Chinese Text to Speech: Free Mandarin AI Voice, MP3
Type or paste Chinese text, pick one of 4 natural Mandarin voices and download it as an MP3, made in seconds on any phone or computer. Free with no sign-up.
Your text is only used to make the voice. How?
In German, Arabic, Japanese and Chinese, the voice is made on our server in seconds: your text is sent there to be spoken and isn't kept. In the other languages, the AI voice runs in your browser and nothing is sent.
0 / 10,000 characters
Free, no sign-up, no watermark. The voice is made in seconds.
How to turn Chinese text into speech
Type or paste Chinese text
Simplified or traditional characters, up to 10,000 characters at a time.
Pick a voice
Tap ▶ to hear the 4 Mandarin voices first, then choose a speed.
Make the voice
The voice is made on our server in seconds, on a phone or a computer.
Listen and download
Play it on the page and download it as an MP3 (or WAV), or send it straight to WhatsApp from a phone.
What people use it for
Mandarin voice-overs for videos, Shorts and Douyin or TikTok clips; narration for lessons and stories; listening practice for Chinese learners; and messages read out.
For a video, put the MP3 in Audio to Video to add a background, or in CapCut or any video editor.
How the Chinese voice is made
The voices come from Kokoro, an open-source AI speech model that's free to use, even commercially, reading Mandarin with its tones. The voice is made on our server in seconds (through DeepInfra), on phones and computers alike, and your text isn't kept.
5 minutes of speech a day are free; ClipUtils Pro makes as much as you like.
Features
Natural Mandarin voices
Xiaoxiao, Xiaoyi, Yunxi and Yunjian. Hear each one before you choose.
MP3 download
Download the speech as an MP3 for any phone, editor or app, or as a WAV for editing. No watermark, no sign-up.
Private
Your text is spoken on our server in seconds and never kept. No account, nothing saved.
Other languages too
Switch to English (8 American and British voices), Hindi, Spanish, Portuguese, French, German, Italian, Arabic, Japanese or Chinese on the same page.
Frequently asked questions
Is this Chinese text to speech free?
Yes, for 5 minutes of speech a day, with no sign-up or watermark. ClipUtils Pro makes as much as you like, in seconds.
Can I use the voice on YouTube?
Yes. The voices come from Kokoro, an open-source model under the Apache 2.0 license, so the audio can be used in videos, including monetized ones.
Is my text uploaded?
Yes, to be spoken: the voice is made on our server in seconds (through DeepInfra), and your text isn't kept.
How long does it take?
Seconds, on a phone or a computer: the voice is made on our server.