Overview
Qwen-Audio-3.1-TTS-Plus is a professional text-to-speech model focused on audio quality and content production. It converts text to audio and supports streaming synthesis, multiple languages and dialects, voice cloning, voice design, and natural-language or tag-based control of expression, including emotion, tone, persona, speaking rate, and volume. Voice cloning uses a reference recording. (docs.qwencloud.com)
Uses
The official announcement identifies brand voices, audio content creation, film and television dubbing, and character performance as intended uses. (docs.qwencloud.com)
Limitations
The model page lists function calling, structured output, web search, context caching, batch inference, and fine-tuning as unsupported. It does not specify maximum input length, maximum output length, or context window. Supported languages depend on the selected voice; using a voice with an unsupported language can produce pronunciation errors or unnatural speech. (help.aliyun.com)
Release date
October 21, 2026, according to the official model-release announcement. (docs.qwencloud.com)
API pricing
Prices below are official listed rates checked on November 15, 2026. For this model, synthesis is billed by input text character count; audio output has no separate charge. The prices apply to the stated sites and deployment regions and are not currency conversions. (help.aliyun.com)
- Alibaba Cloud China site, China North 2 (Beijing): CNY 1.4 per 10,000 input characters. China site, Singapore, international deployment: CNY 2.19 per 10,000 input characters. Source: official China pricing. (help.aliyun.com)
- Alibaba Cloud international site, Singapore, international deployment: USD 0.30 per 10,000 input characters. International site, China (Beijing), mainland China deployment: USD 0.20 per 10,000 input characters. Source: official international pricing. (alibabacloud.com)
For billing, each Chinese character, including Japanese kanji and Korean hanja, counts as two characters; other characters, such as English letters, spaces, and punctuation, count as one. SSML tags themselves are excluded. The China-site Beijing and international-site Singapore listings each include a 10,000-character free quota, subject to their respective published 90-day conditions. (help.aliyun.com)