{"schema":"hottub-news/story/v1","story":"st_tg6i2gietsdo5oa5uy7q","title":"将语音与音乐作为单一连贯音轨共同生成，AI 音乐制作平台 Suno 推出 Speech 语音功能","title_en":"Combining speech and music as a single coherent audio track, AI music production platform Suno launches Speech voice function","outlets":1,"brief":null,"page":"https://hottub.news/stories/combining-speech-and-music-as-a-single-coherent-audio-track-ai-music-tg6i2giets","count":1,"items":[{"id":"n_tg6i2gietsdo5oa5uy7q","seq":1489302,"kind":"article","title":"将语音与音乐作为单一连贯音轨共同生成，AI 音乐制作平台 Suno 推出 Speech 语音功能","title_en":"Combining speech and music as a single coherent audio track, AI music production platform Suno launches Speech voice function","url":"https://www.ithome.com/1/009/440.htm","summary":"IT之家 10 月 3 日消息，当地时间 10 月 1 日，AI 音乐制作平台 Suno 宣布推出 Speech，Suno 宣称这是 业界首个能够将语音与音乐作为单一连贯音轨共同生成的音频模型 。 据悉，该模型并非像传统工作流那样先做 TTS（文本转语音）再拼接 BGM，而是端到端一体化生成，是首个能单次生成完整融合“语音朗读 + 原创 BGM”的端到端闭源音频模型。 在过去一个月中，Suno 与小范围用户共同测试了该功能，现在正式面向所有人开放公测（Beta）。 官方表示，通过 Speech，用户可以轻松创作带有 BGM 的语音音频。该功能已直接内置于 Suno 中：只需输入一个灵感、一首诗或一段文字，再描述用户心目中的音色与音乐风格即可。 IT之家注意到，Suno 官方也指出了当前 Beta 版的不足，当前版本偶发口音不稳定的问题，例如英音可能会在中途漂移到澳音然后又漂回来；语调与情感停顿有时会显得“过于戏剧化”，导致断句节奏过慢。","published":"2026-10-03T06:01:12Z","seen":"2026-10-03T06:43:14Z","lang":"zh","country":"CN","source":{"id":"kite-ithome-com-f1cdd0","name":"ithome.com","domain":"ithome.com","outlet":{"wikidata":"Q28413779","name":"IThome","type":"website","country":"CN","designations":["website"]}},"via":"kite-ithome-com-f1cdd0","entities":[{"id":"Q22634","name":"Suno","type":"org"}],"story":"st_tg6i2gietsdo5oa5uy7q","category":"science-technology","category_p":0.8799999952316284,"sentiment":"neutral","tone":0.36000001430511475,"political":0.029999999329447746}]}