Mandarin Chinese TTS audio on tts.audio runs on three MAI Voice 2 voices: Bo (male), Lan (female), and Mei (female). All three produce Standard Mandarin in Simplified Chinese, the variety used in mainland China, Singapore, and the Chinese diaspora, and the official language of the People's Republic of China (普通话). Bo supports all eighteen MAI expressive styles. Mei supports the same full set. Lan supports a reduced ten-style set covering the most common emotional colors. Mandarin is a tonal language with four tones (plus the neutral tone) that change word meaning. The MAI voices reproduce tones correctly based on the written Chinese characters and the context. Use cases for Mandarin TTS include e-learning localization for the mainland China market, accessibility audio for Chinese-language documentation, audiobook drafts, and pronunciation reference for English-speaking learners of Mandarin. For Cantonese, Traditional Chinese (Hong Kong, Taiwan), or other varieties, MAI does not ship dedicated voices; switch to the Gemini multilingual model. PDF upload handles Simplified Chinese characters natively.
Chinese (Mandarin, Simplified) TTS audio
3 neural voices on tts.audio. Free to play, no sign-up. PDF upload, MP3 download, expressive styles.
3 voices
Male
18 styles
Female
10 styles
Female
18 styles
Chinese (Mandarin, Simplified) TTS — frequently asked questions
Reviewed by Antonio Foti, Founder. Updated July 2026.
Do you support Cantonese or Traditional Chinese?
Not on MAI Voice 2; the three voices (Bo, Lan, Mei) are Mandarin-only with Simplified Chinese input. For Cantonese, Traditional Chinese (Hong Kong, Taiwan), Wu, Min, or other Chinese varieties, switch to the Gemini multilingual model.
Do the voices handle Mandarin tones correctly?
Yes. Mandarin has four tones (high, rising, dip-rise, falling) plus a neutral tone, and the MAI voices reproduce them based on the written characters and context. Because Chinese characters do not mark tone, the model relies on context to disambiguate polyphonic characters (多音字).
Which Mandarin voice should I pick?
Bo or Mei for narration and character work. Both support the full eighteen MAI expressive styles. Lan for steady reading with a reduced ten-style set, suited to neutral technical content.
Try Chinese (Mandarin, Simplified) TTS audio
Type up to 300 characters into the free TTS audio tool. No sign-up required to play.