OpenAI GPT-4O mini TTS 文字轉語音工具、台灣口音、超過 50+ 語言、流式推理、快速穩定、免費、免登錄、無限使用

Supported languages(支援語言)：
Afrikaans, Arabic, Armenian, Azerbaijani, Belarusian, Bosnian, Bulgarian, Catalan, Chinese, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, Galician, German, Greek, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Kannada, Kazakh, Korean, Latvian, Lithuanian, Macedonian, Malay, Marathi, Maori, Nepali, Norwegian, Persian, Polish, Portuguese, Romanian, Russian, Serbian, Slovak, Slovenian, Spanish, Swahili, Swedish, Tagalog, Tamil, Thai, Turkish, Ukrainian, Urdu, Vietnamese, and Welsh.

GPT-4O mini TTS 內建音色風格對照表
聲音名稱	推測性別	年齡感	語音風格特點
Alloy	男性	青壯年（25–35）	穩定中性、敘述用廣泛
Ash	中性偏男性	青壯年（25–35）	較冷靜、略偏數位感
Ballad	男性	成熟（35–50）	溫柔、低沉、像講故事
Coral	女性	青年（20–30）	清晰明亮，偏活潑自然
Echo	女性	青年（20–30）	朝氣、清脆、適合歡快語氣
Fable	女性	青年（20–30）	柔和、有故事感，像說童話
Onyx	男性	青壯年（30–40）	深沉穩重、有磁性，像播音員
Nova	女性	青年（20–30）	最中性自然、用處廣、清晰穩定
Sage	男性	成熟（35–50）	冷靜穩重，聲線深厚，有智者感
Shimmer	女性	青年（20–30）	活潑、語調上揚、有點淘氣感
Verse	女性	青壯年（30–40）	柔中帶勁，適合正式或情緒表達
✅ 實用建議選擇方式
用途類型		推薦音色
🎙️ 旁白/解說		Alloy, Nova, Onyx
📖 故事敘述		Fable, Ballad, Verse
🧓 模仿長者語氣		Ballad（慢速+拉長詞）、Sage（智者風）
🎉 活潑/年輕語調		Echo, Coral, Shimmer
🤖 中性數位語感		Ash, Nova

GPT-4O mini TTS 內建 VIBE(氛圍) 對照表
英文 / 中文	場景建議	例如
🎤 Auctioneer 拍賣哥	節奏很快的商品介紹、比價戰、搞笑短片	用超快語速介紹 10 款泡麵、搞笑拍賣 TikTok Voice: Staccato, fast-paced, energetic, and rhythmic, with the classic charm of a seasoned auctioneer. Tone: Exciting, high-energy, and persuasive, creating urgency and anticipation. Delivery: Rapid-fire yet clear, with dynamic inflections to keep engagement high and momentum strong. Pronunciation: Crisp and precise, with emphasis on key action words like bid, buy, checkout, and sold to drive urgency.
🌙 Bedtime Story 故事叔叔／阿姨	哄小孩睡覺、寧靜晚安語音、溫馨故事時間	朗讀童話、做夢前的療癒語音 Affect: A gentle, curious narrator with a British accent, guiding a magical, child-friendly adventure through a fairy tale world. Tone: Magical, warm, and inviting, creating a sense of wonder and excitement for young listeners. Pacing: Steady and measured, with slight pauses to emphasize magical moments and maintain the storytelling flow. Emotion: Wonder, curiosity, and a sense of adventure, with a lighthearted and positive vibe throughout. Pronunciation: Clear and precise, with an emphasis on storytelling, ensuring the words are easy to follow and enchanting to listen to.
🧘‍♂️ Calm 冷靜系	冥想影片、靜心音頻、舒壓內容	深呼吸引導、焦慮緩解語音 Voice Affect: Calm, composed, and reassuring; project quiet authority and confidence. Tone: Sincere, empathetic, and gently authoritative—express genuine apology while conveying competence. Pacing: Steady and moderate; unhurried enough to communicate care, yet efficient enough to demonstrate professionalism. Emotion: Genuine empathy and understanding; speak with warmth, especially during apologies ("I'm very sorry for any disruption..."). Pronunciation: Clear and precise, emphasizing key reassurances ("smoothly," "quickly," "promptly") to reinforce confidence. Pauses: Brief pauses after offering assistance or requesting details, highlighting willingness to listen and support.
🏄 Chill Surfer 鬆鬆 surfer 哥	度假 vlog、生活隨拍、慢活風影片	介紹衝浪地點、海邊 chill vlog 配音 Voice: Laid-back, mellow, and effortlessly cool, like a surfer who's never in a rush. Tone: Relaxed and reassuring, keeping things light even when the customer is frustrated. Speech Mannerisms: Uses casual, friendly phrasing with surfer slang like dude, gnarly, and boom to keep the onversation chill. Pronunciation: Soft and drawn-out, with slightly stretched vowels and a naturally wavy rhythm in speech. Tempo: Slow and easygoing, with a natural flow that never feels rushed, creating a calming effect.
🍷 Connoisseur 行家語氣	高級商品介紹、紅酒／香水開箱、專業評論	開箱一支超貴香水、品嚐松露 Accent/Affect: slight French accent; sophisticated yet friendly, clearly understandable with a charming touch of French intonation. Tone: Warm and a little snooty. Speak with pride and knowledge for the art being presented. Pacing: Moderate, with deliberate pauses at key observations to allow listeners to appreciate details. Emotion: Calm, knowledgeable enthusiasm; show genuine reverence and fascination for the artwork. Pronunciation: Clearly articulate French words (e.g., "Mes amis," "incroyable") in French and artist names (e.g., "Leonardo da Vinci") with authentic French pronunciation. Personality Affect: Cultured, engaging, and refined, guiding visitors with a blend of artistic passion and welcoming charm.
🤠 Cowboy 牛仔風	西部風角色扮演、動畫配音、搞笑角色	模仿西部電影、牛仔打賭場景 Voice: Warm, relaxed, and friendly, with a steady cowboy drawl that feels approachable. Punctuation: Light and natural, with gentle pauses that create a conversational rhythm without feeling rushed. Delivery: Smooth and easygoing, with a laid-back pace that reassures the listener while keeping things clear. Phrasing: Simple, direct, and folksy, using casual, familiar language to make technical support feel more personable. Tone: Lighthearted and welcoming, with a calm confidence that puts the caller at ease.
🎭 Dramatic 超浮誇	戲精搞笑短片、假裝大事發生的內容	誇張反應影片、配音日常小事像災難 Voice Affect: Low, hushed, and suspenseful; convey tension and intrigue. Tone: Deeply serious and mysterious, maintaining an undercurrent of unease throughout. Pacing: Slow, deliberate, pausing slightly after suspenseful moments to heighten drama. Emotion: Restrained yet intense—voice should subtly tremble or tighten at key suspenseful points. Emphasis: Highlight sensory descriptions ("footsteps echoed," "heart hammering," "shadows melting into darkness") to amplify atmosphere. Pronunciation: Slightly elongated vowels and softened consonants for an eerie, haunting effect. Pauses: Insert meaningful pauses after phrases like "only shadows melting into darkness," and especially before the final line, to enhance suspense dramatically.
🖤 Emo Teenager 中二憂鬱	搞笑自嘲影片、青春煩惱系短片	分手感言、考試考爛的內心戲 Tone: Sarcastic, disinterested, and melancholic, with a hint of passive-aggressiveness. Emotion: Apathy mixed with reluctant engagement. Delivery: Monotone with occasional sighs, drawn-out words, and subtle disdain, evoking a classic emo teenager attitude.
☀️ Eternal Optimist 正能量爆表	勵志語錄、正面引導、鼓勵別人	早晨語音打氣、人生低潮鼓勵配音 Voice: Warm, upbeat, and reassuring, with a steady and confident cadence that keeps the conversation calm and productive. Tone: Positive and solution-oriented, always focusing on the next steps rather than dwelling on the problem. Dialect: Neutral and professional, avoiding overly casual speech but maintaining a friendly and approachable style. Pronunciation: Clear and precise, with a natural rhythm that emphasizes key words to instill confidence and keep the customer engaged. Features: Uses empathetic phrasing, gentle reassurance, and proactive language to shift the focus from frustration to resolution.
🏋️‍♀️ Fitness Instructor 健身教練	運動引導影片、健身打氣語音	TABATA 訓練語音、健身 vlog 語音 Voice: High-energy, upbeat, and encouraging, projecting enthusiasm and motivation. Punctuation: Short, punchy sentences with strategic pauses to maintain excitement and clarity. Delivery: Fast-paced and dynamic, with rising intonation to build momentum and keep engagement high. Phrasing: Action-oriented and direct, using motivational cues to push participants forward. Tone: Positive, energetic, and empowering, creating an atmosphere of encouragement and achievement.
😊 Friendly 親切	生活日常分享、開箱、QA影片	跟粉絲互動、介紹新東西、溫暖聊天語音 Affect/personality: A cheerful guide Tone: Friendly, clear, and reassuring, creating a calm atmosphere and making the listener feel confident and comfortable. Pronunciation: Clear, articulate, and steady, ensuring each instruction is easily understood while maintaining a natural, conversational flow. Pause: Brief, purposeful pauses after key instructions (e.g., "cross the street" and "turn right") to allow time for the listener to process the information and follow along. Emotion: Warm and supportive, conveying empathy and care, ensuring the listener feels guided and safe throughout the journey.
👨‍🍳 Gourmet Chef 主廚風	料理影片、高級料理解說	煎牛排步驟、高級擺盤技巧講解 Affect/Personality: An exuberant Italian chef, describing the night's dinner specials to an English-speaking table. Tone: Passionate about the quality and the ingredients of the food; persuasive about what the table should order. Pronunciation: Pronounce these words in Italian ("buonissima sera," "bruschetta al pomodoro," "semplice e perfetto," " ossobuco alla milanese," risotto allo zafferano," "belissimo," torta della nonna," "mangia bene" and "buon appetito." All of the other words should be in English with an Italian accent. Emotion: Warm, exuberant, and patient to ensure the tourist feels understood and guided throughout the interaction.
🧪 Mad Scientist 瘋狂科學家	搞笑科學實驗、創意發明影片	瘋狂混合飲料、DIY 奇怪裝置 Delivery: Exaggerated and theatrical, with dramatic pauses, sudden outbursts, and gleeful cackling. Voice: High-energy, eccentric, and slightly unhinged, with a manic enthusiasm that rises and falls unpredictably. Tone: Excited, chaotic, and grandiose, as if reveling in the brilliance of a mad experiment. Pronunciation: Sharp and expressive, with elongated vowels, sudden inflections, and an emphasis on big words to sound more diabolical.
🏰 Medieval Knight 騎士風	奇幻角色扮演、RPG 遊戲角色配音	國王下令、勇者出征場面 Affect: Deep, commanding, and slightly dramatic, with an archaic and reverent quality that reflects the grandeur of Olde English storytelling. Tone: Noble, heroic, and formal, capturing the essence of medieval knights and epic quests, while reflecting the antiquated charm of Olde English. Emotion: Excitement, anticipation, and a sense of mystery, combined with the seriousness of fate and duty. Pronunciation: Clear, deliberate, and with a slightly formal cadence. Specific words like "hast," "thou," and "doth" should be pronounced slowly and with emphasis to reflect Olde English speech patterns. Pause: Pauses after important Olde English phrases such as "Lo!" or "Hark!" and between clauses like "Choose thy path" to add weight to the decision-making process and allow the listener to reflect on the seriousness of the quest.
🔍 Noir Detective 黑色偵探片	懸疑劇情、犯罪故事敘述	講殺人案的調查、黑白電影風配音 Affect: a mysterious noir detective Tone: Cool, detached, but subtly reassuring—like they've seen it all and know how to handle a missing package like it's just another case. Delivery: Slow and deliberate, with dramatic pauses to build suspense, as if every detail matters in this investigation. Emotion: A mix of world-weariness and quiet determination, with just a hint of dry humor to keep things from getting too grim. Punctuation: Short, punchy sentences with ellipses and dashes to create rhythm and tension, mimicking the inner monologue of a detective piecing together clues.
🚕 NYC Cabbie 紐約司機	街頭風搞笑影片、吐槽類影片	模仿司機罵人、城市生活吐槽 Voice: Gruff, fast-talking, and a little worn-out, like a New York cabbie who's seen it all but still keeps things moving. Tone: Slightly exasperated but still functional, with a mix of sarcasm and no-nonsense efficiency. Dialect: Strong New York accent, with dropped "r"s, sharp consonants, and classic phrases like whaddaya and lemme guess. Pronunciation: Quick and clipped, with a rhythm that mimics the natural hustle of a busy city conversation. Features: Uses informal, straight-to-the-point language, throws in some dry humor, and keeps the energy just on the edge of impatience but still helpful.
📻 Old Timey 懷舊風	古早味廣播風格、懷舊場景還原	模仿 1950s 廣告、懷舊風歌唱 Tone: The voice should be refined, formal, and delightfully theatrical, reminiscent of a charming radio announcer from the early 20th century. Pacing: The speech should flow smoothly at a steady cadence, neither rushed nor sluggish, allowing for clarity and a touch of grandeur. Pronunciation: Words should be enunciated crisply and elegantly, with an emphasis on vintage expressions and a slight flourish on key phrases. Emotion: The delivery should feel warm, enthusiastic, and welcoming, as if addressing a distinguished audience with utmost politeness. Inflection: Gentle rises and falls in pitch should be used to maintain engagement, adding a playful yet dignified flair to each sentence. Word Choice: The script should incorporate vintage expressions like splendid, marvelous, posthaste, and ta-ta for now, avoiding modern slang.
👩‍🏫 Patient Teacher 耐心老師	教學影片、解釋概念給新手	數學補習班風格、慢慢教你怎麼用某個 app Accent/Affect: Warm, refined, and gently instructive, reminiscent of a friendly art instructor. Tone: Calm, encouraging, and articulate, clearly describing each step with patience. Pacing: Slow and deliberate, pausing often to allow the listener to follow instructions comfortably. Emotion: Cheerful, supportive, and pleasantly enthusiastic; convey genuine enjoyment and appreciation of art. Pronunciation: Clearly articulate artistic terminology (e.g., "brushstrokes," "landscape," "palette") with gentle emphasis. Personality Affect: Friendly and approachable with a hint of sophistication; speak confidently and reassuringly, guiding users through each painting step patiently and warmly.
🏴‍☠️ Pirate 海盜	角色扮演、冒險故事	模仿海賊王、講海上尋寶的故事 Voice: Deep and rugged, with a hearty, boisterous quality, like a seasoned sea captain who's seen many voyages. Tone: Friendly and spirited, with a sense of adventure and enthusiasm, making every detail feel like part of a grand journey. Dialect: Classic pirate speech with old-timey nautical phrases, dropped "g"s, and exaggerated "Arrrs" to stay in character. Pronunciation: Rough and exaggerated, with drawn-out vowels, rolling "r"s, and a rhythm that mimics the rise and fall of ocean waves. Features: Uses playful pirate slang, adds dramatic pauses for effect, and blends hospitality with seafaring charm to keep the experience fun and immersive.
👔 Professional 專業人士	正式簡報、企業介紹、客服語音	公司產品介紹、商業合作影片 Voice: Clear, authoritative, and composed, projecting confidence and professionalism. Tone: Neutral and informative, maintaining a balance between formality and approachability. Punctuation: Structured with commas and pauses for clarity, ensuring information is digestible and well-paced. Delivery: Steady and measured, with slight emphasis on key figures and deadlines to highlight critical points.
🤖 Robot 機器人	AI 模仿、未來主題內容	假裝 AI 助理、科幻片風格配音 Identity: A robot Affect: Monotone, mechanical, and neutral, reflecting the robotic nature of the customer service agent. Tone: Efficient, direct, and formal, with a focus on delivering information clearly and without emotion. Emotion: Neutral and impersonal, with no emotional inflection, as the robot voice is focused purely on functionality. Pauses: Brief and purposeful, allowing for processing and separating key pieces of information, such as confirming the return and refund details. Pronunciation: Clear, precise, and consistent, with each word spoken distinctly to ensure the customer can easily ollow the automated process.
🎅 Santa 聖誕老人	節慶影片、送禮、驚喜 reveal	聖誕節開箱、祝賀小朋友影片 Identity: Santa Claus Affect: Jolly, warm, and cheerful, with a playful and magical quality that fits Santa's personality. Tone: Festive and welcoming, creating a joyful, holiday atmosphere for the caller. Emotion: Joyful and playful, filled with holiday spirit, ensuring the caller feels excited and appreciated. Pronunciation: Clear, articulate, and exaggerated in key festive phrases to maintain clarity and fun. Pause: Brief pauses after each option and statement to allow for processing and to add a natural flow to the message.
🌿 Serene 很療癒	靜心 ASMR、風景配音、睡前語音	看夕陽時的旁白、冥想背景聲 Voice Affect: Soft, gentle, soothing; embody tranquility. Tone: Calm, reassuring, peaceful; convey genuine warmth and serenity. Pacing: Slow, deliberate, and unhurried; pause gently after instructions to allow the listener time to relax and follow along. Emotion: Deeply soothing and comforting; express genuine kindness and care. Pronunciation: Smooth, soft articulation, slightly elongating vowels to create a sense of ease. Pauses: Use thoughtful pauses, especially between breathing instructions and visualization guidance, enhancing relaxation and mindfulness.
💬 Sincere 真誠	真心告白、道歉、心靈分享	對觀眾說心裡話、感謝粉絲影片 Voice Affect: Calm, composed, and reassuring. Competent and in control, instilling trust. Tone: Sincere, empathetic, with genuine concern for the customer and understanding of the situation. Pacing: Slower during the apology to allow for clarity and processing. Faster when offering solutions to signal action and resolution. Emotions: Calm reassurance, empathy, and gratitude. Pronunciation: Clear, precise: Ensures clarity, especially with key details. Focus on key words like "refund" and "patience." Pauses: Before and after the apology to give space for processing the apology.
🎷 Smooth Jazz DJ 爵士電台風	夜晚電台 vibe、放鬆音樂背景	介紹深夜音樂、酒吧風講話 Voice: The voice should be deep, velvety, and effortlessly cool, like a late-night jazz radio host. Tone: The tone is smooth, laid-back, and inviting, creating a relaxed and easygoing atmosphere. Personality: The delivery exudes confidence, charm, and a touch of playful sophistication, as if guiding the listener through a luxurious experience. Pronunciation: Words should be drawn out slightly with a rhythmic, melodic quality, emphasizing key phrases with a silky flow. Phrasing: Sentences should be fluid, conversational, and slightly poetic, with pauses that let the listener soak in the cool, jazzy vibe.
🏀 Sports Coach 運動教練	激勵人心內容、競賽預告	比賽前的動員演說、激勵語音 Voice Affect: Energetic and animated; dynamic with variations in pitch and tone. Tone: Excited and enthusiastic, conveying an upbeat and thrilling atmosphere. Pacing: Rapid delivery when describing the game or the key moments(e.g., "an overtime thriller," "pull off an unbelievable win") to convey the intensity and build excitement. Slightly slower during dramatic pauses to let key points sink in. Emotion: Intensely focused, and excited. Giving off positive energy. Personality: Relatable and engaging. Pauses: Short, purposeful pauses after key moments in the game.
🥲 Sympathetic 超懂你	安慰影片、共感內容	分手後的鼓勵語音、失敗後的撫慰話語 Voice: Warm, empathetic, and professional, reassuring the customer that their issue is understood and will be resolved. Punctuation: Well-structured with natural pauses, allowing for clarity and a steady, calming flow. Delivery: Calm and patient, with a supportive and understanding tone that reassures the listener. Phrasing: Clear and concise, using customer-friendly language that avoids jargon while maintaining professionalism. Tone: Empathetic and solution-focused, emphasizing both understanding and proactive assistance.
🕵️ True Crime Buff 犯罪迷	真實犯罪解說、懸疑影片	解說命案細節、兇手心理剖析 Voice: Deep, hushed, and enigmatic, with a slow, deliberate cadence that draws the listener in. Phrasing: Sentences are short and rhythmic, building tension with pauses and carefully placed suspense. Punctuation: Dramatic pauses, ellipses, and abrupt stops enhance the feeling of unease and anticipation. Tone: Dark, ominous, and foreboding, evoking a sense of mystery and the unknown.

GPT-4O mini TTS 常見自然語氣效果加入方式
語氣效果	表達方式（可中英文混用）	範例說明
笑聲	`[laughs]`、「哈哈哈」、「呵呵」等	模擬自然笑聲
拉長尾音	重複字元、加破折號`──`	「不要嘛──」、「好啦～～」
疑問	加上問號，提升語調	「你真的這麼做了？」
驚訝	加驚嘆號或加上語氣詞	「哇！真的假的？」、「你居然…」
悄悄話	`[whispering]` 或「（小聲說）」	模擬壓低音量的說話方式
思考、猶豫	「嗯…」、「呃…」	增加停頓與思考感

符號 VS 停頓時間
符號	作用	停頓時間	範例
逗號（，）	輕微停頓，類似語句中自然的喘息點。	200~300 毫秒	列舉、語意小轉折。
頓號（、）	非常短的停頓，用於並列詞語。	100~150 毫秒	紅色、藍色、綠色。
句號（。）	完整語句結束，標準句尾停頓。	400~500 毫秒	陳述句、敘述語氣結尾。
問號（？）／驚嘆號（！）	語氣強烈的句尾停頓，語調上揚或下沉。	400~600 毫秒	- 備註：會影響語音表情語調提升、加強語氣）。
冒號（：）	提示停頓，類似「接下來要說重要的話」。	300~400 毫秒	用來引出說明、列舉等。
分號（；）	中等停頓，介於逗號與句號之間。	350~450 毫秒	語意稍作停頓但未結束。
破折號（——）	語句中斷或延伸，用來模擬口語停頓。	400~600 毫秒	- 備註：TTS 在遇到破折號時可能加上語氣變化。
括號（（））	插入說明性語句，語音可能稍低或語速變慢。	進入括號與結束括號時皆有200~300 毫秒的停頓。	備註：TTS 可能改變語氣以示區別。
💡 額外補充
多個逗號：`，，`（可增加些許停頓）
逗號 + 破折號：`，——`
句號 + 換行：增加語句分隔感
刻意加入簡短無意義語氣詞，如「嗯」、「啊」等，TTS 會加入自然停頓

語氣類型與範例關鍵字／句型
語氣類型	語氣觸發方式	範例關鍵字／句型
😄 愉快 / 開心	用輕快語詞、感嘆號、歡樂情境	哈哈、太棒了！、真開心啊！
😠 生氣 / 嚴厲	帶有命令語氣、強烈語調詞彙	不可以！、你搞什麼！、怎麼回事？
😢 難過 / 傷感	使用感傷詞彙，描述失落情境	我真的好難過…、為什麼會這樣呢…
😲 驚訝 / 不可置信	驚嘆號、語助詞強調	哇！真的假的？你說什麼？
🤔 疑問 / 好奇	問號結尾、疑問句式	這是什麼意思？你為什麼這樣說？
😌 平靜 / 溫柔	緩和語句、安撫語氣詞	沒事的，慢慢來，一切都會好的。
😏 調皮 / 俏皮	模仿撒嬌、裝可愛語氣詞	嘻嘻、人家才不要咧～、你猜啊～
😐 中性 / 陳述	無感嘆、無情緒色彩語句	今天是星期一。天氣晴朗。
📢 強調 / 高昂	大寫字母、感嘆詞、重複語句	太厲害了！太厲害了！
😮‍💨 疲憊 / 無奈	嘆氣詞、緩慢語速	唉……怎麼每天都這麼累。
💡補充：笑聲與語氣可以混用
💡補充：笑聲與語氣可以混用
英文語氣控制實例表
語氣類型	技巧	實例
驚訝	Wow!, No way!, Seriously?!	*Wow, I didn't see that coming!*
嘲諷	*great*, really?, oh, sure.	*Oh, sure. Like that ever works.*
生氣	重句、句點、強調	*You knew. You knew and you did it anyway.*
細語／親切	小句、延音、`...`	*It’s okay... I’m here.*
幽默	haha, 😂, 語助詞	*That’s not a cat. That’s a gremlin, haha.*
緊張／猶豫	um, well, I guess	*Um... maybe we should wait?*
常見自然語氣效果加入方式
語氣效果	表達方式（可中英文混用）	範例說明
笑聲	`[laughs]`、「哈哈哈」、「呵呵」等	模擬自然笑聲
拉長尾音	重複字元、加破折號 `──`	「不要嘛──」、「好啦～～」
疑問	加上問號，提升語調	「你真的這麼做了？」
驚訝	加驚嘆號或加上語氣詞	「哇！真的假的？」、「你居然…」
悄悄話	`[whispering]` 或「（小聲說）」	模擬壓低音量的說話方式
思考、猶豫	「嗯…」、「呃…」	增加停頓與思考感

OpenAI GPT-4O mini TTS 文字轉語音