Skip to content
AWS Machine Learning Blog· Yadan Wei·· 2026-09-29

Build real-time voice applications with vLLM-Omni on SageMaker AI – Part 1

Build real-time voice applications with vLLM-Omni on SageMaker AI – Part 1

AI summary

Deploy a text-to-speech model on Amazon SageMaker AI with the AWS vLLM-Omni Deep Learning Container and stream generated speech over a persistent bidirectional connection. This Part 1 tutorial deploys Qwen3-TTS and streams speech through a Gradio application.

Selection record

Not admittedSum of both 68 < twice the threshold 120

Source tier
Official, first-hand; this tier's threshold is 60
Pre-filter
passed:教程部署TTS模型与vLLM-Omni推理,实质AI开发
Same event

A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.

Source: AWS Machine Learning Blog · aws.amazon.com