Free · No Sign-up · 8 Voices

Free Mandarin Chinese Text to Speech

Generate natural Mandarin Chinese text to speech with 8 distinct voices.

Try it — Live Mandarin Chinese TTS Demo

Select a voice, type your text, and hit Generate. Audio plays instantly in your browser.

1.0×

About Mandarin Chinese Text to Speech

Eight Mandarin Chinese voices — 4 female (Xiaobei, Xiaoni, Xiaoxiao, Xiaoyi) and 4 male (Yunjian, Yunxi, Yunxia, Yunyang) — produce clear, natural Putonghua for Chinese media, eLearning, corporate communications, and accessible content.

Use Cases

Mandarin eLearningChinese corporate videoPutonghua narrationHSK study toolsChinese podcast

Mandarin Chinese Voices (8 available)

All voices are free and unlimited. Click a voice ID in the demo above to preview.

zf_xiaobei
Xiaobei
Female · zh
zf_xiaoni
Xiaoni
Female · zh
zf_xiaoxiao
Xiaoxiao
Female · zh
zf_xiaoyi
Xiaoyi
Female · zh
zm_yunjian
Yunjian
Male · zh
zm_yunxi
Yunxi
Male · zh
zm_yunxia
Yunxia
Male · zh
zm_yunyang
Yunyang
Male · zh

Frequently Asked Questions

Does it support Simplified and Traditional Chinese characters?
The model primarily targets Simplified Chinese. Traditional character input may work for commonly used characters, but Simplified is recommended.
Which Mandarin voices are available?
Female: Xiaobei (bright), Xiaoni (gentle), Xiaoxiao (clear — most popular), Xiaoyi (warm). Male: Yunjian (authoritative), Yunxi (friendly), Yunxia (deep), Yunyang (calm). Eight voices to match any content style.
Does it handle tones correctly?
Yes. The Kokoro model produces correct Mandarin tones (1st–4th + neutral) based on standard Pinyin-aligned training data.
Can I use it for HSK vocabulary learning?
Yes — paste your HSK word list or example sentences to hear correct pronunciation. Ideal for HSK 1–6 self-study.
Is Mandarin TTS suitable for corporate training videos?
Absolutely. The Yunjian and Yunxi voices have a professional tone well-suited to instructional and corporate communications content.

More Languages

We support 9 languages with 54 total voices:

TTS by Use Case