Qwen(@Alibaba_Qwen)
Introducing the Qwen-Audio-3.0-TTS. Our latest text-to-speech model, in two flavors: • Flash: real-...
8.5内容质量
TL;DR · AI 摘要
阿里巴巴推出Qwen-Audio-3.0-TTS，支持16种语言及细粒度情感控制，登顶TTS排行榜。
核心要点
- Qwen-Audio-3.0-TTS支持16种语言及[whisper]、[angry]等情感标签控制
- Plus版本实现高质量生成，Flash版本支持实时交互
- 模型可处理嘈杂参考音频，最长支持3分钟连续生成
结构提纲
按章节快速跳转。
思维导图
用一张图看清主题之间的关系。
查看大纲文本（无障碍 / 无 JS 友好）
- Qwen-Audio-3.0-TTS
- 产品版本
- Flash（实时交互）
- Plus（高质量生成）
- 核心能力
- 16种语言支持
- 情感标签控制
- 嘈杂音频净化
- 性能指标
- 3分钟长文本生成
- TTS排行榜第一
金句 / Highlights
值得收藏与分享的关键句。
Fine-grained inline tags-steer [whisper], [angry], [breaths] & [laughs]
One-pass long-form up to 3 min now #1 on the Artificial Analysis TTS Leaderboard
Clean output even from noisy reference audio
#Qwen-Audio-3.0-TTS#文本到语音#阿里巴巴#AI模型
打开原文Qwen on X: "Introducing the Qwen-Audio-3.0-TTS. Our latest text-to-speech model, in two flavors: • Flash: real-time interaction • Plus: high-quality generation What's new: • Fine-grained inline tags-steer [whisper], [angry], [breaths] & [laughs] • Free-style natural-language control-“read this slowly, like a bedtime story” • 16 languages • Clean output even from noisy reference audio • One-pass long-form up to 3 min now #1 on the Artificial Analysis TTS Leaderboard. Blog: https://t.co/ACqTI2wGHI API: https://t.co/Xh2Y19noVx" / X
Qwen
@Alibaba_Qwen
Introducing the Qwen-Audio-3.0-TTS. Our latest text-to-speech model, in two flavors: • Flash: real-time interaction • Plus: high-quality generation What's new: • Fine-grained inline tags-steer [whisper], [angry], [breaths] & [laughs] • Free-style natural-language control-“read this slowly, like a bedtime story” • 16 languages • Clean output even from noisy reference audio • One-pass long-form up to 3 min now #1 on the Artificial Analysis TTS Leaderboard. Blog:
funaudiollm.github.io/qwen-audio-3.0…
API:
alibabacloud.com/help/en/model-…
12:33 PM · Jul 23, 2026
124.9K
Views
96
167
1.9K
634