Chinese AI Voice

Yunxi — free Mainland Chinese text to speech

Yunxi 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 Yunxi 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-YunxiNeural
Price
Free

How Yunxi sounds — measured

Median pitch

142 Hz

In the middle of 4 male Mainland Chinese voices

Intonation range

10.4 semitones

Steadier than typical for male Mainland Chinese voices (12.1)

Tone (spectral centroid)

2,978 Hz

Brighter, crisper tone than most of its group

Speaking rate

5.0 characters/s

The 3rd fastest of 14 Chinese voices on the same passage

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

How long your audio will be at 5.0 characters/s

1,000 characters
≈ 3 min 19 s
5,000 characters (free limit per render)
≈ 17 min
  • ↔Compared with Yunjian, Yunxi has a higher pitch (142 vs 122 Hz), steadier intonation (10.4 vs 16.8 semitones) and a brighter tone. Listen to Yunjian →
  • ↔Compared with Yunyang, Yunxi has a higher pitch (142 vs 106 Hz), steadier intonation (10.4 vs 13.8 semitones), a brighter tone and slower delivery (5.0 vs 5.4 characters/s). Listen to Yunyang →

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

What Yunxi fits best

  • Long narration and audiobooks

    Its intonation spans 10.4 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 142 Hz it sits above 2 of the 4 male Mainland Chinese voices, which sounds bright and approachable.

  • Fast-paced social video

    At 5.0 characters a second it fits more text into a short clip.

Use Yunxi in a conversation

With Multi-voice, Yunxi 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 Yunxi →

Formats, limits and help

Yunxi: quick answers

Measured from its audio, Yunxi has a median pitch 142 Hz (in the middle of 4 male Mainland Chinese voices); intonation range 10.4 semitones (steadier than typical for male Mainland Chinese voices (12.1)); tone (spectral centroid) 2,978 Hz (brighter, crisper tone than most of its group).
About 3 min 19 s. Yunxi reads about 5.0 characters a second, spaces included (measured on its sample passage), so the free limit of 5,000 characters per render is about 17 minutes of audio. Numbers, names and long pauses make it longer.