YouTube intro
大家好,欢迎回到频道!今天带大家去成都一家开了三十年的小面馆。
Hi everyone, welcome back to the channel! Today, a little noodle shop in Chengdu that has been open for thirty years.
Voices · Mandarin Chinese
Xiǎoyàn is a female Mandarin Chinese voice for Pāṇini TTS, with a warm, expressive tone. The playground opens with the sentence from Xiǎoyàn's own reference recording; replace it with your script and press play.
您好,提醒您一下,您的预约是明天下午,请准时到达,如果有任何变动请提前告诉我们。
Voices
Free to play in your browser without an account, up to 220 characters at a time. To save the audio, sign up free for 10,000 characters and one voice clone, no card required: the dashboard saves WAV and the API returns MP3.
Last verified 26 October 2026
About Xiǎoyàn
Xiǎoyàn reads Mandarin with a Mainland China accent in a warm, expressive tone. It suits food and travel vlogs, children's story videos and friendly channel intros.
Sample lines
Lines a creator would really use in Mandarin Chinese. Each one plays live in Xiǎoyàn's voice; copy any of them into the playground to change it.
YouTube intro
大家好,欢迎回到频道!今天带大家去成都一家开了三十年的小面馆。
Hi everyone, welcome back to the channel! Today, a little noodle shop in Chengdu that has been open for thirty years.
Story opening
很久很久以前,在一座开满桃花的小山村里,住着一只怕水的小鸭子。
Long, long ago, in a mountain village full of peach blossoms, there lived a little duck that was afraid of water.
Recipe Reel
只要十分钟,这道番茄炒蛋就能上桌,简单又下饭。
In just ten minutes this tomato and egg stir-fry is on the table, simple and great with rice.
Languages
A Pāṇini TTS voice is not locked to one language. The language comes from the text you type, so Xiǎoyàn can read any of the 250+ languages Pāṇini TTS supports, including text that mixes two languages.
Xiǎoyàn's accent carries over: a script in another language sounds like a Mandarin Chinese speaker reading it. That is useful for bilingual channels; for a native sound in another language, choose a voice recorded in it.
More on Mandarin Chinese text to speech. See text to speech in every language.
Mandarin Chinese voices
Nearby languages
Browse all 63 voices by language, make a clone of your own voice from a 10-second sample, start from the free voice-over scripts, or see everything for creators.
Commercial use
The full wording is in our terms of service.
YouTube
Yes, AI voices are allowed. What YouTube limits is mass-produced, repetitive content: videos made from a template with little original work. Its July 2025 update renamed that rule from “repetitious” to “inauthentic” content (YouTube’s monetisation policies).
Write your own script, add your own research or editing, and keep one consistent voice for the channel. Where a realistic AI voice could mislead viewers, use YouTube’s altered or synthetic content label. The monetisation decision is always YouTube’s.
FAQ
Yes. Play Xiǎoyàn on this page without an account, up to 220 characters at a time. A free account adds 10,000 characters and one voice clone, no card required. After that, Pāṇini TTS costs $0.03125 per 1,000 characters, the same rate for every language.
Yes, after free sign-up. The playground above plays Xiǎoyàn in your browser only, with no account. Sign up free and the dashboard saves each clip as a WAV file (Download audio), or the API returns MP3 when you set "output_format": "mp3".
Yes. Audio you generate, on the free tier or with paid credits, can be used on monetised YouTube channels, Shorts, Reels and in ads, with no attribution. YouTube limits mass-produced, repetitive videos, not AI voices, so write your own script and keep your edits original. The monetisation decision is YouTube's.
The audio you generate is yours to use, including commercially, with no attribution and no royalties to Sonex Labs. You are responsible for the script itself: if you read someone else's text, you need their permission.
Yes. Xiǎoyàn can read any of the 250+ languages Pāṇini TTS supports, because the language comes from the text you type, not from the voice. Xiǎoyàn's accent carries over, so a script in English sounds like a Mandarin Chinese speaker reading English. For a native sound in another language, pick a voice recorded in it from the full voice list.
10,000 free text-to-speech characters and one free voice clone that speaks every language, no card required. Every language is billed at the same rate.