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

AWS SageMaker JumpStart Model Updates

AWS has introduced three new models in Amazon SageMaker JumpStart: Qwen3-TTS-12Hz-1.7B-CustomVoice, Qwen3-TTS-12Hz-1.7B-Base, and Qwen3-ASR-1.7B. These models offer advanced speech synthesis and recognition capabilities across multiple languages, enhancing the ability to build intelligent voice-powered applications.

New Features

• Qwen3-TTS-12Hz-1.7B-CustomVoice: Multilingual text-to-speech with customizable voice styles, supporting 10 languages with control over timbre, emotion, and prosody. Ideal for interactive voice applications and content creation.
• Qwen3-TTS-12Hz-1.7B-Base: Multilingual text-to-speech with rapid voice cloning from audio input. Suitable for custom voice applications and domain-specific speech synthesis.
• Qwen3-ASR-1.7B: Automatic speech recognition supporting 52 languages and dialects with high accuracy in complex environments. Perfect for transcription services and multilingual customer support.

What to do

• Deploy the models via SageMaker Studio or the SageMaker Python SDK.
• Refer to the Amazon SageMaker JumpStart documentation for deployment and usage details.

Source: AWS release notes

If you need further guidance on AWS, our experts are available at AWS@westloop.io. You may also reach us by submitting the Contact Us form.