Three new models for speech recognition and text-to-speech are now available in Amazon SageMaker JumpStart

This article announces the availability of three new Qwen3 speech models in Amazon SageMaker JumpStart for speech recognition and text-to-speech capabilities.

• Qwen3-TTS-12Hz-1.7B-CustomVoice: Multilingual TTS with customizable voice styles across 10 languages
• Qwen3-TTS-12Hz-1.7B-Base: Multilingual TTS with 3-second rapid voice cloning from audio input
• Qwen3-ASR-1.7B: Automatic speech recognition supporting 52 languages with state-of-the-art accuracy
• Models enable real-time interactive voice applications, virtual assistants, and transcription services
• Deploy models with few clicks using SageMaker Studio or Python SDK

These models expand SageMaker JumpStart's foundation model portfolio, enabling customers to build intelligent voice-powered applications on AWS infrastructure.