How to adjust pauses and blank time in Ondoku narration [2 methods]

Hello, thank you for always using Ondoku.

One of the needs of those who use Ondoku is the desire to "add a bit more of a pause."

While we aren't very conscious of pauses in daily conversation, having Ondoku read text makes us realize once again just how important they are.

Those who master the pause, master the world.

This time, I will introduce how to add pauses.

If you want to adjust "pauses" to add a little space, there are two types of adjustment methods:

1. Punctuation marks
2. SSML

Adjusting pauses with punctuation marks

Adjusting pauses with punctuation marks allows you to slightly adjust the interval using symbols such as:

• 、
• 。
• …

However, this is not something that can "guarantee a pause of exactly X seconds."

With punctuation marks, you can only adjust the pause by about one breath's worth.

To adjust the pause,

• ",,,,,,,"
• "......."
• "………………"

some people try to adjust the pause by typing punctuation marks many times, but there is no point in using multiple punctuation marks.

Ondoku is not designed to adjust pauses based on the number of punctuation marks.

Using the small "tsu" like "っっっっっ" has a slight effect of making the pause interval a bit longer.

However, methods that use many punctuation marks or small "tsu" characters consume a large number of characters in the character count, even though they cannot guarantee a precise pause.

When you want a longer pause or a guaranteed blank interval, please use SSML tags.

How to reliably get a pause when you want X seconds (SSML tags)

If you want to create a reliable pause, the recommended method is

using SSML tags to adjust the interval.

When using this method, please keep the number of characters read at one time to less than 3000. Errors are more likely to occur with 3000 characters or more.

What is SSML?
SSML is a speech markup language. HTML is famous as another markup language of the same kind.

You might think, "Markup for something invisible?", but it allows you to control the utterance of machine voices.

The way to write SSML is similar to HTML, so if you have ever created a website, you will likely understand it quickly.

SSML is also explained in detail in this article.

What is Speech Synthesis Markup Language (SSML)? Usage and main code list for text-to-speech software. | Text-to-speech software Ondoku

SSML stands for Speech Synthesis Markup Language. By writing SSML code, you can further control Ondoku's speech. We will introduce how to use SSML in Ondoku and provide detailed code examples.

When creating a pause with SSML, you write the tags as follows.

To make the pauses easy to understand, I have inserted intervals of 1 to 5 seconds.

Created By ondoku3.com

S is an abbreviation for seconds.
By increasing the number before the S, you can make the pause in that part longer.
MS stands for milliseconds.

Only two tags are needed to create a pause.

This tag is necessary to instruct Ondoku that "this text uses SSML."

Please add it at the beginning and the end of the text respectively.

This tag means break time or rest.

By putting your preferred number in the ○, you can take a pause of that length.

The "s" is an abbreviation for seconds.

1s means 1 second.

ms represents milliseconds.

"1000ms = 1s," so 1000 milliseconds is the same as 1 second.

*The maximum pause that can be specified with SSML tags is 10 seconds. If a longer time is set, it will be rounded to 10 seconds.

Currently, the SSML tags supported in all languages are:

Only these two types of tags. Other tags may not be used depending on the language or voice type. Please be aware of this in advance.
*The behavior of the tag before the text depends on the voice specification, and operation cannot be guaranteed.

I don't want to use them because they increase the character count.

Only these two tags do not count towards the character count.

However, if there is even a single character error, such as an extra space within the tag, the tag will not be recognized normally. In that case, characters will be counted.

Points to note when using SSML

1. Keep it under 3000 characters
2. Do not use extra symbols
3. If there is even a single character error in the tag, it cannot be read
4. Do not specify an excessively long number of seconds
5. Do not use the tag before the text

1. Keep it under 3000 characters

When using SSML, please keep the number of characters read at one time to less than 3000. If it is 3000 characters or more, an error will occur.

2. Do not use extra symbols

When using SSML, please do not include symbols in the text to be read.

In particular, < > 「 」 & are symbols that cannot be used, so if they are included in the text you want to read, it will not be possible to read it.

Please perform the reading with other symbols also removed.

3. If there is even a single character error in the tag, it cannot be read

SSML is the same as programming code; if there is even a single character error, it cannot be read.

An extra space in the tag, an extra slash, or a single letter wrong in the alphabet notation.

Just that alone will make it impossible to read.

We recommend copying and pasting tags from the website.

Tags are very delicate. Please be very careful when writing tags yourself.

4. The maximum specified pause/blank is 10 seconds

In Ondoku, the pause/blank that can be specified using SSML tags is up to 10 seconds.

If a time longer than that is specified, it will be read as a 10-second pause/blank.

5. Do not use the tag before the text

The behavior of the tag before the text depends on the voice specification, and operation cannot be guaranteed.

Example: I want to create a 5-second pause at the beginning

↑ This kind of usage is not possible due to the specifications.

For other errors when using SSML, please see here.

Common errors and workarounds when using Speech Synthesis Markup Language (SSML) | Text-to-speech software Ondoku

You can adjust pauses and change the way text is read by using Speech Synthesis Markup Language (SSML).

We have introduced two methods for adding pauses in Ondoku reading.

SSML might look difficult at first glance, but it is very easy once you use it. If you just want to add a pause, it is the easiest and most recommended method.

Please give it a try!

■ 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.

Text-to-speech software "Ondoku" can read out 5000 characters every month with AI voice for free. You can easily download MP3s and commercial use is also possible. If you sign up for free, you can convert up to 5,000 characters per month for free from text to speech. Try Ondoku now.

HP: ondoku3.com
Email: ondoku3.com@gmail.com