{"@context":"https://schema.org","@type":"NewsArticle","generatedAt":"2026-10-22T18:00:34.180Z","headline":"Suno 推出 Speech 语音功能，语音与音乐可单轨共同生成","description":"当地时间 10 月 1 日，AI 音乐制作平台 Suno 宣布推出 Speech 功能并开放公测（Beta），官方称这是业界首个将语音与音乐作为单一连贯音轨共同生成的端到端闭源音频模型。该功能内置于 Suno 中，输入一段文字并描述音色与音乐风格即可生成带 BGM 的语音音频；官方承认当前版本偶发口音漂移和语调过于戏剧化的问题。","url":"https://www.aioga.com/news/ji0urqug3bzzbbz4vg0bhulkr/","mainEntityOfPage":"https://www.aioga.com/news/ji0urqug3bzzbbz4vg0bhulkr/","datePublished":"2026-10-03T06:01:12.000Z","dateModified":"2026-10-03T06:01:12.000Z","inLanguage":"zh-CN","publisher":{"@type":"NewsMediaOrganization","name":"Aioga","url":"https://www.aioga.com"},"citation":["https://www.ithome.com/1/009/440.htm","https://aihot.news/items/ji0urqug3bzzbbz4vg0bhulkr"],"canonicalUrl":"https://www.aioga.com/news/ji0urqug3bzzbbz4vg0bhulkr/","directAnswer":{"@type":"Answer","text":"Aioga 编辑摘要：当地时间 10 月 1 日，AI 音乐制作平台 Suno 宣布推出 Speech 功能并开放公测（Beta），官方称这是业界首个将语音与音乐作为单一连贯音轨共同生成的端到端闭源音频模型。 Aioga 将其归入「行业动态」方向，重点关注它对真实使用和行业竞争的影响。","url":"https://www.aioga.com/news/ji0urqug3bzzbbz4vg0bhulkr/","dateCreated":"2026-10-03T06:01:12.000Z","author":{"@type":"Organization","@id":"https://www.aioga.com/authors/aioga-editorial/#editorial-team","name":"Aioga Editorial Team","url":"https://www.aioga.com/authors/aioga-editorial/"}},"evidence":[{"@type":"CreativeWork","name":"IT之家 source article","url":"https://www.ithome.com/1/009/440.htm","datePublished":"2026-10-03T06:01:12.000Z","provider":{"@type":"Organization","name":"IT之家","url":"https://www.ithome.com/1/009/440.htm"}},{"@type":"CreativeWork","name":"AIHot archive record","url":"https://aihot.news/items/ji0urqug3bzzbbz4vg0bhulkr","datePublished":"2026-10-03T06:01:12.000Z","provider":{"@type":"Organization","name":"AIHot","url":"https://aihot.news/items/ji0urqug3bzzbbz4vg0bhulkr"}}],"aggregationSource":"IT之家","originalPublisher":{"name":"IT之家","url":"https://www.ithome.com/1/009/440.htm"},"geoDeepAnswer":null,"article":{"id":"ji0urqug3bzzbbz4vg0bhulkr","slug":"ji0urqug3bzzbbz4vg0bhulkr","url":"https://www.aioga.com/news/ji0urqug3bzzbbz4vg0bhulkr/","title":"Suno 推出 Speech 语音功能，语音与音乐可单轨共同生成","title_en":"","summary":"当地时间 10 月 1 日，AI 音乐制作平台 Suno 宣布推出 Speech 功能并开放公测（Beta），官方称这是业界首个将语音与音乐作为单一连贯音轨共同生成的端到端闭源音频模型。该功能内置于 Suno 中，输入一段文字并描述音色与音乐风格即可生成带 BGM 的语音音频；官方承认当前版本偶发口音漂移和语调过于戏剧化的问题。","source":"IT之家","sourceUrl":"https://www.ithome.com/1/009/440.htm","aiHotUrl":"https://aihot.news/items/ji0urqug3bzzbbz4vg0bhulkr","publishedAt":"2026-10-03T06:01:12.000Z","category":"行业动态","score":58,"selected":false,"articleBody":["IT之家：https://www.ithome.com/ 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。"],"articleImages":[{"sourceUrl":"https://img.ithome.com/newsuploadfiles/2026/10/90ae17d2-6815-4cf3-9f31-b3981ccf4d44.jpg?x-bce-process=image/format,f_auto","alt":"","afterParagraph":0,"url":"/media/articles/ji0urqug3bzzbbz4vg0bhulkr/30eb8f249e3c67e0.jpg"}],"mediaStatus":"ok","articleBodyZh":["Suno 推出 Speech 语音功能，语音与音乐可单轨共同生成 这条更新来自 ithome.com，发布时间为 2026-10-03，Aioga 保留原文入口以便核验。","摘要：当地时间 10 月 1 日，AI 音乐制作平台 Suno 宣布推出 Speech 功能并开放公测（Beta），官方称这是业界首个将语音与音乐作为单一连贯音轨共同生成的端到端闭源音频模型。该功能内置于 Suno 中，输入一段文字并描述音色与音乐风格即可生成带 BGM 的语音音频；官方承认当前版本偶发口音漂移和语调过于戏剧化的问题。","背景：背景分析：公司与行业类动态需要放在竞争格局、商业化路径、资本信号和监管环境中观察，单条公告不能代表最终结果。","Aioga 观察：Aioga 判断：这条动态更适合作为行业观察信号，当前信息足以建立线索，但不足以推导长期结论。","影响与后续：影响分析：对相关团队而言，短期应先核对来源、可用范围和实际成本，再判断是否值得接入或跟进。 后续观察：继续观察官方文件、合作落地、收入或用户信号、竞品动作和监管后续。"],"translationStatus":"","bodyOrigin":"source-page","editorial":{"summary":"Aioga 编辑摘要：当地时间 10 月 1 日，AI 音乐制作平台 Suno 宣布推出 Speech 功能并开放公测（Beta），官方称这是业界首个将语音与音乐作为单一连贯音轨共同生成的端到端闭源音频模型。 Aioga 将其归入「行业动态」方向，重点关注它对真实使用和行业竞争的影响。","background":"背景分析：公司与行业类动态需要放在竞争格局、商业化路径、资本信号和监管环境中观察，单条公告不能代表最终结果。","viewpoint":"Aioga 判断：这条动态更适合作为行业观察信号，当前信息足以建立线索，但不足以推导长期结论。","implications":"影响分析：对相关团队而言，短期应先核对来源、可用范围和实际成本，再判断是否值得接入或跟进。","nextStep":"后续观察：继续观察官方文件、合作落地、收入或用户信号、竞品动作和监管后续。","evidenceRefs":["title","summary","articleBody"],"confidence":"medium","status":"published","aiGenerated":false,"autoApproved":true,"generatedBy":"rule-safe-fallback","generatedAt":"2026-10-22T18:36:34.151Z","sourceHash":"688291be5c066b22","validation":{"passed":true,"mode":"rule-safe-fallback","checks":["schema","length","source-attribution","no-html"]}},"tags":["行业动态","IT之家"],"translations":{"zh-CN":{"title":"Suno 推出 Speech 语音功能，语音与音乐可单轨共同生成","summary":"当地时间 10 月 1 日，AI 音乐制作平台 Suno 宣布推出 Speech 功能并开放公测（Beta），官方称这是业界首个将语音与音乐作为单一连贯音轨共同生成的端到端闭源音频模型。该功能内置于 Suno 中，输入一段文字并描述音色与音乐风格即可生成带 BGM 的语音音频；官方承认当前版本偶发口音漂移和语调过于戏剧化的问题。","category":"行业动态","source":"IT之家","aggregationSource":"IT之家","pageTitle":"Suno 推出 Speech 语音功能，语音与音乐可单轨共同生成 - Aioga AI资讯","description":"当地时间 10 月 1 日，AI 音乐制作平台 Suno 宣布推出 Speech 功能并开放公测（Beta），官方称这是业界首个将语音与音乐作为单一连贯音轨共同生成的端到端闭源音频模型。该功能内置于 Suno 中，输入一段文字并描述音色与音乐风格即可生成带 BGM 的语音音频；官方承认当前版本偶发口音漂移和语调过于戏剧化的问题。","url":"https://www.aioga.com/news/ji0urqug3bzzbbz4vg0bhulkr/","articleBody":["Suno 推出 Speech 语音功能，语音与音乐可单轨共同生成 这条更新来自 ithome.com，发布时间为 2026-10-03，Aioga 保留原文入口以便核验。","摘要：当地时间 10 月 1 日，AI 音乐制作平台 Suno 宣布推出 Speech 功能并开放公测（Beta），官方称这是业界首个将语音与音乐作为单一连贯音轨共同生成的端到端闭源音频模型。该功能内置于 Suno 中，输入一段文字并描述音色与音乐风格即可生成带 BGM 的语音音频；官方承认当前版本偶发口音漂移和语调过于戏剧化的问题。","背景：背景分析：公司与行业类动态需要放在竞争格局、商业化路径、资本信号和监管环境中观察，单条公告不能代表最终结果。","Aioga 观察：Aioga 判断：这条动态更适合作为行业观察信号，当前信息足以建立线索，但不足以推导长期结论。","影响与后续：影响分析：对相关团队而言，短期应先核对来源、可用范围和实际成本，再判断是否值得接入或跟进。 后续观察：继续观察官方文件、合作落地、收入或用户信号、竞品动作和监管后续。"]},"en":{"title":"Suno launches the Speech voice feature, allowing voice and music to be generated together on a single track.","summary":"On October 1 local time, AI music production platform Suno announced the launch of its Speech feature and the opening of its public beta (Beta). The company said it is the industry’s first end-to-end closed-source audio model to generate speech and music together as a single coherent audio track. Built into Suno, the feature can generate voice audio with BGM by inputting a passage of text and describing the desired vocal timbre and music style. The company acknowledged that the current version occasionally suffers from accent drift and overly dramatic intonation.","category":"Industry","source":"IT之家","aggregationSource":"IT之家","pageTitle":"Suno launches the Speech voice feature, allowing voice and music to be generated together on a single track. - Aioga AI News","description":"On October 1 local time, AI music production platform Suno announced the launch of its Speech feature and the opening of its public beta (Beta). The company said it is the industry...","url":"https://www.aioga.com/en/news/ji0urqug3bzzbbz4vg0bhulkr/","contentTranslated":true,"translationStatus":"translated","translationRetryAt":"","translationError":"","sourceHash":"8541ac0af2332570","translatedAt":"2026-10-03T18:41:05.619Z"},"ja":{"title":"SunoはSpeech音声機能を導入し、音声と音楽を単一トラックで共に生成できる","summary":"現地時間10月1日、AI音楽制作プラットフォームSunoは、Speech機能を導入しパブリックベータを開始すると発表しました。公式によれば、これは業界初となる、音声と音楽を単一の一貫したトラックとして共同生成するエンドツーエンドのクローズドソースオーディオモデルです。この機能はSunoに組み込まれており、テキストを入力し音色や音楽スタイルを指定するだけでBGM付きの音声オーディオを生成できます。公式は現在のバージョンでは、アクセントのズレや抑揚が過度に劇的になる問題が時折発生することを認めています。","category":"業界動向","source":"IT之家","aggregationSource":"IT之家","pageTitle":"SunoはSpeech音声機能を導入し、音声と音楽を単一トラックで共に生成できる - Aioga AIニュース","description":"現地時間10月1日、AI音楽制作プラットフォームSunoは、Speech機能を導入しパブリックベータを開始すると発表しました。公式によれば、これは業界初となる、音声と音楽を単一の一貫したトラックとして共同生成するエンドツーエンドのクローズドソースオーディオモデルです。この機能はSunoに組み込まれており、テキストを入力し音色や音楽スタイルを指定するだけでBG...","url":"https://www.aioga.com/ja/news/ji0urqug3bzzbbz4vg0bhulkr/","contentTranslated":true,"translationStatus":"translated","translationRetryAt":"","translationError":"","sourceHash":"8541ac0af2332570","translatedAt":"2026-10-03T18:41:38.490Z"},"ko":{"title":"Suno는 Speech 음성 기능을 출시하며, 음성과 음악을 단일 트랙에서 함께 생성할 수 있습니다.","summary":"현지 시간 10월 1일, AI 음악 제작 플랫폼 Suno는 Speech 기능을 출시하고 공개 베타 테스트를 시작한다고 발표했다. 공식 발표에 따르면 이는 업계 최초로 음성과 음악을 단일 연속 음원으로 함께 생성하는 엔드투엔드 폐쇄형 오디오 모델이다. 이 기능은 Suno에 내장되어 있으며, 텍스트를 입력하고 음색과 음악 스타일을 설명하면 BGM이 포함된 음성 오디오를 생성할 수 있다. 공식적으로 현재 버전에서는 가끔 억양이 벗어나거나 음조가 지나치게 극적이 되는 문제가 발생한다고 인정했다.","category":"업계 동향","source":"IT之家","aggregationSource":"IT之家","pageTitle":"Suno는 Speech 음성 기능을 출시하며, 음성과 음악을 단일 트랙에서 함께 생성할 수 있습니다. - Aioga AI 뉴스","description":"현지 시간 10월 1일, AI 음악 제작 플랫폼 Suno는 Speech 기능을 출시하고 공개 베타 테스트를 시작한다고 발표했다. 공식 발표에 따르면 이는 업계 최초로 음성과 음악을 단일 연속 음원으로 함께 생성하는 엔드투엔드 폐쇄형 오디오 모델이다. 이 기능은 Suno에 내장되어 있으며, 텍스트를 입력하고 음색과 음악 스...","url":"https://www.aioga.com/ko/news/ji0urqug3bzzbbz4vg0bhulkr/","contentTranslated":true,"translationStatus":"translated","translationRetryAt":"","translationError":"","sourceHash":"8541ac0af2332570","translatedAt":"2026-10-03T18:41:32.707Z"},"es":{"title":"Suno lanzó la función de voz Speech, donde la voz y la música pueden generarse conjuntamente en una sola pista","summary":"El 1 de octubre, hora local, la plataforma de producción musical basada en IA Suno anunció el lanzamiento de la función Speech y la apertura de su beta pública (Beta). Según la empresa, se trata del primer modelo de audio de extremo a extremo y de código cerrado del sector que genera conjuntamente la voz y la música como una única pista de audio coherente. La función está integrada en Suno: basta con introducir un texto y describir el timbre de voz y el estilo musical para generar un audio hablado con música de fondo (BGM). La empresa reconoce que la versión actual presenta ocasionalmente problemas de deriva del acento y una entonación excesivamente dramática.","category":"Industria","source":"IT之家","aggregationSource":"IT之家","pageTitle":"Suno lanzó la función de voz Speech, donde la voz y la música pueden generarse conjuntamente en una sola pista - Aioga Noticias de IA","description":"El 1 de octubre, hora local, la plataforma de producción musical basada en IA Suno anunció el lanzamiento de la función Speech y la apertura de su beta pública (Beta). Según la emp...","url":"https://www.aioga.com/es/news/ji0urqug3bzzbbz4vg0bhulkr/","contentTranslated":true,"translationStatus":"translated","translationRetryAt":"","translationError":"","sourceHash":"8541ac0af2332570","translatedAt":"2026-10-03T18:46:18.828Z"},"fr":{"title":"Suno lance la fonctionnalité vocale Speech, permettant de générer conjointement la voix et la musique sur une seule piste.","summary":"Le 1er octobre, heure locale, la plateforme de création musicale par IA Suno a annoncé le lancement de la fonction Speech et l’ouverture de la bêta publique. Selon l’entreprise, il s’agit du premier modèle audio fermé de bout en bout de l’industrie à générer conjointement la voix et la musique en une seule piste cohérente. Cette fonction est intégrée à Suno : il suffit de saisir un texte et de décrire le timbre et le style musical pour générer un audio vocal avec BGM ; l’entreprise reconnaît que la version actuelle présente parfois des variations d’accent et un ton trop dramatique.","category":"Industrie","source":"IT之家","aggregationSource":"IT之家","pageTitle":"Suno lance la fonctionnalité vocale Speech, permettant de générer conjointement la voix et la musique sur une seule piste. - Aioga Actualités IA","description":"Le 1er octobre, heure locale, la plateforme de création musicale par IA Suno a annoncé le lancement de la fonction Speech et l’ouverture de la bêta publique. Selon l’entreprise, il...","url":"https://www.aioga.com/fr/news/ji0urqug3bzzbbz4vg0bhulkr/","contentTranslated":true,"translationStatus":"translated","translationRetryAt":"","translationError":"","sourceHash":"8541ac0af2332570","translatedAt":"2026-10-03T18:46:03.548Z"},"de":{"title":"Suno führt die Sprachfunktion „Speech“ ein; Sprache und Musik können gemeinsam auf einer einzigen Spur erzeugt werden.","summary":"Am 1. Oktober Ortszeit gab die KI-Musikproduktionsplattform Suno die Einführung der Speech-Funktion bekannt und öffnete sie für einen öffentlichen Beta-Test (Beta). Laut dem Unternehmen handelt es sich um das branchenweit erste durchgängige Closed-Source-Audiomodell, das Sprache und Musik gemeinsam als eine einzige zusammenhängende Tonspur erzeugt. Die Funktion ist in Suno integriert: Durch Eingabe eines Textes und einer Beschreibung der Klangfarbe und des Musikstils lässt sich eine Sprachaufnahme mit BGM erzeugen. Das Unternehmen räumte ein, dass es in der aktuellen Version gelegentlich zu wechselnden Akzenten und überdramatischer Intonation kommt.","category":"行业动态","source":"IT之家","aggregationSource":"IT之家","pageTitle":"Suno führt die Sprachfunktion „Speech“ ein; Sprache und Musik können gemeinsam auf einer einzigen Spur erzeugt werden. - Aioga KI-News","description":"Am 1. Oktober Ortszeit gab die KI-Musikproduktionsplattform Suno die Einführung der Speech-Funktion bekannt und öffnete sie für einen öffentlichen Beta-Test (Beta). Laut dem Untern...","url":"https://www.aioga.com/de/news/ji0urqug3bzzbbz4vg0bhulkr/","contentTranslated":true,"translationStatus":"translated","translationRetryAt":"","translationError":"","sourceHash":"8541ac0af2332570","translatedAt":"2026-10-03T18:46:18.592Z"},"pt-BR":{"title":"Suno lançou a função de voz Speech, voz e música podem ser geradas juntas em uma única faixa","summary":"No dia 1º de outubro, horário local, a plataforma de produção musical por IA Suno anunciou o lançamento da função Speech e a abertura de testes públicos (Beta). Segundo a empresa, este é o primeiro modelo de áudio proprietário de ponta a ponta do setor que gera voz e música como uma única faixa contínua. A função está incorporada ao Suno; ao inserir um texto e descrever o timbre e o estilo musical, é possível gerar áudio de fala com BGM. A empresa admite que a versão atual apresenta ocasionalmente desvios de sotaque e entonação excessivamente dramática.","category":"行业动态","source":"IT之家","aggregationSource":"IT之家","pageTitle":"Suno lançou a função de voz Speech, voz e música podem ser geradas juntas em uma única faixa - Aioga Notícias de IA","description":"No dia 1º de outubro, horário local, a plataforma de produção musical por IA Suno anunciou o lançamento da função Speech e a abertura de testes públicos (Beta). Segundo a empresa,...","url":"https://www.aioga.com/pt-BR/news/ji0urqug3bzzbbz4vg0bhulkr/","contentTranslated":true,"translationStatus":"translated","translationRetryAt":"","translationError":"","sourceHash":"8541ac0af2332570","translatedAt":"2026-10-03T18:50:43.597Z"},"ru":{"title":"Suno представила голосовую функцию Speech: речь и музыка могут совместно генерироваться в одной дорожке.","summary":"1 октября по местному времени платформа для создания музыки с помощью ИИ Suno объявила о запуске функции Speech и открытии публичного бета-тестирования (Beta). Компания заявляет, что это первая в отрасли сквозная аудиомодель с закрытым исходным кодом, которая совместно генерирует речь и музыку как единую связную звуковую дорожку. Функция встроена в Suno: достаточно ввести текст и описать тембр голоса и музыкальный стиль, чтобы создать голосовую аудиодорожку с BGM. Компания признаёт, что в текущей версии иногда наблюдаются смещение акцента и чрезмерно драматичная интонация.","category":"行业动态","source":"IT之家","aggregationSource":"IT之家","pageTitle":"Suno представила голосовую функцию Speech: речь и музыка могут совместно генерироваться в одной дорожке. - Aioga Новости ИИ","description":"1 октября по местному времени платформа для создания музыки с помощью ИИ Suno объявила о запуске функции Speech и открытии публичного бета-тестирования (Beta). Компания заявляет, ч...","url":"https://www.aioga.com/ru/news/ji0urqug3bzzbbz4vg0bhulkr/","contentTranslated":true,"translationStatus":"translated","translationRetryAt":"","translationError":"","sourceHash":"8541ac0af2332570","translatedAt":"2026-10-03T18:51:23.874Z"},"ar":{"title":"أطلقت Suno ميزة Speech الصوتية، حيث يمكن توليد الصوت والموسيقى معًا على مسار واحد.","summary":"في 1 أكتوبر بالتوقيت المحلي، أعلنت منصة إنتاج الموسيقى بالذكاء الاصطناعي Suno إطلاق وظيفة Speech وفتحها للاختبار العام (Beta). وذكرت الشركة أن هذه الوظيفة تمثل أول نموذج صوتي مغلق المصدر من طرف إلى طرف في القطاع، يُولّد الكلام والموسيقى معًا باعتبارهما مسارًا صوتيًا واحدًا متسقًا. هذه الوظيفة مدمجة في Suno؛ إذ يمكن إدخال نص ووصف خامة الصوت وأسلوب الموسيقى لتوليد ملف صوتي كلامي مصحوب بموسيقى خلفية (BGM). وأقرت الشركة بأن الإصدار الحالي يعاني أحيانًا من انجراف في اللهجة ومن نبرة صوتية درامية أكثر من اللازم.","category":"行业动态","source":"IT之家","aggregationSource":"IT之家","pageTitle":"أطلقت Suno ميزة Speech الصوتية، حيث يمكن توليد الصوت والموسيقى معًا على مسار واحد. - Aioga أخبار الذكاء الاصطناعي","description":"في 1 أكتوبر بالتوقيت المحلي، أعلنت منصة إنتاج الموسيقى بالذكاء الاصطناعي Suno إطلاق وظيفة Speech وفتحها للاختبار العام (Beta). وذكرت الشركة أن هذه الوظيفة تمثل أول نموذج صوتي مغلق...","url":"https://www.aioga.com/ar/news/ji0urqug3bzzbbz4vg0bhulkr/","contentTranslated":true,"translationStatus":"translated","translationRetryAt":"","translationError":"","sourceHash":"8541ac0af2332570","translatedAt":"2026-10-03T18:50:43.521Z"},"hi":{"title":"Suno ने Speech वॉइस फ़ीचर लॉन्च किया है, जिसमें वॉइस और संगीत को एक ही ट्रैक पर साथ में जनरेट किया जा सकता है।","summary":"स्थानीय समयानुसार 1 अक्टूबर को AI संगीत निर्माण प्लेटफ़ॉर्म Suno ने Speech फ़ीचर लॉन्च करने और उसका सार्वजनिक बीटा (Beta) परीक्षण शुरू करने की घोषणा की। कंपनी के अनुसार, यह उद्योग का पहला एंड-टू-एंड क्लोज़्ड-सोर्स ऑडियो मॉडल है जो आवाज़ और संगीत को एक ही सुसंगत ऑडियो ट्रैक के रूप में साथ उत्पन्न करता है। Suno में अंतर्निहित इस फ़ीचर से टेक्स्ट दर्ज करके और आवाज़ की विशेषताओं तथा संगीत शैली का वर्णन करके BGM सहित बोले गए शब्दों की ऑडियो रिकॉर्डिंग बनाई जा सकती है। कंपनी ने माना कि मौजूदा संस्करण में कभी-कभी उच्चारण बदल जाता है और स्वर का उतार-चढ़ाव ज़रूरत से ज़्यादा नाटकीय हो जाता है।","category":"行业动态","source":"IT之家","aggregationSource":"IT之家","pageTitle":"Suno ने Speech वॉइस फ़ीचर लॉन्च किया है, जिसमें वॉइस और संगीत को एक ही ट्रैक पर साथ में जनरेट किया जा सकता है। - Aioga AI समाचार","description":"स्थानीय समयानुसार 1 अक्टूबर को AI संगीत निर्माण प्लेटफ़ॉर्म Suno ने Speech फ़ीचर लॉन्च करने और उसका सार्वजनिक बीटा (Beta) परीक्षण शुरू करने की घोषणा की। कंपनी के अनुसार, यह उद्योग...","url":"https://www.aioga.com/hi/news/ji0urqug3bzzbbz4vg0bhulkr/","contentTranslated":true,"translationStatus":"translated","translationRetryAt":"","translationError":"","sourceHash":"8541ac0af2332570","translatedAt":"2026-10-03T18:55:58.036Z"},"it":{"title":"Suno lancia la funzione vocale Speech, che consente di generare voce e musica insieme su un'unica traccia.","summary":"Il 1º ottobre, ora locale, la piattaforma di produzione musicale basata sull’IA Suno ha annunciato il lancio della funzione Speech e l’apertura della versione beta al pubblico (Beta). L’azienda ha dichiarato che si tratta del primo modello audio end-to-end closed source del settore in grado di generare voce e musica insieme come un’unica traccia audio coerente. La funzione è integrata in Suno: è sufficiente inserire un testo e descrivere il timbro vocale e lo stile musicale per generare un contenuto audio parlato con BGM; l’azienda ha riconosciuto che la versione attuale presenta occasionalmente problemi di deriva dell’accento e di intonazione eccessivamente drammatica.","category":"行业动态","source":"IT之家","aggregationSource":"IT之家","pageTitle":"Suno lancia la funzione vocale Speech, che consente di generare voce e musica insieme su un'unica traccia. - Aioga Notizie IA","description":"Il 1º ottobre, ora locale, la piattaforma di produzione musicale basata sull’IA Suno ha annunciato il lancio della funzione Speech e l’apertura della versione beta al pubblico (Bet...","url":"https://www.aioga.com/it/news/ji0urqug3bzzbbz4vg0bhulkr/","contentTranslated":true,"translationStatus":"translated","translationRetryAt":"","translationError":"","sourceHash":"8541ac0af2332570","translatedAt":"2026-10-03T18:55:37.578Z"},"nl":{"title":"Suno lanceert de Speech-spraakfunctie, spraak en muziek kunnen gezamenlijk op één spoor worden gegenereerd","summary":"Op lokale tijd 1 oktober kondigde het AI-muziekproductieplatform Suno de lancering van de Speech-functie aan en opende het de openbare bèta-test. Volgens de officiële verklaring is dit 's werelds eerste end-to-end gesloten audiodmodel dat spraak en muziek kan genereren als één samenhangende audiotrack. De functie is ingebouwd in Suno; door een stuk tekst in te voeren en het timbre en de muziekstijl te beschrijven, kan een spraakopname met achtergrondmuziek worden gegenereerd. Officieel wordt erkend dat de huidige versie soms accentverschuivingen en een te dramatische intonatie heeft.","category":"行业动态","source":"IT之家","aggregationSource":"IT之家","pageTitle":"Suno lanceert de Speech-spraakfunctie, spraak en muziek kunnen gezamenlijk op één spoor worden gegenereerd - Aioga AI-nieuws","description":"Op lokale tijd 1 oktober kondigde het AI-muziekproductieplatform Suno de lancering van de Speech-functie aan en opende het de openbare bèta-test. Volgens de officiële verklaring is...","url":"https://www.aioga.com/nl/news/ji0urqug3bzzbbz4vg0bhulkr/","contentTranslated":true,"translationStatus":"translated","translationRetryAt":"","translationError":"","sourceHash":"8541ac0af2332570","translatedAt":"2026-10-03T18:55:35.439Z"},"tr":{"title":"Suno, Speech ses özelliğini başlattı, ses ve müzik tek bir parça üzerinde birlikte üretilebilir","summary":"Yerel saatle 1 Ekim'de AI müzik üretim platformu Suno, Speech özelliğini kullanıma sunduğunu ve herkese açık Beta testini başlattığını duyurdu. Şirket, bunun sektörde ses ve müziği tek bir tutarlı ses parçası olarak birlikte üreten ilk uçtan uca kapalı kaynaklı ses modeli olduğunu belirtti. Suno'ya entegre edilen bu özellik, bir metin girip ses rengi ve müzik tarzını açıklayarak BGM içeren konuşma sesleri oluşturmayı mümkün kılıyor. Şirket, mevcut sürümde zaman zaman aksan kayması ve tonlamanın aşırı dramatik olması sorunlarının görüldüğünü kabul etti.","category":"行业动态","source":"IT之家","aggregationSource":"IT之家","pageTitle":"Suno, Speech ses özelliğini başlattı, ses ve müzik tek bir parça üzerinde birlikte üretilebilir - Aioga AI Haberleri","description":"Yerel saatle 1 Ekim'de AI müzik üretim platformu Suno, Speech özelliğini kullanıma sunduğunu ve herkese açık Beta testini başlattığını duyurdu. Şirket, bunun sektörde ses ve müziği...","url":"https://www.aioga.com/tr/news/ji0urqug3bzzbbz4vg0bhulkr/","contentTranslated":true,"translationStatus":"translated","translationRetryAt":"","translationError":"","sourceHash":"8541ac0af2332570","translatedAt":"2026-10-03T19:00:06.110Z"},"vi":{"title":"Suno ra mắt tính năng giọng nói Speech, cho phép tạo giọng nói và âm nhạc cùng nhau trên một track duy nhất","summary":"Ngày 1 tháng 10 theo giờ địa phương, nền tảng sản xuất âm nhạc bằng AI Suno thông báo ra mắt tính năng Speech và mở thử nghiệm công khai (Beta). Theo thông tin từ phía chính thức, đây là mô hình âm thanh mã nguồn đóng đầu cuối đầu tiên trong ngành có khả năng đồng thời tạo giọng nói và âm nhạc dưới dạng một bản nhạc liền mạch duy nhất. Tính năng này được tích hợp trong Suno; người dùng chỉ cần nhập một đoạn văn bản và mô tả chất giọng cùng phong cách âm nhạc để tạo ra âm thanh giọng nói có nhạc nền (BGM). Phía chính thức thừa nhận phiên bản hiện tại đôi khi gặp vấn đề giọng nói bị thay đổi và ngữ điệu quá kịch tính.","category":"行业动态","source":"IT之家","aggregationSource":"IT之家","pageTitle":"Suno ra mắt tính năng giọng nói Speech, cho phép tạo giọng nói và âm nhạc cùng nhau trên một track duy nhất - Tin tức AI Aioga","description":"Ngày 1 tháng 10 theo giờ địa phương, nền tảng sản xuất âm nhạc bằng AI Suno thông báo ra mắt tính năng Speech và mở thử nghiệm công khai (Beta). Theo thông tin từ phía chính thức,...","url":"https://www.aioga.com/vi/news/ji0urqug3bzzbbz4vg0bhulkr/","contentTranslated":true,"translationStatus":"translated","translationRetryAt":"","translationError":"","sourceHash":"8541ac0af2332570","translatedAt":"2026-10-03T19:00:10.387Z"},"id":{"title":"Suno meluncurkan fitur suara Speech, suara dan musik dapat dihasilkan bersama dalam satu trek","summary":"Pada 1 Oktober waktu setempat, platform produksi musik AI Suno mengumumkan peluncuran fitur Speech dan membuka pengujian publik (Beta). Menurut pihak resmi, fitur ini merupakan model audio end-to-end closed-source pertama di industri yang menghasilkan suara dan musik secara bersamaan sebagai satu trek audio yang koheren. Fitur ini terintegrasi dalam Suno; pengguna cukup memasukkan teks serta mendeskripsikan karakter suara dan gaya musik untuk menghasilkan audio suara dengan BGM. Pihak resmi mengakui bahwa versi saat ini terkadang mengalami masalah pergeseran aksen dan intonasi yang terlalu dramatis.","category":"行业动态","source":"IT之家","aggregationSource":"IT之家","pageTitle":"Suno meluncurkan fitur suara Speech, suara dan musik dapat dihasilkan bersama dalam satu trek - Berita AI Aioga","description":"Pada 1 Oktober waktu setempat, platform produksi musik AI Suno mengumumkan peluncuran fitur Speech dan membuka pengujian publik (Beta). Menurut pihak resmi, fitur ini merupakan mod...","url":"https://www.aioga.com/id/news/ji0urqug3bzzbbz4vg0bhulkr/","contentTranslated":true,"translationStatus":"translated","translationRetryAt":"","translationError":"","sourceHash":"8541ac0af2332570","translatedAt":"2026-10-03T19:00:35.423Z"},"th":{"title":"Suno เปิดตัวฟีเจอร์เสียงพูด Speech ซึ่งสามารถสร้างเสียงพูดและดนตรีร่วมกันในแทร็กเดียวได้","summary":"ในเวลาท้องถิ่นวันที่ 1 ตุลาคม แพลตฟอร์มการผลิตเพลง AI Suno ประกาศเปิดตัวฟีเจอร์ Speech และเปิดให้ทดลองใช้งานสาธารณะ (Beta) ทางการระบุว่านี่เป็นโมเดลเสียงปิดแบบครบวงจรตัวแรกในอุตสาหกรรมที่สร้างเสียงพูดและดนตรีเป็นแทร็กเดียวที่สอดคล้องกัน ฟีเจอร์นี้ฝังอยู่ใน Suno เพียงป้อนข้อความและอธิบายโทนเสียงกับสไตล์ดนตรี ก็สามารถสร้างไฟล์เสียงพูดพร้อม BGM ได้ ทางการยอมรับว่ารุ่นปัจจุบันยังมีปัญหาการเบี่ยงของสำเนียงและน้ำเสียงที่เกินจริงเป็นครั้งคราว","category":"行业动态","source":"IT之家","aggregationSource":"IT之家","pageTitle":"Suno เปิดตัวฟีเจอร์เสียงพูด Speech ซึ่งสามารถสร้างเสียงพูดและดนตรีร่วมกันในแทร็กเดียวได้ - ข่าว AI Aioga","description":"ในเวลาท้องถิ่นวันที่ 1 ตุลาคม แพลตฟอร์มการผลิตเพลง AI Suno ประกาศเปิดตัวฟีเจอร์ Speech และเปิดให้ทดลองใช้งานสาธารณะ (Beta) ทางการระบุว่านี่เป็นโมเดลเสียงปิดแบบครบวงจรตัวแรกในอุตสาห...","url":"https://www.aioga.com/th/news/ji0urqug3bzzbbz4vg0bhulkr/","contentTranslated":true,"translationStatus":"translated","translationRetryAt":"","translationError":"","sourceHash":"8541ac0af2332570","translatedAt":"2026-10-03T19:05:30.893Z"},"pl":{"title":"Suno wprowadza funkcję mowy Speech, głos i muzyka mogą być generowane wspólnie na jednej ścieżce","summary":"1 października czasu lokalnego platforma do produkcji muzyki AI Suno ogłosiła uruchomienie funkcji Speech oraz rozpoczęcie jej publicznych testów beta (Beta). Według oficjalnych informacji jest to pierwszy w branży zamknięty model audio typu end-to-end, który generuje mowę i muzykę jako jedną spójną ścieżkę audio. Funkcja jest wbudowana w Suno — wystarczy wprowadzić tekst i opisać barwę głosu oraz styl muzyczny, aby wygenerować nagranie mowy z muzyką w tle (BGM). Oficjalnie przyznano, że obecna wersja sporadycznie zmienia akcent, a jej intonacja bywa zbyt dramatyczna.","category":"行业动态","source":"IT之家","aggregationSource":"IT之家","pageTitle":"Suno wprowadza funkcję mowy Speech, głos i muzyka mogą być generowane wspólnie na jednej ścieżce - Aioga Wiadomości AI","description":"1 października czasu lokalnego platforma do produkcji muzyki AI Suno ogłosiła uruchomienie funkcji Speech oraz rozpoczęcie jej publicznych testów beta (Beta). Według oficjalnych in...","url":"https://www.aioga.com/pl/news/ji0urqug3bzzbbz4vg0bhulkr/","contentTranslated":true,"translationStatus":"translated","translationRetryAt":"","translationError":"","sourceHash":"8541ac0af2332570","translatedAt":"2026-10-03T19:05:09.537Z"}},"evidenceTier":"verified-news","reviewStatus":"automated-ingest","indexable":true,"editorialCover":""}}