模型，实现边生成边播放的流式语音输出。方案通过 SageMaker 双向流式 WebSocket 在单一持久连接上传输文本与音频，并配合 Gradio 应用演示。这是关于专用 DLC 系列文章的第一部分，后续将覆盖图像与视频生成。
正文节选
Build real-time voice applications with vLLM-Omni on SageMaker AI – Part 1 Voice agents, interactive learning applications, accessibility tools, and customer service assistants need to respond without long silent pauses. In this tutorial, you deploy a text-to-speech (TTS) model on Amazon SageMaker AI that can start playing speech before it finishes generating the full response. You use the AWS vLLM-Omni Deep Learning Container (DLC) to deploy Qwen3-TTS, stream text in and audio out over one pers