Gemini勁過ChatGPT?AI Podcast功能等你試!

Ai




我想ChatGPT偷學的Gemini功能,最近變得更強大了

自從ChatGPT Plus用戶可以使用Deep Research功能後,我一直用它來做各種深入研究。這種更長、更詳盡的報告,對於想深入了解某個話題,比一般和AI的簡短對話更有用。它非常適合查詢想買的產品或想去的旅遊地點。

舉例來說,我曾用ChatGPT Deep Research計劃東京之旅,未來也會用它規劃其他地方。因為報告內容豐富,我不需要一次過看完,而是可以隨時回來翻閱部分內容。

但當我請ChatGPT列出符合特定條件的「step-on」滑雪板靴款式時,這份深度報告就得仔細看才能決定買哪款。報告很長,而我正準備跑下一場馬拉松,於是決定用它的朗讀功能聽它念出來。

結果呢?不太理想。可能是朗讀速度太慢,我沒空等。於是我用iPhone的備忘錄複製整份報告,再啟用無障礙功能讓Siri在我跑步時朗讀,螢幕還要一直開著。

與此同時,Google的Gemini有一個超讚功能,可以把AI對話變成播客,叫做Audio Overviews。這功能最初在去年9月的NotebookLM亮相,後來Google把它帶到Gemini app,而且功能還在進步,而OpenAI卻還未抓住這個大好機會。

Audio Overviews能把任何AI對話變成一個有AI主持的播客,主持人會討論你交代Gemini做的事情。例如你上傳一堆長文件,請Gemini總結或回答問題。與其看詳細報告,不如聽AI主持的播客,我肯定會這樣做——只可惜ChatGPT還沒有這功能。

回到我剛才那例子,我只能聽Siri用單調聲音念那份長長的Deep Research報告,跑步時很容易走神,完全聽不入腦。

這份Deep Research報告本來是我選滑雪板靴的好方法,但我根本記不住內容,得再「聽」一次。

令人驚訝的是,Siri朗讀還算流暢,沒有停頓或卡頓。但整體感覺好無趣,Siri那種平穩語調,缺乏角色互動,反而令我更難集中精神,尤其是當天我心思飄忽。

如果是有兩位AI嘉賓主持的播客效果就完全不同,他們會輪流討論主題,甚至互相插嘴,這就是Audio Overviews令人興奮的地方。雖然我聽播客時偶爾也會走神,但播客更有趣味,主持人有個性,比起Siri讀長文好多了。

Audio Overviews支援超過50種語言,對不講英語或多語言用戶來說是大好消息。

用戶還可以上傳不同語言的內容,無需翻譯,直接轉成自己喜歡語言的播客。

正如文章最後短片所示,Gemini AI播客主持人會在不同語言中保持個性與語氣,彼此互相打趣和打斷,呈現資訊,無論用什麼語言都一樣生動。

我非常羨慕這功能,尤其試過把ChatGPT Deep Research用Siri「播客化」後,效果總是差強人意。試過多次,結果都一樣。我寧願在ChatGPT app內直接做到。

如果這是Audio Overviews,第二個角色現在應該會插話,告訴我OpenAI的ChatGPT技術其實有條件做到這種播客。

首先,ChatGPT能處理各種輸入,包括檔案、圖片和文字,並能產生大型Deep Research報告。

其次,ChatGPT可以朗讀答案,且有先進語音模式,支援多種個性化聲音。

最後,ChatGPT本身已支援多種語言,包括上述多聲音模式。

將這些功能結合起來,就能做出像Audio Overviews那樣的功能,讓用戶按個按鈕,就能把對話變成有兩位虛擬主持人的播客。

當然,我本可以直接用Gemini來滿足這需求,享受AI播客娛樂。但我始終是ChatGPT用戶,它是我主要的AI聊天機器人,我不會輕易轉用其他平台。

不過既然各大AI公司都在競爭,推出相似功能,我希望OpenAI能盡快推出自己的AI播客版本,別再讓競爭對手領先。

評論與啟發

這篇文章凸顯了AI語音與內容消費方式的下一波革命:從純文字到多角色播客互動的轉變。Gemini的Audio Overviews功能不單是把文字轉語音,而是模擬多角色對話,讓資訊更生動、易於吸收,這正是當今用戶在碎片化時間內渴望的內容體驗。

相比之下,ChatGPT目前雖有先進語音和多語音人格功能,但缺乏將這些特性整合成一個完整的「AI播客」體驗,顯示OpenAI在用戶體驗設計上還有進步空間。這提醒我們,技術能力並非唯一關鍵,如何包裝及呈現內容,才是吸引用戶的致勝點。

此外,Gemini支援多語言且能保持角色特性,顯示AI跨語言互動的潛力巨大,對全球多語言市場是重大利好。OpenAI若能迅速跟進,整合其多語言和多角色語音技術,將在國際市場更具競爭力。

最後,這種AI生成播客的概念,或許能催生新的內容創作形態:用戶不再是被動閱讀者,而是能主動定制個人化、角色互動的知識播客,甚至在運動、通勤等場景中用更輕鬆方式獲取深度資訊。這是未來AI助理與內容消費融合的趨勢,值得業界密切關注與投入資源開發。

以上文章由特價GPT API KEY所翻譯及撰寫。而圖片則由FLUX根據內容自動生成。

🎨 Nano Banana Pro 圖像生成器|打幾句說話就出圖

想畫人像、產品圖、插畫?SSFuture 圖像生成器支援 Flux Gemini Nano Banana Pro 改圖 / 合成, 打廣東話都得,仲可以沿用上一張圖繼續微調。

🆓 Flux 模型即玩,不用登入
🤖 登入後解鎖 Gemini 改圖
📷 支援上載參考圖再生成
⚡ 每天免費額度任你玩
✨ 即刻玩 AI 畫圖
一隻在香港茶餐的喝奶茶的貓 Certainly! Here is your enhanced, artistic, and detailed prompt for an AI image generator:

---

A captivating portrait of a young Asian woman, inspired by Imada Mio and embodying an exquisitely delicate, doll-like (精緻洋娃娃臉) aesthetic. She has large, round, expressive eyes that radiate innocence and curiosity, subtly accented with a moist shimmer. Her petite V-line face is framed by soft, rosy cheeks, and her lips are naturally pink and slightly parted, exuding an energetic, slightly flirty, yet pure aura. Her expression is a candid blend of sweetness and playful allure.

Her long, dark brown hair is artfully tousled with a messy morning (剛睡醒的凌亂感) effect—loose strands fall gently around her face, conveying natural volume and effortless beauty. The hair has a silky texture, catching the light in places, suggesting a recent awakening.

She is dressed in an oversized, translucent white button-down shirt (男友風白襯衫) with the top buttons casually undone, delicately revealing her collarbones and a slender neckline. The shirt drapes loosely, giving a tasteful "bottomless" look (下衣失蹤風格), her bare legs just barely visible beneath the shirt's hem, enhancing the innocent-meets-sensual ambiance.

The composition is styled in the manner of a Japanese Gravure Photobook (寫真集風格), exuding a pure & sexy vibe with an airy, dreamy atmosphere. Employ bright, high-key lighting for a clean, luminous effect that highlights her velvety soft skin texture. Use Fujifilm PRO 400H film tones for subtle pastel hues, gentle contrast, and a seamless blend of natural colors, further enriching the soft, ethereal, and intimate photographic quality.

The background is minimalist and softly blurred, ensuring complete focus on the subject, and enhancing the overall sense of warmth, comfort, and inviting allure typical of high-end Japanese photobooks.

--- Base Setup
keep 100 percent facial information adherence of the attached image and turn her into a girl standing beneath autumn leaves outside a traditional wooden structure in a live action photograph or movie still, wearing a complex suggestive outfit that harmonizes with the warm fall tones.

Shot and Camera
Three quarter shot at slightly low height, framing her off center to the right so the yellow leaves and carved wooden panels dominate the left. Maintain the intimate close framing and vertical orientation feel of the reference.

Identity and Pose
Preserve her age read, build, silhouette, hairstyle length, and skin tone. She leans lightly against the doorframe, one hand grazing a hanging leaf, her posture relaxed and candid, 8k Photorealistic and hyper realistic.

Lighting and Environment
Soft warm daylight filters through the leaves, casting dappled highlights on her hair and outfit. Ground her feet on aged wooden flooring with natural grain, faint scuffs, and subtle contact shadows.

Masking and Constraints
Change only wardrobe and placement while keeping lighting, perspective, white balance, pose, face geometry, body proportions, and silhouette the same. Absolutely no added text, no CGI look, no plastic skin, no floating feet, with consistent perspective and correct contact shadows.

🎬 YouTube Premium 家庭 Plan成員一位 只需 HK$148/年

不用提供密碼、不用VPN、無需轉區
直接升級你的香港帳號 ➜ 即享 YouTube + YouTube Music 無廣告播放

立即升級 🔗