{"id":52715,"date":"2026-05-07T12:10:45","date_gmt":"2026-05-07T04:10:45","guid":{"rendered":"https:\/\/www.1ai.net\/?p=52715"},"modified":"2026-05-07T12:10:45","modified_gmt":"2026-05-07T04:10:45","slug":"inworld-ai-%e5%8f%91%e5%b8%83-realtime-tts-2-%e8%af%ad%e9%9f%b3%e6%a8%a1%e5%9e%8b%ef%bc%9a%e5%8f%af%e6%84%9f%e7%9f%a5%e7%94%a8%e6%88%b7%e6%83%85%e7%bb%aa%ef%bc%8c%e6%94%af%e6%8c%81-100-%e7%a7%8d","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/52715.html","title":{"rendered":"Inworld AI releases Realtime TTS-2 voice model: Perceptive user emotions, supporting 100 languages to keep the same voice"},"content":{"rendered":"<p>5 \u6708 7 \u65e5\u6d88\u606f\uff0c\u6628\u5929\uff0c<a href=\"https:\/\/www.1ai.net\/en\/tag\/inworld\" title=\"\u3010\u67e5\u770b\u542b\u6709[Inworld]\u6807\u7b7e\u7684\u6587\u7ae0\u3011\" target=\"_blank\" rel=\"noopener\">Inworld<\/a> AI \u53d1\u5e03\u65b0\u4e00\u4ee3<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e8%af%ad%e9%9f%b3%e6%a8%a1%e5%9e%8b\" title=\"\u3010\u67e5\u770b\u542b\u6709[\u8bed\u97f3\u6a21\u578b]\u6807\u7b7e\u7684\u6587\u7ae0\u3011\" target=\"_blank\" rel=\"noopener\">\u8bed\u97f3\u6a21\u578b<\/a> Realtime TTS-2\uff0c\u4ee5\u7814\u7a76\u9884\u89c8\u7248\u5f62\u5f0f\u901a\u8fc7 Inworld API \u548c Inworld Realtime API \u5411\u5f00\u53d1\u8005\u5f00\u653e\u3002<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-52716\" title=\"1fbeb0a4j00tenfl1002id000u000nym\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2026\/05\/1fbeb0a4j00tenfl1002id000u000nym.jpg\" alt=\"1fbeb0a4j00tenfl1002id000u000nym\" width=\"1080\" height=\"862\" \/><\/p>\n<p>TTS-2 \u7684\u6838\u5fc3\u53d8\u5316\u5728\u4e8e\u4ece\u5355\u5411\u6587\u672c\u8f6c\u8bed\u97f3\u7ba1\u7ebf\u8f6c\u5411\u95ed\u73af\u5b9e\u65f6\u5bf9\u8bdd\u67b6\u6784\uff1a\u6a21\u578b\u76f4\u63a5\u63a5\u6536\u5bf9\u8bdd\u4e2d\u7684\u5b9e\u9645\u97f3\u9891\uff0c\u4ece\u800c\u611f\u77e5\u7528\u6237\u7684\u8bed\u6c14\u3001\u8282\u594f\u4e0e\u60c5\u7eea\u72b6\u6001\u5e76\u4f5c\u51fa\u76f8\u5e94\u8c03\u6574\u3002\u65b0\u7248\u672c\u65b0\u589e\u56db\u9879\u80fd\u529b\uff1a<\/p>\n<p>\u8bed\u97f3\u6307\u4ee4\uff08Voice Direction\uff09\uff1a\u7528\u81ea\u7136\u8bed\u8a00\u63cf\u8ff0\u8868\u8fbe\u65b9\u5f0f\uff0c\u4f8b\u5982\u300c\u75b2\u60eb\u4f46\u6e29\u67d4\uff0c\u50cf\u521a\u4e0b\u73ed\u56de\u5bb6\u300d\uff0c\u6a21\u578b\u636e\u6b64\u8c03\u6574\u8bed\u97f3\u98ce\u683c\uff0c\u4e0d\u518d\u4f9d\u8d56\u56fa\u5b9a\u60c5\u611f\u6807\u7b7e\uff1b<\/p>\n<p>\u5bf9\u8bdd\u611f\u77e5\uff08Conversational Awareness\uff09\uff1a\u5728 Realtime \u4f1a\u8bdd\u4e2d\u81ea\u52a8\u63a5\u6536\u524d\u5e8f\u97f3\u9891\uff0c\u8bed\u6c14\u4e0e\u8282\u594f\u53ef\u8de8\u8f6e\u6b21\u5ef6\u7eed\uff1b<\/p>\n<p>\u8de8\u8bed\u8a00\u652f\u6301\uff08Crosslingual\uff09\uff1a\u5355\u4e00\u58f0\u97f3\u8eab\u4efd\u53ef\u5728\u8d85\u8fc7 100 \u79cd\u8bed\u8a00\u95f4\u65e0\u7f1d\u5207\u6362\uff0c\u58f0\u7ebf\u4e0e\u4eba\u7269\u7279\u5f81\u4fdd\u6301\u4e00\u81f4\uff0c\u652f\u6301\u540c\u4e00\u6bb5\u751f\u6210\u4e2d\u6df7\u7528\u591a\u8bed\uff1b<\/p>\n<p>\u9ad8\u7ea7\u8bed\u97f3\u8bbe\u8ba1\uff08Advanced Voice Design\uff09\uff1a\u65e0\u9700\u53c2\u8003\u97f3\u9891\uff0c\u901a\u8fc7\u6587\u5b57\u63cf\u8ff0\u5373\u53ef\u751f\u6210\u53ef\u590d\u7528\u58f0\u97f3\u89d2\u8272\uff0c\u5e76\u63d0\u4f9b\u300c\u5bcc\u6709\u8868\u73b0\u529b\u300d\u300c\u5747\u8861\u300d\u300c\u7a33\u5b9a\u300d\u4e09\u79cd\u6a21\u5f0f\u3002<\/p>\n<p>\u6b64\u5916\uff0c\u6a21\u578b\u652f\u6301\u5185\u8054\u975e\u8bed\u8a00\u6807\u8bb0\uff08\u5982\u3010\u7b11\u3011\u3010\u53f9\u6c14\u3011\uff09\u3001\u8bed\u97f3\u514b\u9686\uff08\u4e0a\u4f20 5 \u81f3 15 \u79d2\u97f3\u9891\u6837\u672c\u5373\u53ef\uff09\uff0cTTS \u5c42\u9996\u5305\u5ef6\u8fdf\u4f4e\u4e8e 200 \u6beb\u79d2\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"<p>News from May 7, yesterday, Inworld AI launched a new generation of voice models Realtime TTS-2, which are open to developers through Inworld API and Inworld Realtime API in the form of research previews. The core change of TTS-2 is the shift from a one-way text to a closed-ringed real-time dialogue structure: the model directly receives the actual audio in the conversation, thereby understanding the tone, rhythm and emotional state of the user and adjusting it accordingly. The new version adds four capabilities: Voice Direction: describe expression in natural languages, such as \"tired but gentle, like home from work\" , where the model adjusts the voice style and no longer relies on fixed emotional labels<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[146],"tags":[1149,1875],"collection":[],"class_list":["post-52715","post","type-post","status-publish","format-standard","hentry","category-news","tag-inworld","tag-1875"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/52715","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/comments?post=52715"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/52715\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=52715"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=52715"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=52715"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=52715"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}