Mandarin TTS tool
Free Chinese Text to Speech With Mandarin Subtitles Included
Paste simplified or traditional Chinese, pick a Mandarin voice or one of the blends and download the MP3 with subtitles cut at 16 characters a line. Mixed-in English is read too. No watermark, and no sign-up to listen.
0 bytes · 0 credits
You can edit or delete these tags directly in your script.
Voice
MeilinChinese · Female
Meilin · 1.00x · MP3
Make your own voice
The first voice sets pronunciation; the second only lends its character.
Primary voice
Meilin
Sets pronunciation and pacing.
Second voice
A fixed sample at your current mix and speed. No credits used.
Advanced settings
Output
0.5x1x2x
- Commercial use included on the free plan
- No watermark on any output
- Blend and preview voices without signing up
Voices for this page
Mandarin voices for announcements, lessons and reports
Four female and four male Mandarin voices, each with its own job, from brief announcements to lesson examples. The blends below add a richer timbre; play both free before you choose.
What you get
What this Chinese voice generator handles
Two writing systems, characters with several readings and English scattered through the text. Each one is handled.
Simplified and traditional, both read
Paste either script as it is. The engine reads traditional characters directly, so there is nothing to convert before you generate.
Setting a reading yourself
Set any reading yourself with the Pronounce as tag: type a character with the sound you want, such as 航 for the 行 in 銀行. The tag works the same way in simplified and traditional text, and your original characters stay on screen and in the subtitles.
Multi-reading characters caught
Paid plans include Tidy up script: the AI pass checks 行, 长, 还, 重, 得 and forty-odd others against their context and tags the intended reading.
How the fix works
The tidy pass reads each character in context and tags the intended reading, such as háng for 行 in a table row. It swaps in a stand-in character with the right sound for the voice only; your original text stays on screen and in the subtitles. You can add the same Pronounce as tag by hand for names and place names.
English inside Chinese text
Brand names, app menus and English terms in a Chinese script are read in place by the Mandarin voice, so nothing is skipped.
How mixed scripts are rendered
The script is split by writing system. The Chinese runs go through the Mandarin reader and the Latin runs through the English reader, and both are joined into one take by the same voice. Numbers, currencies and units are spelled out in Chinese by the tidy pass, so 40,000 is read as 四万.
Subtitles
Chinese subtitles that fit a phone screen
Chinese captions need short lines: 16 characters is the usual width for a vertical video. The SRT here is cut for that, straight from the same render as the audio.
- SRT and WebVTT with every job, on the free plan included
- Lines capped at 16 characters, with breaks at Chinese punctuation
- Each cue anchored to a real pause in the audio
- Edit a sentence, render again and the cues move with the audio
The worker detects the pauses in the finished audio and anchors each cue to them, so a caption changes as each sentence begins. Import the SRT and the MP3 together and the Chinese captions stay in step from the first line to the last.
Generate with subtitles1 00:00:00,160 --> 00:00:03,080 今天介绍一个新功能。 2 00:00:03,300 --> 00:00:06,520 先打开设置页面，找到右上角。 3 00:00:06,760 --> 00:00:09,400 点一下，字幕就生成好了。
Voice blends
Mandarin blends that borrow a richer timbre
Each blend keeps a Mandarin voice in charge of pronunciation and mixes in a second voice for character: Delaney's husk, Maya's clarity, a British lesson tone.
Magnetic Mandarin
Mandarin female with a throaty edge.
Meilin 50% + Delaney 50%
Husky announcer
Mandarin announcements with a throaty edge.
Ruoxi 20% + Delaney 80%
British-toned Mandarin
Mandarin pronunciation, British lesson timbre.
Ruoxi 10% + Freya 90%
Clear Mandarin
Mandarin with Maya's clarity.
Ruoxi 20% + Maya 80%
Instructional Mandarin
Mandarin with a British instructional tone.
Ruoxi 10% + Nell 90%
Soft Mandarin
Two Mandarin voices blended, gentler than either alone.
Ruoxi 20% + Tongtong 80%
Mandarin, Japanese tone
Mandarin pronunciation with a Japanese timbre.
Ruoxi 10% + Yukiko 90%
Magnetic Mandarin male
Mandarin male with a throaty edge.
Weilun 50% + Delaney 50%
Magnetic Mandarin male · lighter
Mandarin male, throaty edge held back.
Weilun 70% + Delaney 30%
Clear Mandarin male
Mandarin male with Maya's clarity.
Weilun 50% + Maya 50%
Mandarin course intro
Lesson opening in Mandarin.
Weilun 30% + Nora 70%
Mandarin report
Report-summary read, two male voices.
Zhiyuan 30% + Marcus 70%
How voice blending works
A blend puts a Mandarin voice in charge of every character's pronunciation and pacing, then mixes in the second voice's timbre at the percentage you choose. Because the second voice may come from any language, these blends add a fuller timbre while the Chinese stays correct. Preview a blend at no cost, then save the ones you like in this browser.
How it works
How to turn Chinese text to audio in three steps
STEP 01Paste the Chinese text
Simplified or traditional, with any English left in place. The generator shows the byte count and the exact credit cost before you submit.
STEP 02Pick a Mandarin voice or a blend, then tidy
Play the samples, choose a voice and run Tidy up script so multi-reading characters and numbers are read the way you meant.
STEP 03Download the MP3 and the subtitles
The audio and the SRT and VTT files appear in My Speech. Import them into your editor together and the captions land on each sentence.
Free plan, plainly
Free Mandarin TTS, and what a paid plan adds
Everything on this page works on the free plan. A paid plan adds priority rendering, WAV output and the tidy pass for multi-reading characters.
| Capability | Free | StarterMost Popular | Creator |
|---|---|---|---|
| Premium voices Try AI voice over | Not included | 1,600+ expressive voices in 40 languages1 credit per 400 bytes | 1,600+ expressive voices in 40 languages1 credit per 400 bytes |
| Plan and credits | |||
| Price | Free | $6.99 a month, or $69.99 a year | $15.99 a month, or $159.99 a year |
| Credits per month | 5 credits | 100 credits | 300 credits |
| Audio per month | Up to 50 minutes | Up to 1,000 minutes | Up to 3,000 minutes |
| Text per credit, standard voices | 10,000 bytes | 10,000 bytes | 10,000 bytes |
| Text per render | No limit | No limit | No limit |
| Credit packs | Not available | 100 credits for $5 that never expire | 100 credits for $5 that never expire |
| Voices | |||
| Voices | 50+ voices in 9 languages | 50+ voices in 9 languages | 50+ voices in 9 languages |
| Custom voices | Blend any two of 50+ voices | Blend any two of 50+ voices | Blend any two of 50+ voices |
| Blend control | Set the mix in 10% steps | Set the mix in 10% steps | Set the mix in 10% steps |
| Cross-language blends | Included | Included | Included |
| Script editing | |||
| Speed | 0.5x to 2x | 0.5x to 2x | 0.5x to 2x |
| Pauses and slow down | Add pauses up to 5 seconds, slow any phrase | Add pauses up to 5 seconds, slow any phrase | Add pauses up to 5 seconds, slow any phrase |
| Pronunciation | Set how any word is read | Set how any word is read | Set how any word is read |
| Script tidy (AI) | Not available | Included | Included |
| Files and rights | |||
| Subtitles | SRT and VTT | SRT and VTT | SRT and VTT |
| Output format | MP3 | MP3 and WAV | MP3 and WAV |
| Queue | Free queue, no promised time | Skips the free queue | Skips the free queue |
| Renders at once | 1 | Several | Several |
| File retention | 72 hours | 30 days | 30 days |
| Watermark | None | None | None |
| Commercial use | Included | Included | Included |
Minutes per credit are based on standard voices reading English at normal speed.
How credits are counted
Each credit covers 10,000 bytes of text with standard voices and makes up to 10 minutes of audio. With premium voices, each credit covers 400 bytes. Letters in English and most European languages take one byte each, while characters in scripts such as Chinese, Japanese or Hindi take three. Credits are refunded in full if a job fails.
FAQ
Questions about Chinese TTS, answered
Does it support traditional Chinese?
Yes. Traditional and simplified characters are both supported natively, with no conversion step. Set any reading yourself with the Pronounce as tag.
How does it handle characters with multiple pronunciations?
Tidy up script scans about fifty common multi-reading characters, 行, 长, 还, 重 and so on, and tags the intended reading from context. The Pronounce as tag lets you set any other reading yourself.
How many credits does a Chinese script use?
One credit makes up to 10 minutes of audio, and a longer script adds one credit per extra block. The generator shows the exact credit cost before you click generate.
Can I get Chinese subtitles with correct timing?
Yes. Each cue is anchored to a real pause in the audio and cut at 16 characters a line, so the captions change as each sentence is spoken.
Are the voices male or female?
Both: four female and four male Mandarin voices, plus blends that add Delaney's husk or Maya's clarity.
Can I mix Chinese and English in one text?
Yes. Keep Chinese as the main script and the English words are read in place by the Mandarin voice.
Generate your Mandarin audio
Paste the text, pick a voice or a blend and download the MP3 with Chinese subtitles.