AI Models Navi
Back to Models
AlibabaOpen Source

Qwen3-TTS-12Hz-1.7B-Base

Qwen3-TTS-12Hz-1.7B-Base is a speech foundation model developed by Alibaba. It has a parameter scale of 17.0 billion and achieves advanced speech generation.

Parameters

17.0B

Context Window

License

Apache 2.0

Release Date

2026-01-22

API Pricing

API pricing for this model is not yet available

Strengths

  • ・Rich 17 billion parameter count
  • ・Open Apache 2.0 license
  • ・Efficient model file size

Weaknesses

  • ・Requires fine-tuning as a base model
  • ・Voice-specific, not for general text tasks
  • ・Insufficient detailed performance metrics

Use Cases

  • ・Building high-quality voice synthesis systems
  • ・Developing AI voice assistants
  • ・Downstream task learning for voice generation