← All models

Qwen-Audio-3.0-TTS-Plus

Published Publisher Alibabaqwen-audio-3.0-tts-plus

Overview

Qwen-Audio-3.0-TTS-Plus is a text-to-speech model focused on high-quality, expressive speech generation. Alibaba lists it for both speech synthesis and real-time speech synthesis. The official release date is July 14, 2026. (alibabacloud.com)

Capabilities and uses

The model accepts text and produces audio. Alibaba reports expanded support for low-resource languages and Chinese dialects, as well as free-form instructions and fine-grained tags for controlling emotion, tone, character, speaking rate, volume, and synthesis style. It is positioned for content creation, audiobooks, film and video dubbing, brand voice design, and premium speech services. (alibabacloud.com)

Limitations

The model information page lists function calling, structured output, web search, context caching, batch inference, and model tuning as unsupported. It does not specify maximum input, output, or context lengths. The listed rate limit is 180 requests per minute in Beijing and Singapore; actual limits and availability should be checked for the deployment in use. (help.aliyun.com)

Pricing

Official prices checked on November 16, 2026. These are distinct platform and deployment prices, not currency conversions. For this model, billing is based on input text characters; output audio is not charged separately. (help.aliyun.com)

Official sources