Text to speech · 普通话 / 國語
Pāṇini TTS speaks Mandarin Chinese from Simplified or Traditional characters, with its four tones and neutral tone, in the voice of Xiǎoyàn, a native Mandarin speaker.
这里是Sonex，提醒您本月账单三千二百元，还款日是十一月五日。您可以直接在App里一键还款，还款成功后我们会发短信给您确认。
Voices
Free to play in your browser without an account, up to 220 characters at a time. To save the audio as a file, sign up free for 10,000 characters and one voice clone, no card required: the dashboard saves WAV and the API returns MP3.
Making a video? See AI voice-over for YouTube and Reels. The audio is yours to use on monetised channels.
Last verified 24 October 2026
Xiǎoyàn, a native Mandarin Chinese platform voice, reads the playground above. Any Sonex Labs voice can also read Mandarin Chinese, keeping its own accent, and a voice cloned from a 10-second recording of a Mandarin Chinese speaker carries that speaker's accent.
Sign up free, then send Mandarin Chinese text to the API with "output_format": "mp3" and save the file, or generate clips in the dashboard and download them. Scripts longer than the playground's 220 characters work the same way.
About Mandarin Chinese
Mandarin has four tones plus a neutral tone, and the same syllable changes meaning with each: mā (妈, mother), má (麻, hemp), mǎ (马, horse), mà (骂, to scold). Tones also shift in context: two third tones in a row change the first, so 你好 is said ní hǎo, and 一 and 不 change tone depending on what follows. Characters carry no tone marks, so the voice has to know each word. Some characters have more than one reading, such as 行 in 银行 (bank, háng) and 不行 (no good, xíng).
Mainland China and Singapore write Simplified characters (说话); Taiwan uses Traditional (說話), and vocabulary differs too: 视频 versus 影片 for video, 出租车 versus 計程車 for taxi. Customer service speech is courteous but brisk, opening with 您好 and using 请 (please). Messages mix in English and Latin letters, such as APP, VIP and Wi-Fi. The samples are read by Xiǎoyàn, a native Mandarin platform voice.
Use cases
Online stores and couriers announce delivery times and pickup codes to customers in China, Singapore and Malaysia.
Banks and payment apps read bill reminders and security notices in courteous Mandarin.
Airlines, hotels and tour operators serve Mandarin-speaking travellers across Asia and beyond.
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.
Voice cloning
Clone your voice from a 10-second recording. Your clone speaks Mandarin Chinese, and every other language Pāṇini supports, in your own voice. The language comes from the text you type, so a clone recorded in English or Hindi can read a Mandarin Chinese script.
Your accent comes with it: a clone sounds like you speaking Mandarin Chinese, not like a different native speaker. Every free account includes one voice clone. Clone only your own voice, or a voice whose owner has agreed.
API
One request returns Mandarin Chinese audio as MP3. The language is detected from the text, so no language setting is needed. Pāṇini TTS starts streaming audio in under 200 ms (time to first byte).
1curl https://api.sonexlabs.com/v1/speech \2 --header 'Authorization: Bearer YOUR_API_KEY' \3 --header 'Content-Type: application/json' \4 --data '{"text": "这里是Sonex，提醒您本月账单三千二百元，还款日是十一月五日。您可以直接在App里一键还款，还款成功后我们会发短信给您确认。", "output_format": "mp3"}' \5 --output mandarin-chinese.mp3FAQ
Yes. The playground on this page reads up to 220 characters of Mandarin Chinese at a time with no account. Sign up free for 10,000 characters and one voice clone, no card; after that it costs $0.03125 per 1,000 characters.
Yes, after free sign-up. The playground on this page plays audio in your browser only, up to 220 characters at a time, so you can check the voice first. Sign up free (10,000 characters and one voice clone, no card): the dashboard saves each clip as a WAV file with Download audio, and the API returns MP3 when you set "output_format": "mp3".
Yes. Send whichever your customers use; the voice speaks standard Mandarin from both.
Yes. Xiǎoyàn is a native Mandarin voice. Any Sonex Labs voice can also speak Mandarin, and you can clone your own from a 10-second sample.
Yes. Words like APP and VIP inside a Chinese sentence are read in the same voice.
$0.03125 per 1,000 characters, the same as every language.
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. A Sonex voice clone is not tied to the language it was recorded in. Type a Mandarin Chinese script and your clone reads it in your own voice, with Mandarin Chinese pronunciation. Your natural accent carries over, so it sounds like you speaking Mandarin Chinese.
More languages
See text to speech in every language, the full list of 250+ languages, pricing, the Pāṇini TTS API, or transcribe Mandarin Chinese audio with Valmiki speech to text.
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.