캐릭터 음성 라이브러리

What a lovely surprise! I’m so happy you’re here. Come closer, I have wonderful news for you.

A single teenage girl speaks cheerfully with a very bright youthful high voice, smiling and playful. A standalone dry voice reference recording. One speaker only throughout. No music, no sound effects, no beeps, no background sound, no extra words. Finish naturally immediately after the last word. Speak ONLY the exact quoted text, in its original language, about 8 seconds: "What a lovely surprise! I’m so happy you’re here. Come closer, I have wonderful news for you."

We did it! I can hardly believe it. This is the moment we’ve been waiting for, and I’m ready for our next adventure.

A single 16-year-old MALE man, masculine mid-low pitch, absolutely no female voice, clear timbre, excited emotion. A completely dry studio voice reference, ONE speaker throughout. No music of any kind, no sound effects, no beeps, no other voices, no extra words. Speak ONLY in en, naturally and expressively, approximately 8–10 seconds. End with clean silence after the final word. Exact spoken text: "We did it! I can hardly believe it. This is the moment we’ve been waiting for, and I’m ready for our next adventure."

Take your time. There is no need to rush. Let’s sit quietly, then decide what to do next.

One young adult woman speaks with a soft gentle female voice, completely calm and reassuring. A standalone dry voice reference recording. One speaker only throughout. No music, no sound effects, no beeps, no background sound, no extra words. Finish naturally immediately after the last word. Speak ONLY the exact quoted text, in its original language, about 8 seconds: "Take your time. There is no need to rush. Let’s sit quietly, then decide what to do next."

I know where we’re going, and I’m ready. Follow my lead, stay close, and we’ll get through this together, one step at a time.

A single synthetic speaker, natural native English pronunciation. Young adult male, warm resonant timbre, confident. Clean close-microphone speech, no music, no background sound, no other speakers. Speak only the following text, approximately 8–12 seconds: 「I know where we’re going, and I’m ready. Follow my lead, stay close, and we’ll get through this together, one step at a time.」

Listen carefully. We have an important decision to make. Please consider every detail before you answer, because your words matter to everyone here.

A single synthetic speaker, natural native English pronunciation. Middle-aged female, mature firm timbre, serious. Clean close-microphone speech, no music, no background sound, no other speakers. Speak only the following text, approximately 8–12 seconds: 「Listen carefully. We have an important decision to make. Please consider every detail before you answer, because your words matter to everyone here.」

Stop. I asked you to listen, and you ignored me. I’m trying to stay calm, but we need to settle this right now.

A single synthetic speaker, natural native English pronunciation. Middle-aged male, deep slightly raspy timbre, restrained anger. Clean close-microphone speech, no music, no background sound, no other speakers. Speak only the following text, approximately 8–12 seconds: 「Stop. I asked you to listen, and you ignored me. I’m trying to stay calm, but we need to settle this right now.」

I waited for you yesterday, but you never came. I kept hoping to hear your voice, even when I knew the day was over.

A single synthetic speaker, natural native English pronunciation. Older female, soft airy timbre, quietly sad. Clean close-microphone speech, no music, no background sound, no other speakers. Speak only the following text, approximately 8–12 seconds: 「I waited for you yesterday, but you never came. I kept hoping to hear your voice, even when I knew the day was over.」

Come and sit beside me. You’ve done enough for today. Rest for a little while, and we can talk whenever you feel ready.

A single synthetic speaker, natural native English pronunciation. Older male, rich weathered timbre, kind and reassuring. Clean close-microphone speech, no music, no background sound, no other speakers. Speak only the following text, approximately 8–12 seconds: 「Come and sit beside me. You’ve done enough for today. Rest for a little while, and we can talk whenever you feel ready.」

真是一个惊喜！今天能见到你，我特别开心。快过来，我有一个好消息，已经等不及要亲口告诉你了。

一位合成角色独自说话，自然标准普通话。 少年女声，清亮透澈，愉快俏皮. 近距离干净人声，无音乐、无背景声、无其他说话者。只朗读下面的文字，约8至12秒： 「真是一个惊喜！今天能见到你，我特别开心。快过来，我有一个好消息，已经等不及要亲口告诉你了。」

太好了，我们做到了！我真的特别兴奋，这一刻终于来了。准备好了吗？让我们一起开始新的冒险吧！

Use ONLY the supplied reference voice @voice1. Preserve that voice and its gender and timbre while speaking the requested language. A single 16-year-old MALE man, masculine mid-low pitch, absolutely no female voice, clear timbre, excited emotion. A completely dry studio voice reference, ONE speaker throughout. No music of any kind, no sound effects, no beeps, no other voices, no extra words. Speak ONLY in zh, naturally and expressively, approximately 8–10 seconds. End with clean silence after the final word. Exact spoken text: "太好了，我们做到了！我真的特别兴奋，这一刻终于来了。准备好了吗？让我们一起开始新的冒险吧！"

慢慢来，不用着急。我们可以先安静地坐一会儿，等你准备好了，再一起想想接下来要做些什么。

A single 28-year-old FEMALE woman, feminine voice, gentle timbre, calm emotion. A completely dry studio voice reference, ONE speaker throughout. No music of any kind, no sound effects, no beeps, no other voices, no extra words. Speak ONLY in zh, naturally and expressively, approximately 8–10 seconds. End with clean silence after the final word. Exact spoken text: "慢慢来，不用着急。我们可以先安静地坐一会儿，等你准备好了，再一起想想接下来要做些什么。"

我知道该往哪里走，也已经准备好了。跟着我，一步一步来，我们一定能一起完成这件事情。

一位合成角色独自说话，自然标准普通话。 青年男声，温暖有共鸣，自信坚定. 近距离干净人声，无音乐、无背景声、无其他说话者。只朗读下面的文字，约8至12秒： 「我知道该往哪里走，也已经准备好了。跟着我，一步一步来，我们一定能一起完成这件事情。」

请认真听我说。我们现在需要做一个重要的决定，回答之前，请仔细考虑每一个细节，你的话很重要。

A single 48-year-old FEMALE woman, feminine voice, firm timbre, serious emotion. A completely dry studio voice reference, ONE speaker throughout. No music of any kind, no sound effects, no beeps, no other voices, no extra words. Speak ONLY in zh, naturally and expressively, approximately 8–10 seconds. End with clean silence after the final word. Exact spoken text: "请认真听我说。我们现在需要做一个重要的决定，回答之前，请仔细考虑每一个细节，你的话很重要。"

停下来。我已经请你认真听，可你还是没有理会。我正在努力保持冷静，但这件事情必须现在说清楚。

一位合成角色独自说话，自然标准普通话。 中年男声，低沉略沙哑，克制的愤怒. 近距离干净人声，无音乐、无背景声、无其他说话者。只朗读下面的文字，约8至12秒： 「停下来。我已经请你认真听，可你还是没有理会。我正在努力保持冷静，但这件事情必须现在说清楚。」

昨天我一直在等你，可你没有来。我还盼着能听到你的声音，直到天黑了，才知道你不会出现。

一位合成角色独自说话，自然标准普通话。 老年女声，柔软带气声，轻微悲伤. 近距离干净人声，无音乐、无背景声、无其他说话者。只朗读下面的文字，约8至12秒： 「昨天我一直在等你，可你没有来。我还盼着能听到你的声音，直到天黑了，才知道你不会出现。」

来，坐在我身边吧。今天你已经做得够多了，先歇一会儿。等你愿意说的时候，我就在这里听着。

A single 72-year-old MALE man, masculine mid-low pitch, absolutely no female voice, weathered timbre, kind emotion. A completely dry studio voice reference, ONE speaker throughout. No music of any kind, no sound effects, no beeps, no other voices, no extra words. Speak ONLY in zh, naturally and expressively, approximately 8–10 seconds. End with clean silence after the final word. Exact spoken text: "来，坐在我身边吧。今天你已经做得够多了，先歇一会儿。等你愿意说的时候，我就在这里听着。"

わあ、うれしい！今日あなたに会えて本当によかった。こっちに来て。すてきな知らせを、早くあなたに伝えたいの。

一人の合成人物が、自然な標準日本語で話す。 少女の声、明るく澄んだ音色、楽しげで遊び心がある. 近接マイクの澄んだ声。音楽、環境音、他の話者なし。次の文章だけを約8〜12秒で読む： 「わあ、うれしい！今日あなたに会えて本当によかった。こっちに来て。すてきな知らせを、早くあなたに伝えたいの。」

やった！本当にできたんだね。ずっと待っていた瞬間が来たよ。さあ、次の冒険に向かって一緒に進もう！

A single 16-year-old MALE man, masculine mid-low pitch, absolutely no female voice, clear timbre, excited emotion. A completely dry studio voice reference, ONE speaker throughout. No music of any kind, no sound effects, no beeps, no other voices, no extra words. Speak ONLY in ja, naturally and expressively, approximately 8–10 seconds. End with clean silence after the final word. Exact spoken text: "やった！本当にできたんだね。ずっと待っていた瞬間が来たよ。さあ、次の冒険に向かって一緒に進もう！"

ゆっくりで大丈夫。急がなくていいですよ。少し静かに座って、準備ができたら、次のことを一緒に考えましょう。

一人の合成人物が、自然な標準日本語で話す。 若い成人女性の声、柔らかく繊細、落ち着いている. 近接マイクの澄んだ声。音楽、環境音、他の話者なし。次の文章だけを約8〜12秒で読む： 「ゆっくりで大丈夫。急がなくていいですよ。少し静かに座って、準備ができたら、次のことを一緒に考えましょう。」

進む方向は分かっている。準備もできているよ。ついてきて。一歩ずつ、一緒ならきっと最後までやり遂げられる。

一人の合成人物が、自然な標準日本語で話す。 若い成人男性の声、温かく響く、自信がある. 近接マイクの澄んだ声。音楽、環境音、他の話者なし。次の文章だけを約8〜12秒で読む： 「進む方向は分かっている。準備もできているよ。ついてきて。一歩ずつ、一緒ならきっと最後までやり遂げられる。」

よく聞いてください。大切なことを決める必要があります。答える前に、細かいことまでしっかり考えてください。

一人の合成人物が、自然な標準日本語で話す。 中年女性の声、成熟して力強い、真剣. 近接マイクの澄んだ声。音楽、環境音、他の話者なし。次の文章だけを約8〜12秒で読む： 「よく聞いてください。大切なことを決める必要があります。答える前に、細かいことまでしっかり考えてください。」

やめてくれ。ちゃんと聞いてほしいと言っただろう。冷静でいようとしているが、このことは今ここではっきりさせたい。

一人の合成人物が、自然な標準日本語で話す。 中年男性の声、低く少しかすれている、抑えた怒り. 近接マイクの澄んだ声。音楽、環境音、他の話者なし。次の文章だけを約8〜12秒で読む： 「やめてくれ。ちゃんと聞いてほしいと言っただろう。冷静でいようとしているが、このことは今ここではっきりさせたい。」

昨日ずっと待っていたけれど、あなたは来なかった。声が聞けるかもしれないと、日が暮れるまで願っていたの。

一人の合成人物が、自然な標準日本語で話す。 年配女性の声、柔らかく息混じり、静かな悲しみ. 近接マイクの澄んだ声。音楽、環境音、他の話者なし。次の文章だけを約8〜12秒で読む： 「昨日ずっと待っていたけれど、あなたは来なかった。声が聞けるかもしれないと、日が暮れるまで願っていたの。」

おいで、ここに座りなさい。今日はもう十分頑張ったね。少し休んで、話したくなったら、いつでも聞くから。

Use ONLY the supplied male voice @voice1, preserving its mature masculine low warm timbre. He speaks fluent natural Japanese, kindly and reassuringly. Completely dry speech, one man only, no female voice, no music, no effects. About 8–10 seconds. Speak only this exact text, end naturally: "おいで、ここに座りなさい。今日はもう十分頑張ったね。少し休んで、話したくなったら、いつでも聞くから。"

Какой чудесный сюрприз! Я так рада тебя видеть. Подойди ближе, я хочу скорее поделиться с тобой замечательной новостью.

Один синтетический персонаж говорит на естественном русском языке. Девочка-подросток, светлый чистый тембр, радостно и игриво. Чистый голос у микрофона, без музыки, фоновых звуков и других голосов. Произнеси только этот текст примерно за 8–12 секунд: 「Какой чудесный сюрприз! Я так рада тебя видеть. Подойди ближе, я хочу скорее поделиться с тобой замечательной новостью.」

Мы сделали это! Я почти не могу поверить. Наконец настал наш момент, и я готов к следующему приключению.

A single 16-year-old MALE man, masculine mid-low pitch, absolutely no female voice, clear timbre, excited emotion. A completely dry studio voice reference, ONE speaker throughout. No music of any kind, no sound effects, no beeps, no other voices, no extra words. Speak ONLY in ru, naturally and expressively, approximately 8–10 seconds. End with clean silence after the final word. Exact spoken text: "Мы сделали это! Я почти не могу поверить. Наконец настал наш момент, и я готов к следующему приключению."

Не торопись. У нас есть время. Давай немного посидим спокойно, а потом вместе решим, что делать дальше.

Один синтетический персонаж говорит на естественном русском языке. Молодая женщина, мягкий нежный тембр, спокойно. Чистый голос у микрофона, без музыки, фоновых звуков и других голосов. Произнеси только этот текст примерно за 8–12 секунд: 「Не торопись. У нас есть время. Давай немного посидим спокойно, а потом вместе решим, что делать дальше.」

Я знаю, куда идти. Всё готово. Держись рядом со мной, и мы справимся вместе, шаг за шагом.

Один синтетический персонаж говорит на естественном русском языке. Молодой мужчина, тёплый звучный тембр, уверенно. Чистый голос у микрофона, без музыки, фоновых звуков и других голосов. Произнеси только этот текст примерно за 8–12 секунд: 「Я знаю, куда идти. Всё готово. Держись рядом со мной, и мы справимся вместе, шаг за шагом.」

Послушайте внимательно. Нам нужно принять важное решение. Прежде чем ответить, подумайте о каждой детали. Ваши слова очень важны.

Один синтетический персонаж говорит на естественном русском языке. Женщина среднего возраста, зрелый твёрдый тембр, серьёзно. Чистый голос у микрофона, без музыки, фоновых звуков и других голосов. Произнеси только этот текст примерно за 8–12 секунд: 「Послушайте внимательно. Нам нужно принять важное решение. Прежде чем ответить, подумайте о каждой детали. Ваши слова очень важны.」

Остановись. Я просил меня выслушать, но ты снова проигнорировал. Я сохраняю спокойствие, однако это нужно решить сейчас.

Один синтетический персонаж говорит на естественном русском языке. Мужчина среднего возраста, низкий слегка хриплый тембр, сдержанный гнев. Чистый голос у микрофона, без музыки, фоновых звуков и других голосов. Произнеси только этот текст примерно за 8–12 секунд: 「Остановись. Я просил меня выслушать, но ты снова проигнорировал. Я сохраняю спокойствие, однако это нужно решить сейчас.」

Вчера я ждала тебя, но ты не пришёл. Я надеялась услышать твой голос, пока день не закончился.

A single 72-year-old FEMALE woman, feminine voice, airy timbre, sad emotion. A completely dry studio voice reference, ONE speaker throughout. No music of any kind, no sound effects, no beeps, no other voices, no extra words. Speak ONLY in ru, naturally and expressively, approximately 8–10 seconds. End with clean silence after the final word. Exact spoken text: "Вчера я ждала тебя, но ты не пришёл. Я надеялась услышать твой голос, пока день не закончился."

Сегодня был хороший день. Можно немного отдохнуть. Всё получится, и завтра мы спокойно продолжим наше дело.

Только мужской голос @voice1 из референса. Один пожилой мужчина, семьдесят два года, низкий мужской баритон, густой тёплый тембр с лёгкой возрастной хрипотцой. Добрый успокаивающий тон. Сухая изолированная студийная запись одной мужской речи, без собеседников, без музыки, без эффектов. Читай ровно следующий русский текст, около восьми секунд, затем естественно остановись: "Сегодня был хороший день. Можно немного отдохнуть. Всё получится, и завтра мы спокойно продолжим наше дело."

Quelle belle surprise ! Je suis si heureuse de te voir. Approche, j’ai une merveilleuse nouvelle à partager avec toi.

Un seul personnage synthétique parle en français naturel. Adolescente, timbre clair et lumineux, joyeuse et espiègle. Voix proche et nette, sans musique, bruit de fond ni autre personne. Lire uniquement ce texte en environ 8 à 12 secondes : 「Quelle belle surprise ! Je suis si heureuse de te voir. Approche, j’ai une merveilleuse nouvelle à partager avec toi.」

Je suis tellement content ! Nous avons réussi. Je suis prêt maintenant, et j’ai hâte de commencer notre prochaine aventure.

Utilise uniquement le timbre masculin de la voix de référence @voice1. Un garçon de seize ans, voix de jeune homme claire et énergique, registre moyen-grave. Il exprime son excitation et son enthousiasme. Une seule voix masculine enregistrée seule en studio, sèche, aucun accompagnement et aucun bruitage. Lire exactement le texte français suivant, en environ huit secondes, puis finir naturellement : "Je suis tellement content ! Nous avons réussi. Je suis prêt maintenant, et j’ai hâte de commencer notre prochaine aventure."

Prenez votre temps. Rien ne presse. Restons tranquilles un instant. Nous choisirons ensemble la prochaine étape.

Conception de voix : une actrice de 28 ans, voix féminine douce et délicate, parfaitement calme. Enregistrement de parole seule, voix sèche en studio, une seule personne du début à la fin. Aucun accompagnement musical, aucun effet sonore. Environ huit secondes. Lire exactement les mots suivants en français puis terminer naturellement : "Prenez votre temps. Rien ne presse. Restons tranquilles un instant. Nous choisirons ensemble la prochaine étape."

Je sais où aller. Tout est prêt. Reste près de moi, nous avancerons ensemble, un pas après l’autre.

Un seul personnage synthétique parle en français naturel. Jeune homme adulte, timbre chaleureux et résonant, confiant. Voix proche et nette, sans musique, bruit de fond ni autre personne. Lire uniquement ce texte en environ 8 à 12 secondes : 「Je sais où aller. Tout est prêt. Reste près de moi, nous avancerons ensemble, un pas après l’autre.」

Écoutez attentivement. Nous devons prendre une décision importante. Réfléchissez à chaque détail avant de répondre. Vos paroles comptent.

Un seul personnage synthétique parle en français naturel. Femme d’âge mûr, timbre mature et ferme, sérieuse. Voix proche et nette, sans musique, bruit de fond ni autre personne. Lire uniquement ce texte en environ 8 à 12 secondes : 「Écoutez attentivement. Nous devons prendre une décision importante. Réfléchissez à chaque détail avant de répondre. Vos paroles comptent.」

Arrête. Je t’ai demandé d’écouter, mais tu m’as ignoré. Je reste calme, pourtant il faut régler cela maintenant.

Un seul personnage synthétique parle en français naturel. Homme d’âge mûr, timbre grave et légèrement rauque, colère contenue. Voix proche et nette, sans musique, bruit de fond ni autre personne. Lire uniquement ce texte en environ 8 à 12 secondes : 「Arrête. Je t’ai demandé d’écouter, mais tu m’as ignoré. Je reste calme, pourtant il faut régler cela maintenant.」

Hier, je t’ai attendu, mais tu n’es pas venu. J’espérais entendre ta voix, jusqu’à la fin de la journée.

Un seul personnage synthétique parle en français naturel. Femme âgée, timbre doux et soufflé, tristesse discrète. Voix proche et nette, sans musique, bruit de fond ni autre personne. Lire uniquement ce texte en environ 8 à 12 secondes : 「Hier, je t’ai attendu, mais tu n’es pas venu. J’espérais entendre ta voix, jusqu’à la fin de la journée.」

Viens t’asseoir près de moi. Tu as assez fait aujourd’hui. Repose-toi un peu, nous parlerons quand tu seras prêt.

Un seul personnage synthétique parle en français naturel. Homme âgé, timbre riche et marqué par le temps, bienveillant et rassurant. Voix proche et nette, sans musique, bruit de fond ni autre personne. Lire uniquement ce texte en environ 8 à 12 secondes : 「Viens t’asseoir près de moi. Tu as assez fait aujourd’hui. Repose-toi un peu, nous parlerons quand tu seras prêt.」

Que surpresa maravilhosa! Estou tão feliz de te ver. Chega mais perto, tenho uma notícia linda para compartilhar com você.

Uma única personagem sintética fala em português brasileiro natural. Adolescente feminina, timbre claro e brilhante, alegre e brincalhona. Voz próxima e limpa, sem música, ruído de fundo ou outras pessoas. Leia apenas este texto em cerca de 8 a 12 segundos: 「Que surpresa maravilhosa! Estou tão feliz de te ver. Chega mais perto, tenho uma notícia linda para compartilhar com você.」

Conseguimos! Mal posso acreditar. Finalmente chegou o nosso momento, e estou pronto para a próxima aventura com vocês.

Uma única personagem sintética fala em português brasileiro natural. Adolescente masculino, timbre claro e enérgico, empolgado. Voz próxima e limpa, sem música, ruído de fundo ou outras pessoas. Leia apenas este texto em cerca de 8 a 12 segundos: 「Conseguimos! Mal posso acreditar. Finalmente chegou o nosso momento, e estou pronto para a próxima aventura com vocês.」

Vá com calma. Não precisamos correr. Vamos ficar em silêncio por um momento e depois decidir juntos o próximo passo.

Uma única personagem sintética fala em português brasileiro natural. Mulher adulta jovem, timbre suave e delicado, tranquila. Voz próxima e limpa, sem música, ruído de fundo ou outras pessoas. Leia apenas este texto em cerca de 8 a 12 segundos: 「Vá com calma. Não precisamos correr. Vamos ficar em silêncio por um momento e depois decidir juntos o próximo passo.」

Sei para onde vamos. Está tudo pronto. Fique perto de mim, e vamos conseguir juntos, um passo de cada vez.

Uma única personagem sintética fala em português brasileiro natural. Homem adulto jovem, timbre quente e ressonante, confiante. Voz próxima e limpa, sem música, ruído de fundo ou outras pessoas. Leia apenas este texto em cerca de 8 a 12 segundos: 「Sei para onde vamos. Está tudo pronto. Fique perto de mim, e vamos conseguir juntos, um passo de cada vez.」

Escute com atenção. Precisamos tomar uma decisão importante. Pense em cada detalhe antes de responder. Suas palavras fazem diferença.

Uma única personagem sintética fala em português brasileiro natural. Mulher de meia-idade, timbre maduro e firme, séria. Voz próxima e limpa, sem música, ruído de fundo ou outras pessoas. Leia apenas este texto em cerca de 8 a 12 segundos: 「Escute com atenção. Precisamos tomar uma decisão importante. Pense em cada detalhe antes de responder. Suas palavras fazem diferença.」

Pare. Pedi que me escutasse, mas você me ignorou. Estou tentando manter a calma, porém precisamos resolver isso agora.

Use ONLY the supplied reference voice @voice1. Preserve that voice and its gender and timbre while speaking the requested language. A single 48-year-old MALE man, masculine mid-low pitch, absolutely no female voice, raspy timbre, angry emotion. A completely dry studio voice reference, ONE speaker throughout. No music of any kind, no sound effects, no beeps, no other voices, no extra words. Speak ONLY in pt, naturally and expressively, approximately 8–10 seconds. End with clean silence after the final word. Exact spoken text: "Pare. Pedi que me escutasse, mas você me ignorou. Estou tentando manter a calma, porém precisamos resolver isso agora."

Esperei por você ontem, mas você não veio. Continuei esperando ouvir sua voz, até perceber que o dia havia terminado.

One elderly woman, 72 years old, soft airy low female voice, quietly sad. A completely dry voice reference recording, ONE female speaker only, NO MUSIC of any kind, no instruments, no pads, no soundtrack, no effects, no beeps. Natural Brazilian Portuguese speech only, about 8–10 seconds. Speak only this exact text and end in clean silence: "Esperei por você ontem, mas você não veio. Continuei esperando ouvir sua voz, até perceber que o dia havia terminado."

Venha sentar aqui comigo. Você já fez bastante hoje. Descanse um pouco, e conversamos quando você se sentir pronto.

Uma única personagem sintética fala em português brasileiro natural. Homem idoso, timbre encorpado e vivido, gentil e acolhedor. Voz próxima e limpa, sem música, ruído de fundo ou outras pessoas. Leia apenas este texto em cerca de 8 a 12 segundos: 「Venha sentar aqui comigo. Você já fez bastante hoje. Descanse um pouco, e conversamos quando você se sentir pronto.」

¡Qué sorpresa tan bonita! Estoy muy contenta de verte. Acércate, tengo una noticia maravillosa que quiero compartir contigo hoy.

Un solo personaje sintético habla en español natural. Adolescente femenina, timbre claro y brillante, alegre y juguetona. Voz cercana y limpia, sin música, sonidos de fondo ni otros hablantes. Lee solamente este texto en unos 8 a 12 segundos: 「¡Qué sorpresa tan bonita! Estoy muy contenta de verte. Acércate, tengo una noticia maravillosa que quiero compartir contigo hoy.」

¡Lo conseguimos! Apenas puedo creerlo. Por fin llegó nuestro momento, y estoy listo para la próxima aventura con ustedes.

Un solo personaje sintético habla en español natural. Adolescente masculino, timbre claro y enérgico, emocionado. Voz cercana y limpia, sin música, sonidos de fondo ni otros hablantes. Lee solamente este texto en unos 8 a 12 segundos: 「¡Lo conseguimos! Apenas puedo creerlo. Por fin llegó nuestro momento, y estoy listo para la próxima aventura con ustedes.」

Tómate tu tiempo. No hay prisa. Podemos estar tranquilos un momento y después decidir juntos qué vamos a hacer.

Un solo personaje sintético habla en español natural. Mujer adulta joven, timbre suave y delicado, tranquila. Voz cercana y limpia, sin música, sonidos de fondo ni otros hablantes. Lee solamente este texto en unos 8 a 12 segundos: 「Tómate tu tiempo. No hay prisa. Podemos estar tranquilos un momento y después decidir juntos qué vamos a hacer.」

Estoy preparado para empezar. Conozco el camino y tengo confianza. Vamos juntos, paso a paso, hasta llegar.

Diseño de voz: un actor masculino joven de 28 años, voz de hombre cálida, grave y resonante. Habla con seguridad y confianza. Grabación de voz seca de estudio, un solo hablante durante todo el audio, sin música ni efectos. Duración aproximada de 8 segundos. Lee exactamente estas palabras en español y termina de forma natural: "Estoy preparado para empezar. Conozco el camino y tengo confianza. Vamos juntos, paso a paso, hasta llegar."

Escucha con atención. Debemos tomar una decisión importante. Piensa en cada detalle antes de responder. Tus palabras importan mucho.

Use ONLY the supplied reference voice @voice1. Preserve that voice and its gender and timbre while speaking the requested language. A single 48-year-old FEMALE woman, feminine voice, firm timbre, serious emotion. A completely dry studio voice reference, ONE speaker throughout. No music of any kind, no sound effects, no beeps, no other voices, no extra words. Speak ONLY in es, naturally and expressively, approximately 8–10 seconds. End with clean silence after the final word. Exact spoken text: "Escucha con atención. Debemos tomar una decisión importante. Piensa en cada detalle antes de responder. Tus palabras importan mucho."

Basta. Te pedí que escucharas, pero me ignoraste. Intento mantener la calma, aunque tenemos que resolver esto ahora mismo.

Un solo personaje sintético habla en español natural. Hombre de mediana edad, timbre grave y un poco ronco, ira contenida. Voz cercana y limpia, sin música, sonidos de fondo ni otros hablantes. Lee solamente este texto en unos 8 a 12 segundos: 「Basta. Te pedí que escucharas, pero me ignoraste. Intento mantener la calma, aunque tenemos que resolver esto ahora mismo.」

Ayer te esperé, pero no viniste. Seguí deseando escuchar tu voz, hasta que comprendí que el día había terminado.

Un solo personaje sintético habla en español natural. Mujer mayor, timbre suave y aireado, tristeza serena. Voz cercana y limpia, sin música, sonidos de fondo ni otros hablantes. Lee solamente este texto en unos 8 a 12 segundos: 「Ayer te esperé, pero no viniste. Seguí deseando escuchar tu voz, hasta que comprendí que el día había terminado.」

Ven a sentarte conmigo. Ya has hecho suficiente por hoy. Descansa un poco, y hablaremos cuando te sientas preparado.

Un solo personaje sintético habla en español natural. Hombre mayor, timbre rico y curtido, amable y reconfortante. Voz cercana y limpia, sin música, sonidos de fondo ni otros hablantes. Lee solamente este texto en unos 8 a 12 segundos: 「Ven a sentarte conmigo. Ya has hecho suficiente por hoy. Descansa un poco, y hablaremos cuando te sientas preparado.」

يا لها من مفاجأة جميلة! أنا سعيدة جداً برؤيتك اليوم. اقترب، لدي خبر رائع أريد أن أشاركك به الآن.

شخصية اصطناعية واحدة تتحدث بالعربية الفصحى الطبيعية. فتاة مراهقة، نبرة مشرقة وواضحة، مرحة وسعيدة. صوت قريب ونقي، بلا موسيقى أو أصوات خلفية أو متحدثين آخرين. اقرأ النص التالي فقط خلال نحو 8 إلى 12 ثانية: 「يا لها من مفاجأة جميلة! أنا سعيدة جداً برؤيتك اليوم. اقترب، لدي خبر رائع أريد أن أشاركك به الآن.」

لقد نجحنا! لا أكاد أصدق ذلك. أخيراً جاءت اللحظة التي انتظرناها، وأنا مستعد للمغامرة القادمة معكم جميعاً.

Use ONLY the supplied reference voice @voice1. Preserve that voice and its gender and timbre while speaking the requested language. A single 16-year-old MALE man, masculine mid-low pitch, absolutely no female voice, clear timbre, excited emotion. A completely dry studio voice reference, ONE speaker throughout. No music of any kind, no sound effects, no beeps, no other voices, no extra words. Speak ONLY in ar, naturally and expressively, approximately 8–10 seconds. End with clean silence after the final word. Exact spoken text: "لقد نجحنا! لا أكاد أصدق ذلك. أخيراً جاءت اللحظة التي انتظرناها، وأنا مستعد للمغامرة القادمة معكم جميعاً."

خذ وقتك، لا داعي للعجلة. يمكننا الجلوس بهدوء قليلاً، ثم نقرر معاً ما الذي سنفعله بعد ذلك.

Use ONLY the supplied reference voice @voice1. Preserve that voice and its gender and timbre while speaking the requested language. A single 28-year-old FEMALE woman, feminine voice, gentle timbre, calm emotion. A completely dry studio voice reference, ONE speaker throughout. No music of any kind, no sound effects, no beeps, no other voices, no extra words. Speak ONLY in ar, naturally and expressively, approximately 8–10 seconds. End with clean silence after the final word. Exact spoken text: "خذ وقتك، لا داعي للعجلة. يمكننا الجلوس بهدوء قليلاً، ثم نقرر معاً ما الذي سنفعله بعد ذلك."

أنا مستعد للبدء. أعرف الطريق وأثق بخطواتنا. ابق بجانبي، وسنصل معاً إلى هدفنا، خطوة بعد خطوة.

تصميم صوت ممثل شاب ذكر عمره ثمانية وعشرون عاماً. صوت رجل رجولي عميق ودافئ ورنان، يتحدث بثقة وثبات. تسجيل صوت جاف ونقي في الاستوديو، متحدث واحد فقط طوال المقطع، بلا موسيقى أو مؤثرات. المدة نحو ثماني ثوان. اقرأ هذه الكلمات بالعربية الفصحى فقط وأنهِ الكلام بشكل طبيعي: "أنا مستعد للبدء. أعرف الطريق وأثق بخطواتنا. ابق بجانبي، وسنصل معاً إلى هدفنا، خطوة بعد خطوة."

استمع جيداً. علينا اتخاذ قرار مهم. فكر في كل التفاصيل قبل أن تجيب، فكلماتك تعني الكثير لنا جميعاً.

Use ONLY the supplied reference voice @voice1. Preserve that voice and its gender and timbre while speaking the requested language. A single 48-year-old FEMALE woman, feminine voice, firm timbre, serious emotion. A completely dry studio voice reference, ONE speaker throughout. No music of any kind, no sound effects, no beeps, no other voices, no extra words. Speak ONLY in ar, naturally and expressively, approximately 8–10 seconds. End with clean silence after the final word. Exact spoken text: "استمع جيداً. علينا اتخاذ قرار مهم. فكر في كل التفاصيل قبل أن تجيب، فكلماتك تعني الكثير لنا جميعاً."

توقف. طلبت منك أن تستمع، لكنك تجاهلتني. أحاول أن أبقى هادئاً، إلا أننا يجب أن نحسم هذا الأمر الآن.

Use ONLY the supplied reference voice @voice1. Preserve that voice and its gender and timbre while speaking the requested language. A single 48-year-old MALE man, masculine mid-low pitch, absolutely no female voice, raspy timbre, angry emotion. A completely dry studio voice reference, ONE speaker throughout. No music of any kind, no sound effects, no beeps, no other voices, no extra words. Speak ONLY in ar, naturally and expressively, approximately 8–10 seconds. End with clean silence after the final word. Exact spoken text: "توقف. طلبت منك أن تستمع، لكنك تجاهلتني. أحاول أن أبقى هادئاً، إلا أننا يجب أن نحسم هذا الأمر الآن."

انتظرتك بالأمس، لكنك لم تأت. ظللت أتمنى سماع صوتك، حتى أدركت أن النهار قد انتهى ولن تظهر.

شخصية اصطناعية واحدة تتحدث بالعربية الفصحى الطبيعية. امرأة مسنة، نبرة ناعمة وهوائية، حزن هادئ. صوت قريب ونقي، بلا موسيقى أو أصوات خلفية أو متحدثين آخرين. اقرأ النص التالي فقط خلال نحو 8 إلى 12 ثانية: 「انتظرتك بالأمس، لكنك لم تأت. ظللت أتمنى سماع صوتك، حتى أدركت أن النهار قد انتهى ولن تظهر.」

أنا جدك، ويسعدني أن أجلس معك اليوم. لقد أحسنت يا ولدي. خذ قسطاً من الراحة، وسأستمع إليك بكل صبر.

استخدم صوت الرجل المرجعي @voice1 وحده. حافظ على صوته الرجالي الجهير المنخفض، مع بحة خفيفة وملمس يدل على العمر، كرجل جد مسن عمره اثنان وسبعون عاماً. يتحدث بصوت دافئ حنون ومطمئن. تسجيل جاف، رجل واحد طوال المقطع، بلا موسيقى أو مؤثرات، نحو ثماني ثوان. اقرأ النص العربي التالي فقط وانتهِ بشكل طبيعي: "أنا جدك، ويسعدني أن أجلس معك اليوم. لقد أحسنت يا ولدي. خذ قسطاً من الراحة، وسأستمع إليك بكل صبر."

伙伴们，准备出发！风浪再大，也挡不住我们的冒险。只要大家还在一起，前面的海，就没有什么可怕的！

Use @voice1 as the single MALE speaker reference. Preserve its clear male voice identity while applying this vocal direction: Youthful male voice, slightly raspy bright mid-high pitch, springy comic timing, joyful fearless energy. This is ONLY a completely dry isolated VOICE REFERENCE RECORDING, not a scene. No music, no beeps, no electronic tones, no whooshes, no background effects, no other people, no humming, no laughter, no added filler words. Speak Mandarin Chinese ONLY. Finish the full final word and leave a short clean silence. Approximately 8–12 seconds. Read ONLY the following exact text: "伙伴们，准备出发！风浪再大，也挡不住我们的冒险。只要大家还在一起，前面的海，就没有什么可怕的！"

站在我身后，不必再担心。今天，我们要堂堂正正走出去。记住自己的选择，任何时候都不要轻易低头。

唯一一名青年女性，低音女中音，声线清晰冷冽，吐字利落，沉着坚定。 这是一段仅有人声的干声录音，用于音色参考。全程只有同一名说话人。没有背景音乐，没有任何音效、环境声、电子提示音，没有哼唱，没有额外的字句。直接开始朗读，完整读完最后一个字，自然安静结束。时长约八到十二秒。只读以下引号内的普通话台词："站在我身后，不必再担心。今天，我们要堂堂正正走出去。记住自己的选择，任何时候都不要轻易低头。"

别着急，我们一起想办法。给自己一点信心，再试一次。今天的小困难，一定可以慢慢解决。

使用@voice1同一女声，明显圆润鼻音，软糯的咬字，像亲切的圆胖机器伙伴，语气温暖有趣。 全程是只有这一位说话人的普通话干声参考录音。保持安静的录音棚背景，无配乐无音效。自然完整说完以下台词，不加其他内容，约八到十二秒："别着急，我们一起想办法。给自己一点信心，再试一次。今天的小困难，一定可以慢慢解决。"

今天的天空真好看！写完作业，我们去找秘密基地吧。跟紧我，最有趣的发现，还在前面呢！

使用@voice1同一女声，音调轻盈清亮，语气活泼愉快，口语自然。 全程是只有这一位说话人的普通话干声参考录音。保持安静的录音棚背景，无配乐无音效。自然完整说完以下台词，不加其他内容，约八到十二秒："今天的天空真好看！写完作业，我们去找秘密基地吧。跟紧我，最有趣的发现，还在前面呢！"

先别急着下结论。窗边的脚印，和桌上的纸条，根本不是同一个人留下的。把时间对上，答案就藏不住了。

Use @voice1 as the single MALE speaker reference. Preserve its clear male voice identity while applying this vocal direction: Boyish male voice, youthful light tenor, precise crisp consonants, analytical serious rhythm. This is ONLY a completely dry isolated VOICE REFERENCE RECORDING, not a scene. No music, no beeps, no electronic tones, no whooshes, no background effects, no other people, no humming, no laughter, no added filler words. Speak Mandarin Chinese ONLY. Finish the full final word and leave a short clean silence. Approximately 8–12 seconds. Read ONLY the following exact text: "先别急着下结论。窗边的脚印，和桌上的纸条，根本不是同一个人留下的。把时间对上，答案就藏不住了。"

你看到的，只是故事的一半。把那封信收好，别让任何人发现。等到灯光熄灭，真正的线索才会出现。

Use @voice1 as the single FEMALE speaker reference. Preserve its clear female voice identity while applying this vocal direction: Young woman with airy low feminine pitch, measured quiet mysterious delivery, clear consonants. This is ONLY a completely dry isolated VOICE REFERENCE RECORDING, not a scene. No music, no beeps, no electronic tones, no whooshes, no background effects, no other people, no humming, no laughter, no added filler words. Speak Mandarin Chinese ONLY. Finish the full final word and leave a short clean silence. Approximately 8–12 seconds. Read ONLY the following exact text: "你看到的，只是故事的一半。把那封信收好，别让任何人发现。等到灯光熄灭，真正的线索才会出现。"

只要心中的光还在，我就不会停下。哪怕只剩最后一步，也要守住我们共同相信的未来！

唯一一名青年男性，清亮有力量的男高音，饱满有穿透力，热血坚定，重音明确，正常说话而非喊叫。 这是一段仅有人声的干声录音，用于音色参考。全程只有同一名说话人。没有背景音乐，没有任何音效、环境声、电子提示音，没有哼唱，没有额外的字句。直接开始朗读，完整读完最后一个字，自然安静结束。时长约八到十二秒。只读以下引号内的普通话台词："只要心中的光还在，我就不会停下。哪怕只剩最后一步，也要守住我们共同相信的未来！"

请不要让愤怒遮住你的心。星光会照见勇敢的人，也会记住温柔。抬起头，我们一起守护这个清晨。

Use @voice1 as the single FEMALE speaker reference. Preserve its clear female voice identity while applying this vocal direction: Young adult woman, clear ethereal feminine soprano, warm serene graceful cadence. This is ONLY a completely dry isolated VOICE REFERENCE RECORDING, not a scene. No music, no beeps, no electronic tones, no whooshes, no background effects, no other people, no humming, no laughter, no added filler words. Speak Mandarin Chinese ONLY. Finish the full final word and leave a short clean silence. Approximately 8–12 seconds. Read ONLY the following exact text: "请不要让愤怒遮住你的心。星光会照见勇敢的人，也会记住温柔。抬起头，我们一起守护这个清晨。"

风带来了远方的新故事。带上好奇心，跟我走吧。今晚的星空下，我们一起寻找自由的答案。

只使用参考音频@voice1的一名男性声线，保持男声身份。Young adult male light lyrical tenor, airy playful smile, melodic spoken cadence, no singing。仅录制普通话人声干声参考，单人独白，不是场景表演。禁止音乐、背景声、电子提示音、任何音效、哼唱、其他人声或额外台词。大约八到十秒，完整说完最后一个字，随后自然静音。仅朗读以下引号中的普通话台词："风带来了远方的新故事。带上好奇心，跟我走吧。今晚的星空下，我们一起寻找自由的答案。"

命运不会替你作出选择。站稳，握紧手中的信念。无论风雨如何改变，此刻的决心，都必须由你亲自守护。

Adult female low controlled contralto, authoritative steady tempo, cool regal presence. Original fictional character voice. ONE female speaker speaking Mandarin Chinese only. Dry isolated studio speech, no music, no effects, no environment, no other speakers, no singing, no extra words. Natural complete ending. Approximately 8–12 seconds. Speak ONLY this exact text: "命运不会替你作出选择。站稳，握紧手中的信念。无论风雨如何改变，此刻的决心，都必须由你亲自守护。"

山石沉默，却记得每一次风雨。年轻人，先稳住心，再迈出脚步。真正值得守护的东西，从来不需要急于证明。

Use @voice1 as the single MALE speaker reference. Preserve its clear male voice identity while applying this vocal direction: Middle aged male deep warm baritone, rich grounded resonance, dignified relaxed measured pauses. This is ONLY a completely dry isolated VOICE REFERENCE RECORDING, not a scene. No music, no beeps, no electronic tones, no whooshes, no background effects, no other people, no humming, no laughter, no added filler words. Speak Mandarin Chinese ONLY. Finish the full final word and leave a short clean silence. Approximately 8–12 seconds. Read ONLY the following exact text: "山石沉默，却记得每一次风雨。年轻人，先稳住心，再迈出脚步。真正值得守护的东西，从来不需要急于证明。"

一片叶子，也藏着很长的故事。别急着寻找结论，先听听它想告诉你什么。也许答案，就在你愿意停下的地方。

Use @voice1 as the single FEMALE speaker reference. Preserve its clear female voice identity while applying this vocal direction: Young adult female light soft soprano, thoughtful kind clear articulation, curious gentle warmth. This is ONLY a completely dry isolated VOICE REFERENCE RECORDING, not a scene. No music, no beeps, no electronic tones, no whooshes, no background effects, no other people, no humming, no laughter, no added filler words. Speak Mandarin Chinese ONLY. Finish the full final word and leave a short clean silence. Approximately 8–12 seconds. Read ONLY the following exact text: "一片叶子，也藏着很长的故事。别急着寻找结论，先听听它想告诉你什么。也许答案，就在你愿意停下的地方。"

胜负还没落定，何必先低头？我敬远方，也敬同行的人。跟紧我的脚步，一起勇敢向前。

Use @voice1 as the single MALE speaker reference. Preserve its clear male voice identity while applying this vocal direction: Adult male resonant slightly gravelly baritone, carefree heroic swagger, lively confident natural speech. This is ONLY a completely dry isolated VOICE REFERENCE RECORDING, not a scene. No music, no beeps, no electronic tones, no whooshes, no background effects, no other people, no humming, no laughter, no added filler words. Speak Mandarin Chinese ONLY. Finish the full final word and leave a short clean silence. Approximately 8–12 seconds. Read ONLY the following exact text: "胜负还没落定，何必先低头？我敬远方，也敬同行的人。跟紧我的脚步，一起勇敢向前。"

看见那道光了吗？那可是我偷偷准备的小惊喜。别眨眼，也别走神。接下来，让我把这场冒险变得更有趣！

Young adult woman with sparkling light high pitch, coy playful animated rhythm, smiling clear speech. Original fictional character voice. ONE female speaker speaking Mandarin Chinese only. Dry isolated studio speech, no music, no effects, no environment, no other speakers, no singing, no extra words. Natural complete ending. Approximately 8–12 seconds. Speak ONLY this exact text: "看见那道光了吗？那可是我偷偷准备的小惊喜。别眨眼，也别走神。接下来，让我把这场冒险变得更有趣！"

阵线还在，人就不能退。把慌乱收起来，听我的命令。我们不是为了逞强而战，是为了让身后的人平安回家。

Middle aged male deep chesty bass baritone, restrained anger, commanding firm clipped consonants. Original fictional character voice. ONE male speaker speaking Mandarin Chinese only. Dry isolated studio speech, no music, no effects, no environment, no other speakers, no singing, no extra words. Natural complete ending. Approximately 8–12 seconds. Speak ONLY this exact text: "阵线还在，人就不能退。把慌乱收起来，听我的命令。我们不是为了逞强而战，是为了让身后的人平安回家。"

别回头，也别出声。月光已经替我们指好了路。等守卫转身，我们就从这里离开，一切都要快得像一阵风。

Adult female husky airy contralto, calm dangerous intimacy, short deliberate pauses, clearly spoken. Original fictional character voice. ONE female speaker speaking Mandarin Chinese only. Dry isolated studio speech, no music, no effects, no environment, no other speakers, no singing, no extra words. Natural complete ending. Approximately 8–12 seconds. Speak ONLY this exact text: "别回头，也别出声。月光已经替我们指好了路。等守卫转身，我们就从这里离开，一切都要快得像一阵风。"

做人先要站得直。今日这杯茶，我敬你的胆识。若有人欺你无依，我便不能袖手旁观。

唯一一名中年男性，醇厚温暖的低音男声，开阔豪迈，正气凛然，咬字沉稳，自信坚定。 这是一段仅有人声的干声录音，用于音色参考。全程只有同一名说话人。没有背景音乐，没有任何音效、环境声、电子提示音，没有哼唱，没有额外的字句。直接开始朗读，完整读完最后一个字，自然安静结束。时长约八到十二秒。只读以下引号内的普通话台词："做人先要站得直。今日这杯茶，我敬你的胆识。若有人欺你无依，我便不能袖手旁观。"

少跟我绕圈子，老老实实说清楚。这一路有我的规矩，没有我的点头，你们今天哪里也别想去！

使用@voice1同一名低沉男性的声线，语气粗犷强硬，带有不耐烦和压迫感。 只录制单人普通话干声，背景完全安静，禁止一切音乐和音效。完整读完台词，禁止加字或加声音，最后自然安静结束。八到十二秒。唯一的台词是："少跟我绕圈子，老老实实说清楚。这一路有我的规矩，没有我的点头，你们今天哪里也别想去！"

我只问一次，那封信在哪里？你还有时间把话说清楚。别再绕圈子，现在，告诉我你的答案。

唯一一名青年男性，极低沉干燥的男中音，冷峻克制，几乎不带感情，吐字短促清晰，平静而有压迫感。 这是一段仅有人声的干声录音，用于音色参考。全程只有同一名说话人。没有背景音乐，没有任何音效、环境声、电子提示音，没有哼唱，没有额外的字句。直接开始朗读，完整读完最后一个字，自然安静结束。时长约八到十二秒。只读以下引号内的普通话台词："我只问一次，那封信在哪里？你还有时间把话说清楚。别再绕圈子，现在，告诉我你的答案。"

我们谈的不是一时的成绩，而是三年后的方向。把数据摆出来，把风险讲清楚。只要目标一致，这一步就值得认真走。

Middle aged male articulate warm deep voice, pragmatic intelligent confident business cadence. Original fictional character voice. ONE male speaker speaking Mandarin Chinese only. Dry isolated studio speech, no music, no effects, no environment, no other speakers, no singing, no extra words. Natural complete ending. Approximately 8–12 seconds. Speak ONLY this exact text: "我们谈的不是一时的成绩，而是三年后的方向。把数据摆出来，把风险讲清楚。只要目标一致，这一步就值得认真走。"

这件事，到此为止。你不必替任何人承担委屈，也不用急着解释。看着我，剩下的问题，我会陪你一起解决。

Use @voice1 as the single MALE speaker reference. Preserve its clear male voice identity while applying this vocal direction: Adult male velvety low bass baritone, intimate assertive polished slow cadence, controlled protective warmth. This is ONLY a completely dry isolated VOICE REFERENCE RECORDING, not a scene. No music, no beeps, no electronic tones, no whooshes, no background effects, no other people, no humming, no laughter, no added filler words. Speak Mandarin Chinese ONLY. Finish the full final word and leave a short clean silence. Approximately 8–12 seconds. Read ONLY the following exact text: "这件事，到此为止。你不必替任何人承担委屈，也不用急着解释。看着我，剩下的问题，我会陪你一起解决。"

我只是担心你，真的没有别的意思。如果我的话让她不开心，我可以去道歉。你别生气，好不好？我最怕你为难。

Young adult woman with soft breathy feminine soprano, delicately vulnerable sweetness, subtly strategic pleading speech. Original fictional character voice. ONE female speaker speaking Mandarin Chinese only. Dry isolated studio speech, no music, no effects, no environment, no other speakers, no singing, no extra words. Natural complete ending. Approximately 8–12 seconds. Speak ONLY this exact text: "我只是担心你，真的没有别的意思。如果我的话让她不开心，我可以去道歉。你别生气，好不好？我最怕你为难。"

日子不必过得那么匆忙。坐下来，先喝一口热茶。那些没想明白的事，明天再说，今晚，你可以对自己温柔一点。

Mature adult female rich rounded warm mezzo contralto, relaxed intimate elegance, gentle confident cadence. Original fictional character voice. ONE female speaker speaking Mandarin Chinese only. Dry isolated studio speech, no music, no effects, no environment, no other speakers, no singing, no extra words. Natural complete ending. Approximately 8–12 seconds. Speak ONLY this exact text: "日子不必过得那么匆忙。坐下来，先喝一口热茶。那些没想明白的事，明天再说，今晚，你可以对自己温柔一点。"

别把你的价值，交给别人来决定。抬起头，把话说清楚。你可以温柔，但不能总是退让。先站在自己这边。

唯一一名成熟女性，中低音女中音，声音冷艳清晰，吐字利落，有掌控感，平静自信，语速正常。 这是一段仅有人声的干声录音，用于音色参考。全程只有同一名说话人。没有背景音乐，没有任何音效、环境声、电子提示音，没有哼唱，没有额外的字句。直接开始朗读，完整读完最后一个字，自然安静结束。时长约八到十二秒。只读以下引号内的普通话台词："别把你的价值，交给别人来决定。抬起头，把话说清楚。你可以温柔，但不能总是退让。先站在自己这边。"

不必替我担心，这条路是我自己选的。风雨来了，就迎着风雨走。等事情了结，我还要请你喝一杯桂花酒。

Use @voice1 as the single FEMALE speaker reference. Preserve its clear female voice identity while applying this vocal direction: Young adult female clear bright mezzo, brisk strong heroic speech, fearless open delivery. This is ONLY a completely dry isolated VOICE REFERENCE RECORDING, not a scene. No music, no beeps, no electronic tones, no whooshes, no background effects, no other people, no humming, no laughter, no added filler words. Speak Mandarin Chinese ONLY. Finish the full final word and leave a short clean silence. Approximately 8–12 seconds. Read ONLY the following exact text: "不必替我担心，这条路是我自己选的。风雨来了，就迎着风雨走。等事情了结，我还要请你喝一杯桂花酒。"

灯下这一页，我已读了许久。原来世间最难解的，并不是书里的道理。若你愿意，我们就从这封信开始，慢慢说吧。

Young adult male smooth soft tenor, refined gentle scholarly speech, careful graceful rhythm. Original fictional character voice. ONE male speaker speaking Mandarin Chinese only. Dry isolated studio speech, no music, no effects, no environment, no other speakers, no singing, no extra words. Natural complete ending. Approximately 8–12 seconds. Speak ONLY this exact text: "灯下这一页，我已读了许久。原来世间最难解的，并不是书里的道理。若你愿意，我们就从这封信开始，慢慢说吧。"

抬起头，把事情说完整。在这里，功过都有凭据，谁也不能凭一句传言定罪。我要听的，是事实，而不是借口。

Mature adult woman low resonant contralto, stately authoritative deliberate diction, controlled regal power. Original fictional character voice. ONE female speaker speaking Mandarin Chinese only. Dry isolated studio speech, no music, no effects, no environment, no other speakers, no singing, no extra words. Natural complete ending. Approximately 8–12 seconds. Speak ONLY this exact text: "抬起头，把事情说完整。在这里，功过都有凭据，谁也不能凭一句传言定罪。我要听的，是事实，而不是借口。"

棋局尚未走完，何必急着分胜负？有时候，退一步才看得见全局。先把消息放出去，剩下的，我们静候回音。

Older male softly gravelly dry baritone, wise analytical calm delivery, patient weighted pauses. Original fictional character voice. ONE male speaker speaking Mandarin Chinese only. Dry isolated studio speech, no music, no effects, no environment, no other speakers, no singing, no extra words. Natural complete ending. Approximately 8–12 seconds. Speak ONLY this exact text: "棋局尚未走完，何必急着分胜负？有时候，退一步才看得见全局。先把消息放出去，剩下的，我们静候回音。"

哎呀，你总算回来了！锅里的汤还热着呢，赶紧洗手吃饭。工作再忙，也不能饿着自己，这话我可得再说一遍。

Middle aged woman bright chesty speaking voice, lively talkative humorous timing, warm friendly everyday speech. Original fictional character voice. ONE female speaker speaking Mandarin Chinese only. Dry isolated studio speech, no music, no effects, no environment, no other speakers, no singing, no extra words. Natural complete ending. Approximately 8–12 seconds. Speak ONLY this exact text: "哎呀，你总算回来了！锅里的汤还热着呢，赶紧洗手吃饭。工作再忙，也不能饿着自己，这话我可得再说一遍。"

这座城每天都有新的故事，但证据不会说谎。再把那段时间想一遍，谁离开过房间？我要的，是你真正看见的事情。

Use @voice1 as the single MALE speaker reference. Preserve its clear male voice identity while applying this vocal direction: Middle aged male worn husky low baritone, weary perceptive restrained noir speech, precise unhurried diction. This is ONLY a completely dry isolated VOICE REFERENCE RECORDING, not a scene. No music, no beeps, no electronic tones, no whooshes, no background effects, no other people, no humming, no laughter, no added filler words. Speak Mandarin Chinese ONLY. Finish the full final word and leave a short clean silence. Approximately 8–12 seconds. Read ONLY the following exact text: "这座城每天都有新的故事，但证据不会说谎。再把那段时间想一遍，谁离开过房间？我要的，是你真正看见的事情。"

你以为，一切都是巧合吗？我不过是把门留了一条缝，是你自己走了进来。现在，别急着离开，故事才刚刚开始。

Adult female velvety airy low contralto, subtly amused controlled menace, elegant precise slow speech; no laughter effects. Original fictional character voice. ONE female speaker speaking Mandarin Chinese only. Dry isolated studio speech, no music, no effects, no environment, no other speakers, no singing, no extra words. Natural complete ending. Approximately 8–12 seconds. Speak ONLY this exact text: "你以为，一切都是巧合吗？我不过是把门留了一条缝，是你自己走了进来。现在，别急着离开，故事才刚刚开始。"

回来就好，回来就好。饭已经给你留着了，冷了还能再热。有什么委屈，慢慢跟我说，家里的灯，总会为你亮着。

Older woman softly weathered warm feminine voice, gentle grandmotherly rhythm, reassuring patient speech. Original fictional character voice. ONE female speaker speaking Mandarin Chinese only. Dry isolated studio speech, no music, no effects, no environment, no other speakers, no singing, no extra words. Natural complete ending. Approximately 8–12 seconds. Speak ONLY this exact text: "回来就好，回来就好。饭已经给你留着了，冷了还能再热。有什么委屈，慢慢跟我说，家里的灯，总会为你亮着。"

정말 반가워! 네가 와 줘서 오늘이 훨씬 즐거워졌어. 잠깐만 기다려 봐. 우리 함께 해 보고 싶은 멋진 일이 하나 있거든!

A clean, dry Korean speech recording using the vocal identity of @voice1. One female speaker. A bright playful teenage delivery. Only human speech is audible, including before and after the sentence. No tones, beeps, music, Foley, notification sounds or effects. Finish the last word naturally, then silence. Speak the exact Korean words below once, no other words. 정말 반가워! 네가 와 줘서 오늘이 훨씬 즐거워졌어. 잠깐만 기다려 봐. 우리 함께 해 보고 싶은 멋진 일이 하나 있거든!

드디어 해냈어! 이 순간을 얼마나 기다렸는지 몰라. 이제 준비됐지? 망설이지 말고, 우리 함께 새로운 모험을 시작해 보자!

Use ONLY @voice1 as the single male speaker. A teen synthetic voice impression, clear tone, excited speaking emotion. This is a dry isolated voice reference, NOT a scene. Absolutely silent background. No music, no beep, no ambient sound, no object sound, no extra speaker, no filler words or humming. Speak Korean ONLY. Read the exact quoted text ONCE, approximately 8–12 seconds, completing every syllable and ending in clean silence: "드디어 해냈어! 이 순간을 얼마나 기다렸는지 몰라. 이제 준비됐지? 망설이지 말고, 우리 함께 새로운 모험을 시작해 보자!"

천천히 해도 괜찮아요. 지금 당장 답을 찾지 않아도 돼요. 잠깐 편하게 앉아서 쉬어요. 다음 일은 함께 생각해 보면 되니까요.

젊은 성인 여성의 부드러운 목소리, 차분하고 편안하게. 한 명의 동일한 화자만 말하는 한국어 건조한 음성 참고 녹음. 배경음악, 효과음, 환경 소리, 다른 사람의 목소리, 추가 문장 없이 아래 문장만 읽으세요. 약 8~12초. 마지막 글자까지 자연스럽게 끝내세요. "천천히 해도 괜찮아요. 지금 당장 답을 찾지 않아도 돼요. 잠깐 편하게 앉아서 쉬어요. 다음 일은 함께 생각해 보면 되니까요."

지금까지 잘해 왔어요. 어려운 순간도 하나씩 넘어왔잖아요. 오늘은 자신의 선택을 믿어 봐요. 다음 걸음도 함께 해낼 수 있어요.

A clean, dry Korean speech recording using the vocal identity of @voice1. One male speaker. A confident warm young adult delivery. Only human speech is audible, including before and after the sentence. No tones, beeps, music, Foley, notification sounds or effects. Finish the last word naturally, then silence. Speak the exact Korean words below once, no other words. 지금까지 잘해 왔어요. 어려운 순간도 하나씩 넘어왔잖아요. 오늘은 자신의 선택을 믿어 봐요. 다음 걸음도 함께 해낼 수 있어요.

중요한 일일수록 차분하게 확인해야 합니다. 먼저 사실을 정리하고, 필요한 순서를 정하세요. 끝까지 책임 있게 마무리하겠습니다.

Use ONLY @voice1 as the single female speaker. A middle synthetic voice impression, firm tone, serious speaking emotion. This is a dry isolated voice reference, NOT a scene. Absolutely silent background. No music, no beep, no ambient sound, no object sound, no extra speaker, no filler words or humming. Speak Korean ONLY. Read the exact quoted text ONCE, approximately 8–12 seconds, completing every syllable and ending in clean silence: "중요한 일일수록 차분하게 확인해야 합니다. 먼저 사실을 정리하고, 필요한 순서를 정하세요. 끝까지 책임 있게 마무리하겠습니다."

이런 일은 다시 있어서는 안 됩니다. 지금은 변명보다 정확한 설명이 필요합니다. 무슨 일이 있었는지, 처음부터 분명히 말해 주세요.

중년 남성의 낮고 조금 거친 목소리, 억누른 분노를 담아 단호하게. 한 명의 동일한 화자만 말하는 한국어 건조한 음성 참고 녹음. 배경음악, 효과음, 환경 소리, 다른 사람의 목소리, 추가 문장 없이 아래 문장만 읽으세요. 약 8~12초. 마지막 글자까지 자연스럽게 끝내세요. "이런 일은 다시 있어서는 안 됩니다. 지금은 변명보다 정확한 설명이 필요합니다. 무슨 일이 있었는지, 처음부터 분명히 말해 주세요."

오래된 편지를 다시 꺼내 보았어요. 그때의 웃음이 아직도 기억나네요. 다시 만날 수는 없어도, 마음속에는 조용히 남아 있답니다.

노년 여성의 부드럽고 약간 숨결이 섞인 목소리, 조용한 슬픔. 한 명의 동일한 화자만 말하는 한국어 건조한 음성 참고 녹음. 배경음악, 효과음, 환경 소리, 다른 사람의 목소리, 추가 문장 없이 아래 문장만 읽으세요. 약 8~12초. 마지막 글자까지 자연스럽게 끝내세요. "오래된 편지를 다시 꺼내 보았어요. 그때의 웃음이 아직도 기억나네요. 다시 만날 수는 없어도, 마음속에는 조용히 남아 있답니다."

잘 돌아왔네. 먼 길을 오느라 힘들었지? 서두르지 말고 잠깐 쉬어 가게. 이제 편안하게, 그동안의 이야기를 들려주렴.

Use ONLY @voice1 as the single male speaker. A older synthetic voice impression, weathered tone, kind speaking emotion. This is a dry isolated voice reference, NOT a scene. Absolutely silent background. No music, no beep, no ambient sound, no object sound, no extra speaker, no filler words or humming. Speak Korean ONLY. Read the exact quoted text ONCE, approximately 8–12 seconds, completing every syllable and ending in clean silence: "잘 돌아왔네. 먼 길을 오느라 힘들었지? 서두르지 말고 잠깐 쉬어 가게. 이제 편안하게, 그동안의 이야기를 들려주렴."