创建

登录 ReadmeX

或

了解我们如何处理你的信息: 隐私政策

ReadmeX

陪你读懂 AI 动态

今天,想先了解什么?

选一份动态总结,或直接聊聊你的问题。

社区和关注动态总结只属于你自己。

资讯

AWS 演示用 Kokoro-82M 为语音智能体逐句流式合成

AI 总结

AWS 机器学习博客发布教程,介绍如何把 AI 智能体生成的每个句子即时送入托管在 Amazon SageMaker AI 上的 Kokoro-82M 文本转语音模型,让合成从第一句就开始,而不是等完整回复生成完毕。文章把问题描述为延迟缺口:一句回复可能 600 毫秒就生成完,而完整回复需要五秒,这段时间里客户听不到任何声音。Kokoro-82M 仅有 8200 万参数,运行在 ml.g5.xlarge 实时端点上的自定义容器中,提供 POST 流式路由和双向 WebSocket 路由;AWS 还比较了通过 Server-Sent Events 把音频送回浏览器的做法,其中 base64 编码使负载增加约三分之一的预期幅度,且 MP3 帧与传输分块并不对齐。AWS 称在隔离测试中首个音频的到达时间缩短一半以上,在部署的智能体中缩短 2.4 至 3.5 倍,并说明处理器是严格顺序循环,而非并发合成。

深度见解

该教程为给流式文本智能体加入语音的团队提供了一个具体方案,并量化了在完整回答生成前就开始语音合成的成本。

A customer asks an AI voice agent a question and waits. The agent already has an answer, it’s midway through generating a long, multi-paragraph response, but the customer hears nothing for five seconds. By the time an answer arrives, the customer is frustrated, confused, and no longer paying attention.

Text-to-speech integrations create exactly that gap. A one-sentence response might generate in 600 milliseconds, but the full response takes five seconds, and the integration waits for all of it before synthesis starts.

This post shows how to close that gap. We stream each sentence to a hosted Kokoro-82M text-to-speech (TTS) model on Amazon SageMaker AI as soon as an agent produces it, so synthesis begins on sentence one instead of the finished response. Getting that audio back to a browser needs its own solution too, so we also cover both transports for doing it and what each costs in practice.

Solution overview

This solution closes the gap by streaming synthesis alongside generation instead of waiting for it to finish. As the agent produces each sentence, that sentence streams immediately to a hosted Kokoro-82M text-to-speech model, so audio playback can start before the agent finishes speaking its full response. Kokoro-82M holds only 82 million parameters, small enough to run cheaply on a single mid-tier GPU instance. That keeps both latency and inference cost low for a voice agent handling real traffic.

#AWS#Amazon SageMaker AI#Kokoro-82M#Amazon Bedrock AgentCore#Amazon Transcribe

原文约 12 分钟读完阅读原文
群聊

还没有评论,来说说你的看法。