Scenario
← All Models
Audio

Qwen Audio 3.0 TTS

Use it ↗

Fast multilingual text-to-speech from Alibaba Qwen Audio 3.0 (Flash): 45 preset voices across 11 languages, with natural delivery for voiceover, narration, ads, and game dialogue.

Qwen Audio 3.0 TTS (Flash) is Alibaba Tongyi Lab's text-to-speech model. Feed it up to 2,000 characters and it returns natural speech in seconds. Pick from 45 preset voices spanning warm, authoritative, playful, and cinematic personalities, across 11 languages including English, Chinese, Spanish, Portuguese, Japanese, Korean, French, German, Italian, and Russian, with automatic language detection. It reads your text verbatim and adapts tone to punctuation: a fast workhorse for voiceover, trailers, ads, e-learning, and game dialogue.

More models from Alibaba