[Voice Tuning] New AI Voice Styles Guide: Free Human-like Emotions & Acting

Thank you for always using Ondoku.

With the newly released AI voice 『Ondoku Beta』, which provides more human-like reading, it is now possible to freely describe reading styles to enable a wide range of expressions such as emotions, acting, age, and dialects.

In this article, we will introduce tips, methods, and techniques for the "voice adjustment" method of the new AI voices on the AI text-to-speech site Ondoku!

Why not use this article as a reference to more freely use AI voices that can produce a wide range of expressions depending on your adjustments?

[Free] New adjustable AI voice 『Ondoku Beta』

The AI text-to-speech site 『Ondoku Beta』 is available here.

Just like the previous 『Ondoku』, it can be used for free!

Commercial use is OK, so you can use it in YouTube commentary videos or creative videos, and even monetize it! (Click here for details on commercial use)

Since such a wide range of expressions is possible, why not experience Ondoku's new adjustable AI voice for free yourself?

AI Voice Synthesis 【Beta】- Emotionally expressive next-generation TTS | Ondoku

Generate emotionally expressive voices with the latest AI technology. Choose from 25 types of voices for next-generation text-to-speech. Realize natural speech with speed/pitch adjustment and reading style specifications.

How to use the style (voice adjustment) function on Ondoku's new AI text-to-speech site?

By adopting the latest AI voice synthesis engine, the AI text-to-speech site 『Ondoku Beta』 now allows you to freely describe reading styles.

It's easy to use!

Once you open the site from this link, enter the text you want to be read in the text box.

Enter the reading style you want to adjust in the "Reading Style" field.

When you click the "Generate Voice" button, the voice is immediately synthesized using the new AI engine.

How to use Ondoku's new AI voice is explained in detail in this article. Please take a look.

Listen to 25 types of next-generation AI Japanese voice samples for free. Also supports multi-language reading | Text-to-speech software Ondoku

The latest next-generation AI voice, capable of generating emotionally expressive voices with the latest AI technology, is here! In this article, you can listen to voice samples of Ondoku's new AI voices. It's also possible to specify emotional expressions through free description and read in multiple languages.

Listen to the new AI voice style function! What are the adjustment tips and techniques?

Now, let's actually introduce the tips and techniques for what kind of expressions are possible when adjusting with the newly released AI voice style function!

The method is very simple, so please try it yourself.

1. Reading samples and adjustment tips for emotional expressions (joy, anger, sorrow, pleasure)

First is the emotional expression of joy, anger, sorrow, and pleasure.

The method for emotional expression is very simple.

Simply describing the reading style like "joyfully" or "sadly" is all you need to do.

The sample voice uses "Ellis".

Instruction: "Please read joyfully." Voice sample

うれしい！ほんとうにありがとう！

Instruction: "Please read with an angry voice." Voice sample

わたしがどうして怒っているかわかりますか？

Instruction: "Please read sadly." Voice sample

そんな、ひどいです。

Instruction: "Please read happily." Voice sample

ねえねえ！次はジェットコースターに乗りにいこうよ！

2. Reading samples and adjustment tips for acting and tone of voice

Ondoku's new AI voices are capable of not just emotions like joy, anger, sorrow, and pleasure, but also finer, more human-like acting!

Depending on the technique used to specify the reading style, you can adjust to various tones of voice.

Instruction: "Please read with a majestic voice." Voice sample

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。

Voice: Ellis

Voice: Ash

Instruction: "Please read in a whispering voice." Voice sample

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。

Voice: Ellis

Voice: Ash

Instruction: "Please read with a bright, confident voice." Voice sample

こんにちは、Ondokuです！
宇宙一自然で、宇宙一人間らしい声になったぜ！

Voice: Ellis

Instruction: "Please read with an unconfident voice." Voice sample

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、たぶん…。

Voice: Ellis

3. Adjustment technique for reading in a "boy's voice" using a female voice

An application technique unique to AI reading voices that can now read more naturally is the creation of a "boy's voice."

Young boy characters in anime who haven't undergone a voice change are often played by female voice actors, aren't they?

In the same way, with Ondoku's new AI voices, you can adjust to a boy's voice by selecting a female voice and giving instructions.

The sample voice uses "Ellis".

Instruction: "Please read with the voice of a lively 3rd-grade boy." Voice sample

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！

Furthermore, the way of speaking also changes depending on the tone of the text being read.

Instruction: "Please read with the voice of a lively 3rd-grade boy." Voice sample

オッス、俺、Ondoku！
より自然で、より人間らしい声になったぜ！

4. Age specification other than children is also possible. Tips for reading in an elderly person's voice

Of course, it is possible to read not only in a child's voice like the "boy" example but also in an aged voice.

Instruction: "Please read with a grandmother's voice." Voice sample

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！

Voice: Ellis

Instruction: "Please read with a grandfather's voice." Voice sample

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！

Voice: Ash

In addition to descriptions like "grandfather" or "grandmother," it is also possible to have them act by specifying an age.

Instruction: "Please read with a 60-year-old voice." Voice sample

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。

Voice: Ellis

Instruction: "Please read with an 80-year-old voice." Voice sample

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。

Voice: Ellis

Technique for specifying age

As a tip when specifying age in the style,

• with the voice of an 80-year-old woman
• with the voice of an 80-year-old man

rather than specifying it that way,

• with an 80-year-old voice

specifying it this way will result in better voice adjustment.

5. Tips for adjusting character voices. Techniques for creative works

Furthermore,

by getting creative with the way you write the style, you can produce more advanced character acting.

Instruction: "Please read with a gal-like (gyaru) voice." Voice sample

こんちは〜、Ondokuでーす！
マジで自然で、超人間っぽい声になったんだけど！

Voice: Ellis

Instruction: "Please read with the tone of a great professor." Voice sample

ほっほっほ。わしは、とても偉い博士じゃ。

Voice: Ash

Instruction: "Please read with the tone of a police officer." Voice sample

15時24分。あなたを現行犯で逮捕します。

Voice: Ash

6. Acting, age, character—and of course, combining adjustment specifications is also OK!

Of course, it is possible to combine the adjustment specifications introduced so far, such as:

• Emotions
• Acting
• Age
• Character

The sample voice uses "Ellis".

Instruction: "Please read joyfully with the voice of a lively 3rd-grade boy." Voice sample

やったー！オレ、勝っちゃったもんねー！

Instruction: "Please read sadly with the voice of a lively 3rd-grade boy." Voice sample

トホホ、もうこりごりだよー。

Instruction: "Please read with a gal-like (gyaru) voice and a joyful tone." Voice sample

あんたもいいとこあんじゃん、サンキュー！

Instruction: "Please read with a gal-like (gyaru) voice and an angry tone." Voice sample

あんたって…、ほんとサイテー。

Instruction: "Please read joyfully with an 80-year-old voice." Voice sample

長生きしてきた甲斐がありました。

Instruction: "Please read sadly with an 80-year-old voice." Voice sample

そうですか。本当に残念です。

7. Technique for reading in dialects using the style (adjustment) function

In addition to expressions like acting, age, and character, Ondoku's new more human-like AI voices can also read in dialects!

The sample voice uses "Ellis".

Instruction: "Please read brightly and energetically in Kansai dialect." Voice sample

どうも、Ondokuやで。
めっちゃ自然で、人間らしい声になったんや！

Even more detailed specifications than "Kansai dialect" are possible.

Instruction: "Please read brightly and energetically in Kawachi dialect." Voice sample

こんにちは、Ondokuや。
より自然で、より人間らしい声になったで！

Instruction: "Please read brightly and energetically in Kyoto dialect." Voice sample

こんにちは、Ondokuや。
より自然で、より人間らしい声になりました！

8. Read English and foreign languages freely with the style (adjustment) function!

Ondoku's new AI voices can read not only Japanese but also English and other foreign languages from around the world in a natural voice.

As a tip, you need to write the style to match the language of the text, such as "writing the style in English when reading in English."

First is an example of voice synthesis in American English and British English.

The sample voice uses "Ellis".

Instruction: "Speak cheerfully with an American English accent." Voice sample

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

Instruction: "Speak cheerfully with a British English accent." Voice sample

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

Of course, you can also specify pronunciations such as dialects when reading in English or other foreign languages.

For example, if you read in British "Queen's English" and "Cockney," it looks like this.

The sample voice uses "Ellis".

Instruction: "Speak cheerfully in Queen's English." Voice sample

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

Instruction: "Speak cheerfully in Cockney." Voice sample

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

In this way, you can freely read English and other foreign languages with the latest AI voice synthesis engine!

Please try various adjustment techniques in languages other than Japanese as well.

Why not experience the expression techniques of AI voices that have become more human-like for free?

The possibilities of Ondoku's new AI voice are infinite!

Depending on the style description, a wide range of adjustments is possible, including emotions, acting, age, and characters.

For video narration or creative works, why not first experience Ondoku's more human-like new AI voice for free yourself?

AI Voice Synthesis 【Beta】- Emotionally expressive next-generation TTS | Ondoku

Generate emotionally expressive voices with the latest AI technology. Choose from 25 types of voices for next-generation text-to-speech. Realize natural speech 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