The three models include Qwen3-TTS-12Hz-1.7B-CustomVoice for customizable expressive text-to-speech in multiple languages; Qwen3-TTS-12Hz-1.7B-Base for rapid voice cloning and flexible speech synthesis; and Qwen3-ASR-1.7B for automatic speech recognition supporting 52 languages and dialects with high accuracy in complex acoustic settings.
These models facilitate development of real-time interactive voice assistants, transcription services, and multilingual support scenarios. Deployment is streamlined via SageMaker Studio or Python SDK, allowing customers to address varied enterprise needs in speech AI through managed AWS infrastructure.
Source & further reading
Three new models for speech recognition and text-to-speech are now available in Amazon SageMaker JumpStart ↗Source published 2026-05-14. This report was prepared with AI assistance from the linked primary-source material. Claims and limitations should be checked against the original announcement or research.