Jump to content
Learn Chinese in China

Quick Canto TTS Voices Comparison


Recommended Posts

Which one do you like best or is most intelligible and correct: 1, 2 or 3? Each sound file contains three voices roughly matched for speed and pitch.



tts test.mp3



tts test2.mp3


To me, errors like using a wrong tone must count heavily against. And I find changes in speed worse than changes in volume. On different sentences they take turns in their rankings, but I think one of them is definitely the worst and I posted to tell you about it. (Don't know how to make a "spoiler" so I'll tell you later which is which.)

Link to comment
Share on other sites

Site Sponsors:
Pleco for iPhone / Android iPhone & Android Chinese dictionary: camera & hand- writing input, flashcards, audio.
Study Chinese in Kunming 1-1 classes, qualified teachers and unique teaching methods in the Spring City.
Learn Chinese Characters Learn 2289 Chinese Characters in 90 Days with a Unique Flash Card System.
Hacking Chinese Tips and strategies for how to learn Chinese more efficiently
Popup Chinese Translator Understand Chinese inside any Windows application, website or PDF.
Chinese Grammar Wiki All Chinese grammar, organised by level, all in one place.

Thank you Shelley.


The first voice is Google TTS.


The second voice, and winner by a small margin I think, is Microsoft Tracy, free with Windows 8.1 (?) as far as I know. It sounds less human but its delivery is steadier most of the time, so I think it is the most intelligible.


The third voice, and to me easily the worst, is Nuance Sin-Ji. I paid for it some time ago because I was initially impressed but upon close listening I don't like it. At least on the texts that I've tried it gets more tones wrong and has more artifacts. I'll stop at that.

Link to comment
Share on other sites

Thank you for your replies. 

I agree that #1, Google TTS, is the best. I didn't mind that MS Tracy sounds less human, and being a SAPI voice I can control it on the desktop, but Google TTS's consonants are generally better-formed. Want to hear a good representative example?


(Aside from MS Tracy possibly parsing this dou6 seoi2 wrongly as the word dok6 seoi2) Google TTS is better in several places, most noticeably in the final g.



sip3 si6 jat1 baak3 dou6 seoi2 zau6 wei5 gwan2.

Google vs Tracy.mp3


Link to comment
Share on other sites

Join the conversation

You can post now and select your username and password later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.

Click here to reply. Select text to quote.

×   Pasted as rich text.   Paste as plain text instead

  Only 75 emoji are allowed.

×   Your link has been automatically embedded.   Display as a link instead

×   Your previous content has been restored.   Clear editor

×   You cannot paste images directly. Upload or insert images from URL.


  • Create New...