Skip to main content
Qwen-Audio-TTS/CosyVoice

Voice list

System and base voices for qwen-audio-3.0-tts-plus and qwen-audio-3.0-tts-flash

Qwen-Audio-TTS supports the system voices listed below. In addition to system voices, pre-generated base voices created through voice cloning are also available. For details, see Base voice list. For a more personalized voice, you can use the voice cloning feature to create a custom voice for free. For details, see Synthesize speech with a cloned voice. When synthesizing speech:
  • Each model supports only a specific set of voices (voice). Voices cannot be mixed across models. If you specify a voice that is not in the voice list of the selected model, the service returns an InvalidParameter error (for example, [cosyvoice:]Engine error [411]: TTS speak operation failed). In this case, refer to the voice list of the corresponding model below and make sure the voice is supported by the current model.
  • The text to be synthesized must be in a language supported by the selected voice. Otherwise, pronunciation errors or unnatural speech may occur.

qwen-audio-3.0-tts-plus system voices

Use caseVoice nameVoice parameterCharacteristicAgeGenderLanguageSample
Social companionship (flagship voice)Long An Ling XinlonganlingxinWarm and empathetic25FemaleChinese (Mandarin), English
Social companionship (flagship voice)Long An Lu FenglonganlufengBright and cheerful25MaleChinese (Mandarin), English

qwen-audio-3.0-tts-flash system voices

Use caseVoice nameVoice parameterCharacteristicAgeGenderLanguageSample
Social companionship (premium Chinese voice)Long An Feng YuelonganfengyueNatural and friendly30FemaleChinese (Mandarin), English
Social companionship (premium Chinese voice)Long An Yuan FeilonganyuanfeiProud and regal30FemaleChinese (Mandarin), English
Social companionship (premium Chinese voice)Long An Ling XilonganlingxiCute and sweet25FemaleChinese (Mandarin), English
Social companionship (premium Chinese voice)Long An Xiao XinlonganxiaoxinFriendly and lively22FemaleChinese (Mandarin), English
Social companionship (premium Chinese voice)Long An Huanlonganhuan_v3.625FemaleChinese (Mandarin), English
Child companion / smart toy (premium child voice)Long Jie Li Doulongjielidou_v3.6Innocent young boy5MaleChinese (Mandarin), English
Child companion / smart toy (premium child voice)Long Pao Paolongpaopao_v3.6Soft and adorable5FemaleChinese (Mandarin), English
Character / gaming voice (premium Chinese voice)Long Huo Huolonghuohuo_v3.6Mischievous young boy8MaleChinese (Mandarin), English
Character / gaming voice (premium Chinese voice)Long Chuan Shulongchuanshu_v3.6Sichuan-accented middle-aged male40MaleChinese (Mandarin), English
Social companionship / voice assistant (premium English voice)loongmaryloongmaryWarm British accent20FemaleEnglish
Social companionship / voice assistant (premium English voice)loongevaloongeva_v3.6Intelligent-sounding American accent28FemaleEnglish
Social companionship / voice assistant (premium English voice)loongjohnloongjohnCalm and friendly American accent28MaleEnglish

Base voice list

In addition to the system voices above, qwen-audio-3.0-tts-plus and qwen-audio-3.0-tts-flash each provide over 500 base voices generated through voice cloning. They are called the same way as system voices. Base voices follow the naming pattern qwen-audio-3.0-tts-{plus|flash}-{voice suffix}, and the same suffix maps to the same set of preview audio files across both models. Download the Excel files below for the full voice list: Preview steps:
  1. Download the Excel files and the preview audio package, then extract the audio package to your local machine.
  2. In the Excel file, find the "Preview audio file name" column and copy the audio file name.
  3. Locate the corresponding file in the extracted folder and open it with a media player to preview.