Qwen 3 TTS 12hz 1.7B Base
Qwen builds the Qwen 3 TTS 12hz 1.7B Base, a text-to-speech model that excels at generating high-fidelity speech in 10 major languages with strong contextual understanding and adaptive control of tone, speaking rate, and emotional expression. It is notable for its universal end-to-end architecture, which utilizes a discrete multi-codebook LM architecture to realize full-information end-to-end speech modeling.
Input
Output
Context
-
Max Output
-
Parameters
1.9B
Technical Specifications
Model TypeAudio
Context WindowNot available
Max Output TokensNot available
Parameters1.9B
Release DateJan 21, 2026
Training CutoffNot available
Licenseapache-2.0
Open SourceYes
Input Modalities
TextAudio
Output Modalities
Audio
Capabilities
Resources & Links
Estimated GPU Requirements for Qwen 3 TTS 12hz 1.7B Base
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.