XiaozhenMandarin, Simplified female neural voice
Xiaozhen is a female neural voice from Microsoft Azure for Chinese (Mandarin, Simplified). Its tone is calm, serious and confident, tailored for conversational and audiobooks. It reads at about 273 words per minute. It has 6 speaking styles you can switch with SSML.
Xiaozhen's speaking styles
Change the emotion of Xiaozhen with an SSML style tag.
{
"type": "voice",
"model": "azure",
"voice": "zh-CN-XiaozhenNeural",
"text": "<speak><mstts:express-as style=\"angry\">在春天,花园里充满了五颜六色的花朵和鸣禽。 古老的橡树为访客提供阴凉,而蝴蝶在玫…</mstts:express-as></speak>"
}
Similar voices
Chinese female voices with a close tone, from ElevenLabs and Azure.
Type your script and get the voiceover in about a minute. Free account, no credit card.
About Xiaozhen
Xiaozhen is a female neural voice from Microsoft Azure for Chinese (Mandarin, Simplified). Its tone is calm, serious and confident, tailored for conversational and audiobooks. It reads at about 273 words per minute. It has 6 speaking styles you can switch with SSML.
Xiaozhen ranks #28 of 43 Chinese Azure voices by search interest in our gallery.
Best for: conversational and audiobooks.
- Provider
- Azure
- Language
- Chinese (Mandarin, Simplified)
- Gender
- Female
- Tone
- Calm, Serious, Confident
- Type
- Neural · GA
- Speed
- 273 words/min
- Voice ID
zh-CN-XiaozhenNeural
Questions about Xiaozhen
Can I make a voiceover with Xiaozhen for free?
You can try it with a free JSON2Video account, no credit card: free voiceovers are up to 60 seconds. Paid plans remove the limit.
Can I use my Xiaozhen voiceovers on YouTube or in ads?
Yes. You can publish the voiceovers and videos you make with Xiaozhen on YouTube, TikTok, podcasts and ads, and use them in commercial projects.
Which languages can Xiaozhen speak?
Xiaozhen is made for Chinese (Mandarin, Simplified). For other languages, pick a multilingual voice.
Does Xiaozhen support SSML?
Yes. Use SSML to add pauses, change the speed or pitch, spell words out and switch between its 6 speaking styles.
For developers: use Xiaozhen with the API
Add a voice element to any JSON2Video movie. It works the same from n8n, Make, Zapier and the CLI.
{
"type": "voice",
"model": "azure",
"voice": "zh-CN-XiaozhenNeural",
"text": "在春天,花园里充满了五颜六色的花朵和鸣禽。 古老的橡树为访客提供阴凉,而蝴蝶在玫瑰丛中跳舞。 一个小小的喷泉发出宁静的声音,使这里成为放松并享受大自然美丽的完美场所。"
}