Qwen-TTS supported dialects and voice selections
Qwen-TTS offers a wealth of voice options to meet the needs of different scenarios and geographies:
Standardized speech (Mandarin/English)
- Cherry:: Standard female voice for generic scenarios
- Ethan:: Standard male voice, calm and professional
- Chelsie:: Lively young female voice
- Serena: Elegant Mature Female Voice
Dialect-specific speech
- Dylan (Beijing dialect):: With authentic Beijing accent, humor and vividness, especially suitable for content in the northern region
- Jada.: Wu language area style, suitable for users in the Yangtze River Delta region
- Sunny (Sichuan):: Southwest Mandarin, lively and interesting, with local flavor
Common features of each voice
- All voices are supportedChinese-English bilingual
- be capable ofAutomatically adjusts emotion and tone
- preserve the specificity of a dialectPronunciation habits and rhythms
- Suitable for localized content creation
In practice, the desired sound can be specified via the API's voice parameter, for examplevoice="Sunny"You can generate Sichuan speech.
This answer comes from the articleQwen-TTS: Speech Synthesis Tool with Chinese Dialect and Bilingual SupportThe
May not be reproduced without permission:AI productivity tools " What dialects and voice choices does Qwen-TTS support? What are the features of each?
