Listen to 25 types of next-generation AI Japanese voice samples for free. Also supports multi-language text-to-speech.

Thank you for always using Ondoku.

We are excited to announce the release of "Ondoku Beta," a new next-generation AI voice that can read aloud "more naturally" and "more human-like"!

By adopting state-of-the-art voice synthesis AI, the new voices feature:

• Richer emotional expression
• The ability to freely specify voice styles such as "bright voice" or "narration"
• Multilingual support for English and other foreign languages for all voices

This makes it even more convenient to create high-quality text-to-speech audio.

In this article, we will provide a detailed explanation of the new voice samples for the next-generation AI voice and how to use the latest features.

[Free] Next-Generation AI Voice "Ondoku Beta" is Here!

Ondoku's new AI reading voice "Ondoku Beta" is available here.

Why not experience the next-generation AI text-to-speech voice capable of rich emotional expression in Japanese and English for yourself?

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

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

Types of Next-Generation Reading Voices (Speakers) (Japanese, English, and Multilingual Support)

Ondoku's new AI reading voices include both female and male voices.

• Female: 12 types
• Male: 13 types

Every voice (speaker) has its own unique reading style and can read aloud with rich emotional expression in a voice that sounds just like a human.

Furthermore, every type of voice supports multilingual reading!

You can perform multilingual reading in languages from all over the world, including Japanese and English.

Listen to Ondoku's Next-Generation AI Voice Samples

Now, let's introduce the voice samples for Ondoku's new AI voice.

The sample text read aloud is:

こんにちは、Ondokuです。
より自然で、より人間らしい声になりました！

This is a Japanese sample sentence.

The reading settings used to create the audio are:

• Speed: Normal (1x)
• Pitch: Normal (0)
• Reading Style: Bright and energetic

It allows for reading that is more natural and human-like than ever before, so please give it a listen!

New AI Voice Samples (25 Types)

12 Female Voices Reading Japanese Sample Sentence

13 Male Voices Reading Japanese Sample Sentence

[Emotional Expression Possible] Next-Generation AI Voice Setting Items (Reading Style, Quality, Speed, Pitch)

Ondoku's new AI voices allow you to adjust the reading audio freely to suit your preferences and purpose!

The items you can set and adjust are:

• Reading Style
• Speed
• Pitch

Here is an explanation of each setting item.

Reading Style | It is now possible to freely specify styles and emotional expressions!

The biggest update for the newly introduced next-generation AI voices is the ability to freely specify the reading style!

The reading style is specified in this section of the new voice reading page.

Styles can be specified in two ways: pre-registered options and a free-text input box.

How to specify a style from pre-registered options

First is the method of choosing a reading style from the pre-registered options.

There are 6 options registered in the dropdown menu.

• News-style
• Narration
• Bright and energetic
• Calm
• Business
• Story-like

If you want to generate audio immediately for video production, language teaching materials, or in-store announcements, simply choose a reading style from these options.

Audio samples for each reading style (Japanese)

The audio is read by "Achernar".

Audio sample read in "News-style"

Audio sample read in "Narration"

Audio sample read in "Bright and energetic"

Audio sample read in "Calm"

Audio sample read in "Business"

Audio sample read in "Story-like"

How to specify style and emotional expression by freely describing the reading method

Furthermore!

It is now possible to freely describe and instruct the reading style to match the purpose and content of the audio usage.

To instruct the reading style, write the instruction details in the "Reading Style (Optional)" text box.

For example, you can read aloud with rich emotional expression like this.

All audio is read by "Achernar".

Audio sample with instruction "Please read aloud in a whisper"

こんにちは、Ondokuです。より自然で、より人間らしい声になりました！

Audio sample with instruction "Please read aloud in an 80-year-old voice"

こんにちは、Ondokuです。より自然で、より人間らしい声になりました。

Audio sample with instruction "Please read aloud in Osaka's Kansai dialect"

こんにちは、Ondokuや。もっと自然で、もっと人間らしい声になったで！

In this way, reading is now possible in a much wider range of styles than previous reading voices!

Why not try synthesizing speech freely using the new AI voices yourself?

Adjustment of Reading Speed and Pitch (Voice Height)

On Ondoku's new reading page, you can also adjust the reading speed and pitch (voice height).

Reading speed can be adjusted in 5 stages:

• Very slow (0.5x)
• Slightly slow (0.75x)
• Normal (1x)
• Slightly fast (1.25x)
• Very fast (1.5x)

You can use a slower voice for language learning or shadowing, or a faster voice for entertainment videos, adapting it to various expressions.

Additionally, pitch (voice height) can be adjusted in 5 stages:

• Very low (-1)
• Slightly low (-0.5)
• Normal (0)
• Slightly high (0.5)
• Very high (1)

*The function to change reading speed and pitch is currently being adjusted. The adjustment range and setting method may change in the future.

Ondoku's New AI Voice is Multilingual! Supports Multilingual Reading

Ondoku's new AI voice can read aloud in languages other than Japanese as is!

All voices support multilingual reading for English and other foreign languages!

For example, when reading in English, French, Spanish, Korean, and Chinese, it sounds like this.

All audio is read by "Achernar".

English
Instruction: "Please read aloud brightly and energetically."

Hello, I'm Ondoku.
The voice has become more natural and more human-like!

French
Instruction: "Veuillez lire à voix haute avec enthousiasme et énergie."

Bonjour, je suis Ondoku. La voix est devenue plus naturelle et plus humaine !

Spanish
Instruction: "Por favor, lee en voz alta con alegría y energía."

Hola, soy Ondoku. ¡La voz se ha vuelto más natural y más humana!

Korean
Instruction: "밝고 힘차게 읽어주세요."

안녕하세요, Ondoku입니다. 더 자연스럽고, 더 인간다운 목소리가 되었습니다!

Chinese
Instruction: "请明快有活力地朗读。"

你好，我是Ondoku。声音变得更自然、更人性化了！

Notes on Multilingual Reading with Next-Generation AI Voice

When performing multilingual reading in English or other foreign languages with the new AI voice, it is necessary to specify the reading style in the language used for the reading.

In these samples as well, instructions for the reading style are given in each respective language.

If you give an instruction like "Please read aloud brightly and energetically" in Japanese, the reading will result in Katakana-style pronunciation.

Support for Reading Using Multiple Languages!

Ondoku's new voices also support multilingual reading of complex sentences using multiple languages, which previously required instructions using SSML tags in earlier multilingual voices!

For example, in this sample sentence, by specifying the languages in the reading style field, it will read aloud according to the pronunciation of each language, such as English or French.

Audio is read by "Achernar".

Instruction: "Please read aloud brightly and energetically. Read the English part with English pronunciation, the French part with French pronunciation, the Spanish part with Spanish pronunciation, and the German part with native German speaker pronunciation."

ありがとうは、英語で Thank you 、フランス語で Merci 、スペイン語で Gracias 、ドイツ語で Danke といいます。

*For instructions like this, it is also okay to write the reading style in Japanese.

Ondoku's Next-Generation AI Reading Voice FAQ

Finally, we explain the points to keep in mind when using the new reading voice "Ondoku Beta" in a Q&A format.

Q. How many characters can be read aloud?

A. You can read up to 500 characters at a time.

Q. How are the read character counts calculated?

A. They are counted in the same way as before. The character count is aggregated with the amount read by previous reading voices.

Q. Can I check past reading results?

A. You can check them on the "History" page, just like with previous reading voices.

Q. Can I use it for free?

A. Yes, you can. Just like previous voices, credit notation is required for free use.

Instructions on how to write credit notation are explained on this page.

Please take a look.

How to write credit notation for Ondoku. Examples and precautions. | Text-to-Speech Software Ondoku

We welcome you to use Ondoku for free. However, credit notation is mandatory for free use. We have received questions like "Specifically, how should I write it?" This time, we will explain how to handle credit notation for free use of Ondoku.

Q. Can it be used for commercial (business) purposes?

A. Yes, it can be used for commercial (business) purposes just like previous reading voices.

For more details on free use and commercial (business) use, please refer to this page.

What you can do with Ondoku. Commercial (business) use and prohibited items. | Text-to-Speech Software Ondoku

Commercial (business) use is possible with Ondoku. Regardless of whether you are an individual or a corporation, use for the purpose of gaining profit such as money directly or indirectly constitutes commercial use. However, please be aware that prohibited acts are established in Ondoku. This time, we will introduce what you can and cannot do with Ondoku.

Why Not Conveniently Use Ondoku's New AI Voice?

In this way, by using Ondoku's new AI voice, you can easily generate high-quality audio that is easier to listen to than ever before!

Why not experience Ondoku's AI voice, which has become more natural and more human-like, for yourself first?

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

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

■ 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