Chinese AI Voice

Yunxia — free Mainland Chinese text to speech

Yunxia is a free male Mainland Chinese AI voice — a Microsoft neural voice. Type your text below to hear it read aloud, then download the audio. No account needed.

Male Mainland China accent Global voice Free

Make Yunxia say your words

Voice details

Language
Chinese
Accent
Mainland China
Gender
Male
Type
Global · Microsoft neural
Download
MP3
Speed
Natural pace
Voice ID
zh-CN-YunxiaNeural
Price
Free

How Yunxia sounds — measured

Median pitch

336 Hz

The highest of 4 male Mainland Chinese voices

Intonation range

10.2 semitones

Steadier than typical for male Mainland Chinese voices (12.1)

Tone (spectral centroid)

2,245 Hz

Balanced tone for its group

Speaking rate

4.7 characters/s

In the middle of 14 Chinese voices on the same passage

Pitch across the sample passage dashed line = Yunxia’s median

How long your audio will be at 4.7 characters/s

1,000 characters
≈ 3 min 35 s
5,000 characters (free limit per render)
≈ 18 min
  • ↔Compared with Yunxi, Yunxia has a higher pitch (336 vs 142 Hz), a warmer tone and slower delivery (4.7 vs 5.0 characters/s). Listen to Yunxi →
  • ↔Compared with Yunjian, Yunxia has a higher pitch (336 vs 122 Hz) and steadier intonation (10.2 vs 16.8 semitones). Listen to Yunjian →

Measured by SpeakScribe, October 2026 · How we measure · Every Chinese voice side by side

What Yunxia fits best

  • Long narration and audiobooks

    Its intonation spans 10.2 semitones against 12.1 for male Mainland Chinese voices — steady enough to stay easy on the ear over many minutes.

  • Tutorials, kids' content and friendly explainers

    At 336 Hz it sits above 3 of the 4 male Mainland Chinese voices, which sounds bright and approachable.

  • Lessons and step-by-step guides

    At 4.7 characters a second it is one of the slower Chinese readers — easy to follow.

Use Yunxia in a conversation

With Multi-voice, Yunxia can read one character while Xiaoxiao (a female Chinese voice) reads another — the whole dialogue comes back as one MP3 with even volume between speakers. A free account can make 3 two-speaker dialogues a month; paid plans allow up to 4 speakers on Starter.

Try a dialogue with Yunxia →

Formats, limits and help

Yunxia: quick answers

Measured from its audio, Yunxia has a median pitch 336 Hz (the highest of 4 male Mainland Chinese voices); intonation range 10.2 semitones (steadier than typical for male Mainland Chinese voices (12.1)); tone (spectral centroid) 2,245 Hz (balanced tone for its group).
About 3 min 35 s. Yunxia reads about 4.7 characters a second, spaces included (measured on its sample passage), so the free limit of 5,000 characters per render is about 18 minutes of audio. Numbers, names and long pauses make it longer.