How to use SSML tags with Ondoku’s new AI voice | With 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 Speech Synthesis [Beta] - Emotionally Expressive Next-Generation TTS | Ondoku

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

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!

The new AI voices now support "SSML tags" for certain voice types.

This article introduces examples of how to use SSML tags.

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

Examples of using SSML tags with the new AI voice "OndokuBeta"

In "OndokuBeta", you can use SSML tags such as these, for example.

All sample voices use "Ellis."

<prosody rate="〇〇"> Tag | SSML tag for adjusting reading speed

By using the <prosody rate="〇〇"> tag, you can adjust the reading speed via SSML tags.

• <prosody rate="slow">: Speaks slowly.
• <prosody rate="fast">: Speaks quickly.

Reading style: "Bright and energetic"

This is important, so I will tell you slowly.We have no time, so I will tell you quickly.For comparison, I will tell you at normal speed.

<prosody pitch="〇〇"> | SSML tag for adjusting voice pitch

By using the <prosody pitch="〇〇"> tag, you can adjust the pitch of the reading voice via SSML tags.

• <prosody pitch="+2st">: Reads in a high voice (the numerical part can be changed).
• <prosody pitch="-3st">: Reads in a low voice (the numerical part can be changed).

Reading style: "Bright and energetic"

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

<emphasis level="〇〇"> | SSML tag for emphasizing a specified range

By using the <emphasis level="〇〇"> tag, you can emphasize specific parts using SSML tags.

• <emphasis level="strong">: Emphasizes the specified part.
• <emphasis level="moderate">: Emphasizes the specified part more weakly than <emphasis level="strong">.

Reading style: "Business"

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

<say-as interpret-as="digits"> | SSML tag for reading numbers digit-by-digit

By using the <say-as interpret-as="digits"> tag, you can read "1234" 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.

<break time="○○ms"/> is not reflected

The <break time="○○ms"/> tag, used for creating pauses (silent time) in speech, will not be reflected even if entered.

If you want to add silent time, you can create pauses by inserting punctuation, line breaks, or spaces.

It is also recommended to give instructions in the reading style, such as "Please read slowly while taking pauses."

Reading style: "Please read slowly while taking pauses" (Free description)

Hello, this is Ondoku. The voice has become more natural and human-like!

Related Articles on How to Use SSML Tags & Reading Styles

The SSML tags available in the previous version of Ondoku are explained in this article.

Please take a look at it as well.

What is Speech Synthesis Markup Language (SSML)? Usage in text-to-speech software and main code list. | 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 and the codes available in Ondoku.

In addition, detailed examples of the "reading style" for the new AI voice are introduced in this article.

Since it allows even more detailed expressions than SSML tags—such as emotional expression, personality, age, and dialects—why not try listening and experiencing it for yourself?

[Adjustment] Thorough explanation of reading styles for the new AI voice. More human-like emotional expression and acting are now possible for free! | Text-to-speech software Ondoku

Thorough explanation of voice adjustment techniques for the next-generation AI voice "Ondoku Beta." Freely control emotional expressions, age specification, character voices, dialects, and even foreign languages like English. Introducing tips and methods for adjusting AI-generated speech, which is free and OK for commercial use, with samples.

Why not utilize SSML tags with the new AI text-to-speech voice?

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

First, why not experience the new AI text-to-speech voice for yourself for free?

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

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

■ 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