Back to News
Alibaba•December 1, 2025
Qwen3-TTS
Open Source
Audio
TTS
### TL;DR
Qwen3-TTS is an open-source, multilingual text-to-speech (TTS) model developed by Alibaba Cloud's Qwen team. It offers high-fidelity, streaming speech synthesis with ultra-low latency, supporting 10 major languages and 9 Chinese dialects.
Key Insights & Metrics
Pricing
Free for developers with 1 million characters per month; additional usage may incur costs
Cost structure
Version
1.0
Current release version
Hardware
Compatible with modern GPUs; specific requirements depend on deployment scale
Compute requirements
Category
Open Source
Licensing model
Region
China
Primary region
Key Features
- 49 high-quality voices across various genders, ages, and dialects
- Supports 10 major languages and 9 Chinese dialects
- Ultra-low latency with end-to-end synthesis as low as 97ms
- Voice cloning from just 3 seconds of audio input
- Voice design based on natural language descriptions
Discussion
0
Upvotes
0
Downvotes
0 reviews
Sign in to leave a review
Reviews
No reviews yet. Be the first to review!