Chinese AI Voice
HsiaoYu — free Taiwanese Chinese text to speech
HsiaoYu is a free female Taiwanese Chinese AI voice — a Microsoft neural voice. Type your text below to hear it read aloud, then download the audio. No account needed.
Make HsiaoYu say your words
Sample: “你好,欢迎你!你有没有想过,你的稿子变成真正的配音会是什么样子?这个声音可以为你朗读故事、教程和产品视频——可以温柔清晰,也可以充满活力。”
Who is talking?
What do they say?
How to use Multi-voice
· Usually 5–20 seconds. Please keep this tab open and don't click again.
Subtitles preview · first 30 seconds
Next: YouTube title & tags from this text · transcribe a video
Voice details
- Language
- Chinese
- Accent
- Taiwanese
- Gender
- Female
- Type
- Global · Microsoft neural
- Download
- MP3
- Speed
- Natural pace
- Voice ID
zh-TW-HsiaoYuNeural- Price
- Free
How HsiaoYu sounds — measured
Median pitch
202 Hz
The lowest of 8 female Chinese voices
Intonation range
9.1 semitones
Close to typical for its group
Tone (spectral centroid)
2,537 Hz
Balanced tone for its group
Speaking rate
3.9 characters/s
The 2nd slowest of 14 Chinese voices on the same passage
How long your audio will be at 3.9 characters/s
- 1,000 characters
- ≈ 4 min 14 s
- 5,000 characters (free limit per render)
- ≈ 21 min
- ↔Compared with HsiaoChen, HsiaoYu has a lower pitch (202 vs 242 Hz) and slower delivery (3.9 vs 4.7 characters/s). Listen to HsiaoChen →
- ↔Compared with Xiaobei (Liaoning), HsiaoYu has a similar pitch (202 vs 209 Hz). Listen to Xiaobei (Liaoning) →
Measured by SpeakScribe, October 2026 · How we measure · Every Chinese voice side by side
What HsiaoYu fits best
Documentaries and serious explainers
At 202 Hz it sits below 7 of the 8 female Chinese voices, which gives a calm, authoritative sound.
Lessons and step-by-step guides
At 3.9 characters a second it is one of the slower Chinese readers — easy to follow.
Use HsiaoYu in a conversation
With Multi-voice, HsiaoYu 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.