Qwen Releases Qwen-Audio-3.0-TTS, Tops TTS Leaderboard
Original title:Introducing the Qwen-Audio-3.0-TTS. Our latest text-to-speech model, in two flavors: • Flash: real-...
AI summary
Alibaba's Qwen launched its latest text-to-speech model, Qwen-Audio-3.0-TTS, offering Flash (real-time interaction) and Plus (high-quality generation) versions. New features include fine-grained inline tag control (such as [whisper] and [angry]), natural-language style control, support for 16 languages, and generation of long text of up to 3 minutes in a single pass. The model currently ranks first on the Artificial Analysis TTS leaderboard.
Key Takeaways
- Alibaba's Qwen launched its latest text-to-speech model,Qwen-Audio-3.
- 0-TTS,offering Flash (real-time interaction) and Plus (high-quality generation) versions.
- New features include fine-grained inline tag control (such as [whisper] and…
- The model currently ranks first on the Artificial Analysis TTS leaderboard.
Quick Facts
- Published
- Updated
- Category
- Model Releases
- AI score
- 79
TTS 模型终于学会控制情感和语调了,Qwen 这次把自然语言提示和细粒度标签一起放进去,做语音助手的可以直接从‘能说话’跳进‘有性格’。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: Qwen Releases Qwen-Audio-3.0-TTS, Tops TTS Leaderboard. July 23, 2026. https://new.nat6.net/en/news/cmrxihn0u00e7ro4jy78efqxq/