How to Use SSML Tags with New Ondoku AI Voices | Audio Samples

Thank you for always using Ondoku.

A new AI voice, "OndokuBeta," which can read aloud "more naturally" and "more human-like," is now available on Ondoku!

AI Voice Synthesis [Beta] - Expressive Next-Generation TTS | Ondoku

Generate emotionally expressive audio with the latest AI technology. Next-generation text-to-speech with 25 types of voices to choose from. Achieve natural speech through speed/pitch adjustment and reading style specification.

With Ondoku's new AI voice, you can now freely describe the reading style to achieve a wide range of expressions, including emotions, acting, age, and dialects!

Furthermore!

Depending on the type, the new AI voice can now also use "SSML tags."

In this article, we will introduce examples of using SSML tags.

Why not try out various expressions with the new AI voice yourself?

Examples of Using SSML Tags with the New AI Voice "OndokuBeta"

"OndokuBeta" allows you to use SSML tags such as these.

All sample voices use "Ellis."

Tag | SSML Tag for Adjusting Reading Speed

By using the tag, you can adjust the reading speed with an SSML tag.

• : Speaks slowly.
• : Speaks quickly.

Reading Style: "Bright and Energetic"

This is important, so I will tell you slowly.Since we are short on time, I will tell you quickly.For comparison, I will tell you at normal speed.

| SSML Tag for Adjusting Voice Pitch

By using the tag, you can adjust the pitch of the reading voice with an SSML tag.

• : Reads in a high voice (the numerical part can be changed).
• : Reads in a low voice (the numerical part can be changed).

Reading Style: "Bright and Energetic"

I will speak brightly in a slightly higher voice.Conversely, I will speak calmly in a slightly lower voice.Finally, I will speak at normal pitch.

| SSML Tag for Emphasizing a Specified Range

By using the tag, you can emphasize sections specified by the SSML tag.

• : Emphasizes the specified section.
• : Emphasizes the specified section more weakly than .

Reading Style: "Business"

This item is important, but the next item is even more important.

| SSML Tag for Reading Digits Separately

By using the tag, you can read "1234" digit by digit as "one two three four" instead of "one thousand two hundred thirty-four."

Reading Style: "Bright and Energetic"

The inquiry number is 03 1234 5678.

The Tag Cannot Be Used

The tag, used to create pauses (silent time) in the audio, is not reflected in the new AI voices.

Furthermore, please do not enter , as it may cause the text following the tag to not be read aloud and disappear.

Also, you cannot insert pauses by entering many punctuation marks like "....", inserting multiple line breaks, or writing something like "(3-second pause)."

*Note: For conventional voices, you can still insert pauses with the SSML tag as before.

Related Articles on How to Use SSML Tags & Reading Styles

This article explains the SSML tags available in the conventional "Ondoku."

Please take a look at it as well.

What is Speech Synthesis Markup Language (SSML)? How to use it in text-to-speech software and a list of main codes. | 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 in detail how to use SSML in Ondoku and its codes.

In addition, this article provides detailed examples of how to use "reading styles" for the new AI voice.

It allows for even more detailed expressions than SSML tags, such as emotions, personality, age, and dialects. Why not listen and experience it for yourself?

[Vocal Tuning] Thorough Explanation of Reading Styles for the New AI Voice. More human-like emotional expression and acting now possible for free!

A thorough explanation of vocal tuning techniques for the next-generation AI voice "Ondoku Beta." Free control over emotional expressions of joy, anger, sorrow, and pleasure, age specification, character voices, dialects, and foreign languages like English. We will introduce tips and methods for tuning AI reading voices, which are free and okay for commercial use, along with samples.

Why Not Utilize SSML Tags with the New AI Reading Voice?

With the AI voice "OndokuBeta," which can now read aloud more human-like and naturally, a wider range of expressions is possible by using SSML tags.

First, why not experience the new AI reading voice for free yourself?

AI Voice Synthesis [Beta] - Expressive Next-Generation TTS | Ondoku

Generate emotionally expressive audio with the latest AI technology. Next-generation text-to-speech with 25 types of voices to choose from. Achieve natural speech through speed/pitch adjustment and reading style specification.