Deploying real-time personalized speech with Qwen3-TTS on Amazon SageMaker AI

What moved

Deploy the publicly available Qwen3-TTS-12Hz-1.7B-Base text-to-speech model from Amazon SageMaker JumpStart to a fully managed, real-time endpoint, and clone a voice from a short reference clip. Cross-lingual cloning preserves the speaker's identity across languages.

Why it matters

Filed as a public note from AWS, 2026-09-25. Tagged Enterprise.

On the record

• Filed from the AWS official RSS on 2026-09-25.
• Primary source host: aws.amazon.com.
• Deploy the publicly available Qwen3-TTS-12Hz-1.7B-Base text-to-speech model from Amazon SageMaker JumpStart to a fully managed, real-time endpoint, and clone a voice from a short reference clip.