Common errors and workarounds when using Speech Markup Language (SSML)
July 28, 2022
Ondoku uses Speech Markup Language (SSML) to adjust the interval and change the reading.
SSML is a very useful feature that many people use because it allows you to adjust the interval as you wish.
Learn more about SSML.
Errors that are likely to occur when using SSML
You may also run into errors when using SSML.
The most common error is
- Skipping sentences
- High / low error after break time code
The cause of these errors is currently being investigated.
Causes and workarounds for SSML errors
Currently known causes
- Deprecated environment where the browser is internet explorer, Microsoft Edge, etc.
- Number of characters over 3000
- Example of using symbols when using SSML & "
Etc.
There are three workarounds for these errors.
- Use with Google Chrome, the recommended environment
- Read aloud with a small number of characters and combine
- Do not use symbols
1. 1. Use with Google Chrome, the recommended environment
The recommended environment for Ondoku is Google Chrome.
You can use it with other browsers, but it may be error-prone.
2. 2. Read aloud with a small number of characters and combine
You can avoid the error by reading aloud with a small number of characters.
If a short MP3 file is useless, try connecting the MP3 file later.
Although it is an external site, you can easily combine mp3 files with each other on this site.
External site: 123APPS
- Access 123APPS
- Click Add Track
- Put the MP3 files you want to combine
- Click Join
- Save the finished file
3. 3. Do not use symbols
Symbols can have different meanings when using SSML.
Therefore, it may interfere with SSML and read aloud poorly.
If the symbol cannot be used, it cannot be read aloud.
No, that's not the case.
By replacing the symbols with hiragana , katakana , or the alphabet , you can read aloud as you intended.
For example
& Can be written as and.
You can replace it with punctuation, such as "without using."
Other workarounds will be posted at any time.
In addition, we will report to this page as soon as the cause of the error is known.
We are also looking forward to reporting that an error has occurred due to such a workaround.
I will add it to this article.
■ AI voice synthesis software "Ondoku"
"Ondoku" is an online text-to-speech tool that can be used with no initial costs.
- Supports approximately 50 languages, including Japanese, English, Chinese, Korean, Spanish, French, and German
- Available from both PC and smartphone
- Suitable for business, education, entertainment, etc.
- No installation required, can be used immediately from your browser
- Supports reading from images
To use it, simply enter text or upload a file on the site. A natural-sounding audio file will be generated within seconds. You can use voice synthesis up to 5,000 characters for free, so please give it a try.
Email: ondoku3.com@gmail.com
"Ondoku" is a Text-to-Speech service that anyone can use for free without installation. If you register for free, you can get up to 5000 characters for free each month. Register now for free