Salesforce Agentforce加入AI語音客服新功能

Ai




Salesforce為Agentforce AI客戶服務軟件加入語音通話功能

Salesforce宣布推出Agentforce Voice功能,令企業能夠透過人工智能代理以語音形式回應客戶的服務電話,打破以往只限文字聊天的限制。這項新功能讓企業可自定義語音的語氣和語速,甚至可調整特定詞彙的發音,並且支持用戶在通話中打斷AI代理,提升互動靈活度。這個消息是在本週於舊金山舉行的Dreamforce大會前夕公布的。

語音技術正成為生成式人工智能熱潮中的重要一環。自2022年底OpenAI推出ChatGPT後,生成式AI主要以文字提示為主。過去一年,OpenAI及Anthropic等公司已讓聊天機器人能以自然語音進行對話,避免機械化的感覺。如今,這種語音互動的能力逐漸滲透到企業軟件中。

Agentforce Voice將整合亞馬遜、Five9、Genesys、Nice及Ericsson旗下Vonage等企業電話系統。前Salesforce聯席CEO Bret Taylor亦在這市場發力,他於2023年創辦的Sierra公司去年宣布其AI代理已能「主動接聽電話」,市值達100億美元,客戶包括ADT、SiriusXM和SoFi。

今年,Salesforce面對投資者壓力,部分原因是市場擔心AI技術深入程式碼領域會削弱軟件公司業務。2025年迄今其股價下跌約28%,而納斯達克指數同期上升約15%。Anthropic於9月透露,其Claude Sonnet 4.5模型能在30小時內開發出類似Salesforce Slack的聊天應用。Salesforce最新財報亦警告,新AI產品可能改變企業人力需求,對公司產品需求帶來負面影響。

不過,Salesforce CEO Marc Benioff對此風險表示淡化。他上月接受CNBC訪問時說:「若把市場看成零和遊戲,認為一切都會被取代或改變,那就不是在經營公司,因為生意不是這樣運作的,生意是漸進、演化、成長和發展的,我們不認為會有那種劇變。」

Salesforce去年推出Agentforce,當時主打以生成式AI模型協助回應文字聊天的客戶請求,目前已在超過12,000個項目中實施,但市場對其受歡迎程度仍存疑。瑞銀資本市場分析師上週發報告稱:「投資者對Agentforce的熱情已趨於理性,因採用率未達預期。」此外,Salesforce將於11月提供Agent Script軟件的早期使用權,方便組織自訂代理的對話內容和行為。

評論與啟示

Salesforce此次為Agentforce加入語音功能,正是回應生成式AI從純文字對話走向多模態溝通的趨勢。語音交互具備更自然、更即時的溝通優勢,對客服行業尤其重要,因為電話仍是許多客戶首選的溝通渠道。企業若能靈活調整語音語氣、速度及發音,無疑有助提升用戶體驗和滿意度。

然而,市場對Agentforce的接受度不及預期,提醒我們技術的成熟和產品的落地之間仍有鴻溝。企業客戶在導入AI客服時,除了技術本身,還需考慮整合成本、員工培訓、客戶信任及隱私合規等多方面因素。Salesforce的競爭對手如Sierra快速切入市場,展示了AI語音客服的巨大潛力,但同時也加劇了市場競爭。

Benioff對AI帶來的風險持樂觀態度,認為商業是漸進演化而非激烈革命,這種看法在穩健經營層面值得肯定。但從長遠來看,AI技術的快速發展仍可能顛覆傳統工作模式和價值鏈,企業必須保持敏銳,積極調整策略以應對未來挑戰。

總括而言,Salesforce的Agentforce Voice是企業AI客服的又一步進化,象徵著AI不僅是文字助理,更是多渠道溝通的智能夥伴。對香港及華語市場而言,此類技術的本地化應用和語言優化將是關鍵,值得業界持續關注和探索。

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。

✨🎱 Instagram留言 →

AI即回覆下期六合彩預測

🧠 AI 根據統計數據即時生成分析

💬 只要留言,AI就會即刻覆你心水組合

🎁 完!全!免!費!快啲嚟玩!

IG 貼文示意圖 AI 即時回覆示意圖

下期頭獎號碼

📲 去 Instagram 即刻留言

🎨 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
生成電影級人物外拍特寫畫面,16:9,4K:

秋季溫暖的下午,一位年輕的亞洲女性,甜美微笑,穿著一件寬鬆的、露肩的米白色短版毛衣、黑色修身牛仔褲。她站在海邊一條蜿蜒的小徑上,輕輕斜靠在鮮豔的藍色木製欄杆上。

F1.4大光圈鏡頭85mm焦段,中機位特寫人物3/4身像,前景有模糊淺景深的蘆葦或芒草,遠景則是模糊的海岸線跟藍天。黑柔濾鏡,減少對比高光處形成光暈。 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.