AIで声を作るならElevenLabsの「ボイスデザイン」がおすすめ！オリジナルボイスの作り方をプロンプト付きで紹介

An elderly Japanese male voice, approximately 70 years old.
The voice sounds serious, calm, and highly intellectual, with the authority and dignity of a veteran public speaker.
It resembles the voices heard in old Japanese parliamentary broadcasts on television.
Speech is delivered in Japanese, with a slightly slow and deliberate pace.
Pronunciation is clear and careful, with minimal emotional fluctuation.
The tone is formal, composed, and trustworthy.
The vocal texture is thin and slightly dry, with subtle age-related breathiness.
Pitch is low to mid-low, without sharpness.
No modern vocal polish.
Audio quality should resemble a Showa-era black-and-white television broadcast:
slightly narrow frequency range, mild analog noise, soft compression, and a muted, vintage broadcast feel.
Overall impression: a traditional, serious Japanese statesman speaking thoughtfully and calmly.

# あなたの役割
プロンプトエンジニア

# あなたへの依頼
音声生成AIのElevenLabsの「ボイスデザイン」の機能を使い、私だけのオリジナルボイスを生成したい。
以下の設定のボイスを作れるプロンプトを作って欲しい。
プロンプトはElevenLabsのボイスデザイン公式ドキュメント（https://elevenlabs.io/docs/creative-platform/voices/voice-design）を参考に作って。

## 設定① 性別
性別を入力

## 設定② 年齢
年齢を入力

## 設定③ 国籍・人種
国籍・人種を入力

## 設定④ 言語
話す言語を入力

## 設定⑤ キャラクターの性格
キャラクターの性格を入力

## 設定⑥ 声の特徴
キャラクターの声の特徴を入力

## 設定⑦ 話す速さ・ペース
キャラクターの話す速さ・ペースを指定。
ElevenLabsは話し方がややゆっくりになりやすいので、普通に話して欲しい場合は「やや早め」くらいがちょうどよい。

##  設定⑧ オーディオ品質
音質を指定
※特に指定がなければ「完璧な音質」でOK

An elderly Japanese male voice, approximately 70 years old.

The voice sounds serious, calm, and highly intellectual, with the authority and dignity of a veteran public speaker.
It resembles the voices heard in old Japanese parliamentary broadcasts on television.

Speech is delivered in Japanese, with a slightly slow and deliberate pace.
Pronunciation is clear and careful, with minimal emotional fluctuation.
The tone is formal, composed, and trustworthy.

The vocal texture is thin and slightly dry, with subtle age-related breathiness.
Pitch is low to mid-low, without sharpness.
No modern vocal polish.

Audio quality should resemble a Showa-era black-and-white television broadcast:
slightly narrow frequency range, mild analog noise, soft compression, and a muted, vintage broadcast feel.

Overall impression: a traditional, serious Japanese statesman speaking thoughtfully and calmly.

A bright and energetic Japanese female voice, approximately 28 years old.
She speaks fluent, natural Japanese with a cheerful and uplifting tone.
Her voice is clear, lively, and confident, similar to a professional Japanese TV weather announcer.

Speech style:
- Fast-paced but very easy to understand
- Crisp articulation with excellent pronunciation
- Positive, friendly, and approachable energy
- Sounds reliable, professional, and refreshing

Voice characteristics:
- Medium-high pitch
- Clean and smooth vocal texture
- No breathiness or roughness
- Consistent volume and stable delivery

Audio quality:
- Studio-grade, perfectly clean sound
- No background noise
- Broadcast-quality clarity suitable for TV or professional media

A native Japanese female voice, age around 18.

She sounds energetic and confident, like a cheerful big-sister figure who naturally leads and motivates people around her.
Her voice is clear, powerful, and well-projected, with a strong core rather than just loudness.
There is a bright, youthful tone, but also maturity and reliability in the way she speaks.

Speaking pace is slightly fast, lively, and rhythmic, giving a sense of momentum and positivity.
Her pronunciation is very clear and easy to understand in Japanese, with excellent articulation.
Emotionally expressive, warm, and upbeat, suitable for motivating, explaining, or encouraging listeners.

The audio quality is pristine and studio-grade, with no noise, distortion, or artifacts.

A male monster voice from a dark fantasy world.

The age is ambiguous and inhuman, with a presence that feels ancient and unnatural.
He speaks Japanese with a terrifying, ominous personality that instills fear and tension.

The voice is extremely muffled, dark, and heavy, as if coming from deep within a massive creature.
It sounds thick, low, and distorted, with reduced clarity that makes it feel monstrous rather than human.
There is a constant sense of menace and dread in his tone.

Speaking pace is slightly slow and deliberate, creating suspense and intimidation with every word.
Each phrase feels weighted, as if echoing through a vast underground space.

The audio feels like it is resonating inside a cave — deep natural reverb, echoing reflections, and a hollow spatial presence.
The sound design emphasizes darkness, depth, and fear rather than cleanliness or brightness.

A native Japanese male voice, age 39.

He has a party-loving, high-energy personality, like a charismatic radio DJ or event MC.
The voice feels lively, upbeat, and fun, naturally hyping up the audience and keeping the mood energetic.
There is confidence and playfulness in his delivery, making listeners feel excited and engaged.

His voice is light and agile, yet  noticeable depth and richness, giving it a professional and mature DJ-like quality.
It sounds smooth, well-controlled, and expressive, balancing brightness with a solid low-end presence.

Speaking pace is very fast and dynamic, with a strong sense of rhythm and momentum.
Despite the speed, pronunciation in Japanese remains clear and easy to follow.
The delivery feels spontaneous, conversational, and entertainment-focused rather than formal.

The audio quality is top-tier and studio-grade, perfectly clean, polished, and broadcast-ready with no noise or artifacts.