在 Amazon SageMaker AI 上部署 Qwen3-TTS 实时个性化语音

AI 摘要

AWS 博客介绍如何在 Amazon SageMaker AI 上通过 JumpStart 部署阿里云 Qwen 团队开源的 Qwen3-TTS-12Hz-1.7B-Base 文本转语音模型，实现实时语音克隆。该模型支持 10 种语言和跨语言克隆，仅需几秒参考音频即可复刻说话人音色，无需重新训练。部署采用 vLLM-Omni 容器和全托管实时推理端点，用户可自行控制成本并让音频数据保留在 AWS 环境内。

正文节选

Deploying real-time personalized speech with Qwen3-TTS on Amazon SageMaker AI With voice cloning, you can generate new speech in a target speaker’s voice from a short reference recording, without retraining a model. You can now deploy the publicly available Qwen3-TTS-12Hz-1.7B-Base text-to-speech model from Amazon SageMaker JumpStart to a fully managed, real-time inference endpoint. Voice cloning reproduces the vocal identity of a specific speaker. Start with a short recording of the speaker and

发布时间：2026-09-26 00:09

抓取时间：2026-09-26 00:15

来源机构：AWS