Skip to main content
QwenCloud home page
Docs
Voice list

Qwen-Audio-TTS voice list

Browse system voices for Qwen-Audio-TTS models, listen to previews, and download base voice lists and audio samples.

  • The selected voice (voice) must be supported by the model (model). Do not use voices from another model. An unsupported voice returns an InvalidParameter error, such as [cosyvoice:]Engine error [411]: TTS speak operation failed.
  • The input text (text) must use a language supported by the voice. Otherwise, pronunciation errors or unnatural speech may occur.
To create a custom voice, see Voice cloning or Voice design.

System voices

For voices that support dialect instructions, specify the dialect with the instruction control field instruction, for example, 请讲上海话。 (Speak Shanghainese).

qwen-audio-3.1-tts-plus

  • Flagship voices
VoiceGenderFeatures
Name: Long An Lingxin_v3.1Voice ID: longanlingxin_v3.1FemaleSSML: SupportedInstruction control: SupportedTimestamps: Supported
Name: Xu NanchuanVoice ID: xunanchuan_v3.1MaleSSML: SupportedInstruction control: SupportedTimestamps: Supported
Name: Long An Huan_v3.1Voice ID: longanhuan_v3.1FemaleSSML: SupportedInstruction control: SupportedTimestamps: Supported
Name: Long An Fengyue_v3.1Voice ID: longanfengyue_v3.1FemaleSSML: SupportedInstruction control: SupportedTimestamps: Supported

qwen-audio-3.1-tts-flash

Multilingual and dialect voices, premium English voices, and additional language voices are available in Singapore and China North 2 (Beijing). All other voice categories are available only in China North 2 (Beijing).
  • Multilingual and dialect voices
  • Premium Chinese voices
  • Premium English voices
  • Additional system voices
  • Additional language voices
All four voices below support all of the following dialects and languages.
  • Chinese dialects: Shanghainese, Cantonese, Northeastern, Chongqing, Shaanxi, Yunnan, Ningbo, and Gansu.
  • Languages: Japanese, Korean, French, German, Portuguese, Italian, Vietnamese, and Indonesian.
Voice informationGenderFeature supportPreview
Name: Long An Huan_v3.1Voice ID: longanhuan_v3.1FemaleSSML: SupportedInstruction control: SupportedTimestamps: Supported
  • Chongqing dialect
  • Ningbo dialect
  • Korean
  • Indonesian
Name: Long An Lingxin_v3.1Voice ID: longanlingxin_v3.1FemaleSSML: SupportedInstruction control: SupportedTimestamps: Supported
  • Yunnan dialect
  • Shaanxi dialect
  • Shanghainese
  • French
  • Italian
Name: Long An Fengyue_v3.1Voice ID: longanfengyue_v3.1FemaleSSML: SupportedInstruction control: SupportedTimestamps: Supported
  • Northeastern dialect
  • Vietnamese
  • Japanese
Name: Xu NanchuanVoice ID: xunanchuan_v3.1MaleSSML: SupportedInstruction control: SupportedTimestamps: Supported
  • Gansu dialect
  • Northeastern dialect
  • French
  • Portuguese

qwen-audio-3.0-tts-plus

Use caseVoice detailsFeature supportAudio preview (right-click to save audio)

Social companionship (flagship voice)

Name: Long An Ling Xin

Voice parameter: longanlingxin

Characteristic: Warm and empathetic

Age: 25

Gender: Female

Language: Chinese (Mandarin), English

SSML: SupportedInstruction control: SupportedTimestamps: Supported

Name: Long An Lu Feng

Voice parameter: longanlufeng

Characteristic: Bright and cheerful

Age: 25

Gender: Male

Language: Chinese (Mandarin), English

SSML: SupportedInstruction control: SupportedTimestamps: Supported

qwen-audio-3.0-tts-flash

Use caseVoice detailsFeature supportAudio preview (right-click to save audio)

Social companionship (premium Chinese voice)

Name: Long An Feng Yue

Voice parameter: longanfengyue

Characteristic: Natural and friendly

Age: 30

Gender: Female

Language: Chinese (Mandarin), English

SSML: SupportedInstruction control: SupportedTimestamps: Supported

Name: Long An Yuan Fei

Voice parameter: longanyuanfei

Characteristic: Proud and regal

Age: 30

Gender: Female

Language: Chinese (Mandarin), English

SSML: SupportedInstruction control: SupportedTimestamps: Supported

Name: Long An Ling Xi

Voice parameter: longanlingxi

Characteristic: Cute and sweet

Age: 25

Gender: Female

Language: Chinese (Mandarin), English

SSML: SupportedInstruction control: SupportedTimestamps: Supported

Name: Long An Xiao Xin

Voice parameter: longanxiaoxin

Characteristic: Friendly and lively

Age: 22

Gender: Female

Language: Chinese (Mandarin), English

SSML: SupportedInstruction control: SupportedTimestamps: Supported

Name: Long An Huan

Voice parameter: longanhuan_v3.6

Age: 25

Gender: Female

Language: Chinese (Mandarin), English

SSML: SupportedInstruction control: SupportedTimestamps: Supported

Child companion / smart toy (premium child voice)

Name: Long Jie Li Dou

Voice parameter: longjielidou_v3.6

Characteristic: Innocent young boy

Age: 5

Gender: Male

Language: Chinese (Mandarin), English

SSML: SupportedInstruction control: SupportedTimestamps: Supported

Name: Long Pao Pao

Voice parameter: longpaopao_v3.6

Characteristic: Soft and adorable

Age: 5

Gender: Female

Language: Chinese (Mandarin), English

SSML: SupportedInstruction control: SupportedTimestamps: Supported

Character / gaming voice (premium Chinese voice)

Name: Long Huo Huo

Voice parameter: longhuohuo_v3.6

Characteristic: Mischievous young boy

Age: 8

Gender: Male

Language: Chinese (Mandarin), English

SSML: SupportedInstruction control: SupportedTimestamps: Supported

Name: Long Chuan Shu

Voice parameter: longchuanshu_v3.6

Characteristic: Sichuan-accented middle-aged male

Age: 40

Gender: Male

Language: Chinese (Mandarin), English

SSML: SupportedInstruction control: SupportedTimestamps: Supported

Social companionship / voice assistant (premium English voice)

Name: loongmary

Voice parameter: loongmary

Characteristic: Warm British accent

Age: 20

Gender: Female

Language: English

SSML: Not supportedInstruction control: Not supportedTimestamps: Not supported

Name: loongeva

Voice parameter: loongeva_v3.6

Characteristic: Intelligent-sounding American accent

Age: 28

Gender: Female

Language: English

SSML: Not supportedInstruction control: Not supportedTimestamps: Not supported

Name: loongjohn

Voice parameter: loongjohn

Characteristic: Calm and friendly American accent

Age: 28

Gender: Male

Language: English

SSML: Not supportedInstruction control: Not supportedTimestamps: Not supported

Base voices

We recommend prioritizing system voices for more consistent speech synthesis results. To create a custom voice, use voice cloning or voice design. Base voices offer more options. Before using them, listen to the previews and evaluate whether they meet your business needs.
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 in the same way as system voices. Base voices follow the naming pattern qwen-audio-3.0-tts-{plus|flash}-{voice suffix}. The same suffix in both models maps to the same set of preview audio files. Preview steps
  1. Download the Excel files and the preview audio package, and 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.
Qwen-Audio-TTS voice list - QwenCloud