Chinese AI Voice

Xiaoxiao — free Mainland Chinese text to speech

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

Female Mainland China accent Global voice Free

Make Xiaoxiao say your words

Voice details

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

How Xiaoxiao sounds — measured

Median pitch

243 Hz

In the middle of 4 female Mainland Chinese voices

Intonation range

9.0 semitones

Close to typical for its group

Tone (spectral centroid)

2,361 Hz

Balanced tone for its group

Speaking rate

4.9 characters/s

In the middle of 14 Chinese voices on the same passage

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

How long your audio will be at 4.9 characters/s

1,000 characters
≈ 3 min 25 s
5,000 characters (free limit per render)
≈ 17 min
  • ↔Compared with Xiaoni (Shaanxi), Xiaoxiao has a higher pitch (243 vs 218 Hz) and steadier intonation (9.0 vs 12.6 semitones). Listen to Xiaoni (Shaanxi) →
  • ↔Compared with Xiaobei (Liaoning), Xiaoxiao has a higher pitch (243 vs 209 Hz) and faster delivery (4.9 vs 4.2 characters/s). Listen to Xiaobei (Liaoning) →

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

What Xiaoxiao fits best

  • Tutorials, kids' content and friendly explainers

    At 243 Hz it sits above 2 of the 4 female Mainland Chinese voices, which sounds bright and approachable.

  • Fast-paced social video

    At 4.9 characters a second it fits more text into a short clip.

Use Xiaoxiao in a conversation

With Multi-voice, Xiaoxiao can read one character while Yunxi (a male 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 Xiaoxiao →

Formats, limits and help

Xiaoxiao: quick answers

Measured from its audio, Xiaoxiao has a median pitch 243 Hz (in the middle of 4 female Mainland Chinese voices); intonation range 9.0 semitones (close to typical for its group); tone (spectral centroid) 2,361 Hz (balanced tone for its group).
About 3 min 25 s. Xiaoxiao reads about 4.9 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.