{"@context":"https://schema.org","@type":"NewsArticle","generatedAt":"2026-09-28T06:03:00.468Z","headline":"Gradium 发布 Voice Design：写一段描述文字，几秒生成全新合成语音","description":"巴黎语音 AI 公司 Gradium（从 Kyutai 研究实验室分拆）推出 Voice Design，输入 1 到 500 字符的描述即可在 3 到 5 秒内生成 1 到 5 个候选语音，无需参考音频，支持英法西葡德 5 种语言，已在 Gradium API 和 Studio 全部套餐免费开放。","url":"https://www.aioga.com/news/cmtts42qy0l51rofp2l51yxoh/","mainEntityOfPage":"https://www.aioga.com/news/cmtts42qy0l51rofp2l51yxoh/","datePublished":"2026-09-09T07:29:13.000Z","dateModified":"2026-09-09T07:29:13.000Z","inLanguage":"zh-CN","publisher":{"@type":"NewsMediaOrganization","name":"Aioga","url":"https://www.aioga.com"},"citation":["https://www.marktechpost.com/2026/09/09/gradium-launches-voice-design-write-a-prompt-get-a-brand-new-synthetic-voice-in-seconds","https://aihot.news/items/cmtts42qy0l51rofp2l51yxoh"],"canonicalUrl":"https://www.aioga.com/news/cmtts42qy0l51rofp2l51yxoh/","directAnswer":{"@type":"Answer","text":"巴黎语音 AI 公司 Gradium 推出 Voice Design。用户输入 1 至 500 字符的文字描述，可在约 3 至 5 秒生成 1 至 5 个候选合成语音，无需参考音频，支持英语、法语、西班牙语、葡萄牙语和德语。","url":"https://www.aioga.com/news/cmtts42qy0l51rofp2l51yxoh/","dateCreated":"2026-09-09T07:29:13.000Z","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":"marktechpost.com source article","url":"https://www.marktechpost.com/2026/09/09/gradium-launches-voice-design-write-a-prompt-get-a-brand-new-synthetic-voice-in-seconds","datePublished":"2026-09-09T07:29:13.000Z","provider":{"@type":"Organization","name":"marktechpost.com","url":"https://www.marktechpost.com/2026/09/09/gradium-launches-voice-design-write-a-prompt-get-a-brand-new-synthetic-voice-in-seconds"}},{"@type":"CreativeWork","name":"AIHot archive record","url":"https://aihot.news/items/cmtts42qy0l51rofp2l51yxoh","datePublished":"2026-09-09T07:29:13.000Z","provider":{"@type":"Organization","name":"AIHot","url":"https://aihot.news/items/cmtts42qy0l51rofp2l51yxoh"}}],"aggregationSource":"MarkTechPost（RSS）","originalPublisher":{"name":"marktechpost.com","url":"https://www.marktechpost.com/2026/09/09/gradium-launches-voice-design-write-a-prompt-get-a-brand-new-synthetic-voice-in-seconds"},"geoDeepAnswer":null,"article":{"id":"cmtts42qy0l51rofp2l51yxoh","slug":"cmtts42qy0l51rofp2l51yxoh","url":"https://www.aioga.com/news/cmtts42qy0l51rofp2l51yxoh/","title":"Gradium 发布 Voice Design：写一段描述文字，几秒生成全新合成语音","title_en":"","summary":"巴黎语音 AI 公司 Gradium（从 Kyutai 研究实验室分拆）推出 Voice Design，输入 1 到 500 字符的描述即可在 3 到 5 秒内生成 1 到 5 个候选语音，无需参考音频，支持英法西葡德 5 种语言，已在 Gradium API 和 Studio 全部套餐免费开放。","source":"MarkTechPost（RSS）","sourceUrl":"https://www.marktechpost.com/2026/09/09/gradium-launches-voice-design-write-a-prompt-get-a-brand-new-synthetic-voice-in-seconds","aiHotUrl":"https://aihot.news/items/cmtts42qy0l51rofp2l51yxoh","publishedAt":"2026-09-09T07:29:13.000Z","category":"行业动态","score":58,"selected":false,"articleBody":["Voice agent teams keep hitting the same wall. The catalog holds 400 voices and the brief asks for the one that is not in it: a Quebecoise receptionist for a Montreal dealership, a narrator in his sixties with lecture hall authority. Briefs outnumber any catalog, and cloning closes the gap one speaker at a time, each carrying sourcing, consent and a licence.","Gradium：https://gradium.ai/, the Paris-based voice AI company spun out of the Kyutai research lab, has shipped a different answer. Voice Design：https://gradium.ai/voice-design reads a written description and returns complete new voices in a few seconds. No reference audio, no speaker, no rights to clear.","Is it deployable? Yes, Voice Design is live in the Gradium API and in Studio：https://studio.gradium.ai/voices/design, free on every plan including the free tier, and a kept voice runs on the same streaming Text-to-Speech endpoint as any catalog voice, at the same latency and output formats.","The description is the only input the model gets. Gradium’s documentation：https://docs.gradium.ai/guides/voices/voice-design lists the attributes it responds to, and they read like a casting call: gender, age band, accent or origin, pitch, pace, energy, timbre and resonance, register and manner, and the job the voice is doing. Descriptions run 1 to 500 characters in English, French, Spanish, Portuguese or German. Gradium advises ending with the intended use, because it steers delivery and register rather than only the colour of the voice.","One request returns 1 to 5 candidates, typically ready in 3 to 5 seconds. They are variations on a single character, so a different character means a different description, not more samples.","The flow is four calls. POST /voice-generator/generate mints candidate ids with ready: false . GET /voice-generator/embeddings polls until they flip. Each candidate auditions through the ordinary TTS endpoint, using the candidate id as voice_id . POST /voices/from-embedding promotes the one you keep.","Candidates carry three restrictions converted voices do not: audition text is capped at 100 characters, they are REST only, and the TTS WebSocket and Speech-to-Speech reject them. Unconverted candidates are deleted after 30 days. Converting is free, clears the expiry, and uses one custom voice slot shared with clones. The free tier holds 5, paid plans 1,000.","Sampling is deliberately non-deterministic. Gradium team expands the description first, and that expansion varies per request, so the same prompt with a fixed seed still yields a different voice.","Gradium ran a blind pairwise listening test on accent prompts across six voice design systems reachable through public APIs and five languages. Native speakers heard two unlabelled clips and picked the closer match, or a tie. Across 7,627 comparisons, Gradium reports a 72.6% win rate against the field, 13.6 points ahead of ElevenLabs eleven_ttv_v3 at 59.0%, followed by Inworld at 44.8%, Fish Audio at 36.7% and MiniMax at 31.7%. Win rate is wins plus half of ties, so 50% is par. Gradium placed first in all five languages. The widest margins came on regional accents that most catalogs flatten: Quebecois French at 97%, Rioplatense Spanish at 86%, Bavarian German at 85%, Colombian Spanish and African Portuguese at 83%.","A model judge over the same prompt set agreed. Gemini 3.1 Pro rated single unlabelled clips from 1 to 5 and produced the same ranking: Gradium 4.06, ElevenLabs 3.86, Inworld 3.64, Fish Audio 3.51. Separately, the product page claims 83.4% prompt adherence on the English split of InstructTTSEval：https://arxiv.org/abs/2506.16381, the academic benchmark for instruction following in TTS. (Note: All of these numbers are vendor designed and vendor run.)","Need to partner with us for promoting your GitHub Repo OR Hugging Face Page OR Product Release OR Webinar etc.? Connect with us ：https://forms.gle/wbash1wF6efRj8G58","Michal Sutter is a data science professional with a Master of Science in Data Science from the University of Padova. With a solid foundation in statistical analysis, machine learning, and data engineering, Michal excels at transforming complex datasets into actionable insights.","Practitioner-first AI/ML news and analysis, read by 1M+ developers and researchers every month."],"articleImages":[{"sourceUrl":"https://www.marktechpost.com/wp-content/uploads/2025/07/a-professional-linkedin-headshot-photogr_0jcmb0R9Sv6nW5XK-zkPHw_uARV5VW1ST6osLNlunoVWg-300x300.png","alt":"","afterParagraph":10,"url":"/media/articles/cmtts42qy0l51rofp2l51yxoh/84e64b03066de40c.webp"}],"mediaStatus":"ok","articleBodyZh":["语音代理团队不断碰到同样的障碍。目录中有400个声音，而简报要求的是目录中没有的：蒙特利尔经销商的一位魁北克女接待员，一位六十多岁的叙述员，拥有讲堂般的权威感。简报的数量超过任何目录，而克隆则以每次一个说话者的方式弥合差距，每个都拥有来源、同意和许可。","Gradium：https://gradium.ai/，这家总部位于巴黎的语音AI公司由Kyutai研究实验室分拆出来，已经提供了另一种解决方案。Voice Design：https://gradium.ai/voice-design 可以读取书面描述，并在几秒钟内返回完整的新声音。无需参考音频，无需说话者，无需权利清除。","它可以部署吗？可以，Voice Design 已在 Gradium API 和 Studio：https://studio.gradium.ai/voices/design 上上线，包括免费套餐在内的每个计划都可使用，保留的声音在与目录声音相同的流式文本转语音端点运行，具有相同的延迟和输出格式。","描述是模型获得的唯一输入。Gradium 的文档：https://docs.gradium.ai/guides/voices/voice-design 列出了模型可以响应的属性，它们读起来像是选角通知：性别、年龄段、口音或出处、音高、语速、能量、音色和共鸣、声域和方式，以及声音正在执行的工作。描述长度为1到500个字符，可以使用英语、法语、西班牙语、葡萄牙语或德语。Gradium 建议以预期用途结尾，因为这会引导语音的表现和声域，而不仅仅是声音的颜色。","一次请求返回1到5个候选，通常在3到5秒内准备就绪。它们是单一角色的变体，因此不同的角色意味着不同的描述，而不是更多的样本。","流程包含四次调用。POST /voice-generator/generate 会生成候选 id 并设置 ready: false。GET /voice-generator/embeddings 会轮询直到状态改变。每个候选通过普通 TTS 端点进行试听，使用候选 id 作为 voice_id。POST /voices/from-embedding 会提升你选择保留的那个声音。","候选人有三项限制，而已转换的语音没有：试听文本限制为100个字符，他们仅能通过REST使用，且TTS WebSocket和语音对语音功能不支持他们。未转换的候选人在30天后会被删除。转换是免费的，可以清除过期时间，并使用一个与克隆共享的自定义语音槽。免费套餐可存放5个，自付套餐可存放1,000个。","采样是故意非确定性的。Gradium团队会首先扩展描述，这个扩展在每次请求中都不同，因此相同的提示即使使用固定种子仍会生成不同的语音。","Gradium对六种通过公共API可访问的语音设计系统和五种语言的口音提示进行了盲对比听力测试。母语者听两个未标记的音频片段，并选择更接近的匹配，或者判定为平局。在7,627次对比中，Gradium报告胜率为72.6%，比ElevenLabs的eleven_ttv_v3的59.0%高出13.6个百分点，随后是Inworld的44.8%、Fish Audio的36.7%和MiniMax的31.7%。胜率计算为胜利加半数平局，因此50%为基准。Gradium在五种语言中均位居第一。最显著的优势出现在多数目录处理过的区域口音：魁北克法语97%，里约拉普拉塔西班牙语86%，巴伐利亚德语85%，哥伦比亚西班牙语及非洲葡萄牙语83%。","基于相同提示集的模型评审结果一致。Gemini 3.1 Pro对每个未标记音频片段进行1到5的评分，并得出相同排序：Gradium 4.06，ElevenLabs 3.86，Inworld 3.64，Fish Audio 3.51。另据产品页面称，InstructTTSEval英文分集的提示遵循率为83.4%：https://arxiv.org/abs/2506.16381，这是TTS中遵循指令的学术基准。（注：所有这些数据均由供应商设计并运行。）","需要与我们合作推广您的GitHub仓库或Hugging Face页面或产品发布或网络研讨会等？请联系我们： https://forms.gle/wbash1wF6efRj8G58","Michal Sutter是一名数据科学专业人士，拥有帕多瓦大学数据科学硕士学位。凭借统计分析、机器学习和数据工程的扎实基础，Michal擅长将复杂的数据集转化为可操作的洞见。","以实践者为先的AI/ML新闻与分析，每月有超过100万开发者和研究人员阅读。"],"translationStatus":"translated","bodyOrigin":"source-page","editorial":{"summary":"巴黎语音 AI 公司 Gradium 推出 Voice Design。用户输入 1 至 500 字符的文字描述，可在约 3 至 5 秒生成 1 至 5 个候选合成语音，无需参考音频，支持英语、法语、西班牙语、葡萄牙语和德语。","background":"Gradium 从 Kyutai 研究实验室分拆，Voice Design 已在 Gradium API 和 Studio 的全部套餐开放，包括免费层。候选语音可通过普通文本转语音接口试听，选定后可转换为自定义语音；未转换候选保留 30 天。","viewpoint":"Aioga 判断：Voice Design 将语音选择从既有目录匹配扩展到文字描述生成，重点不只是音色，还包括年龄段、口音、音高、语速、能量、共鸣、表达方式和使用场景等维度。","implications":"可能影响：需要快速测试定制语音的团队可能获得更灵活的筛选方式，但候选语音存在 REST-only、试听文本不超过 100 字符等限制，也不支持 TTS WebSocket 和 Speech-to-Speech，因此不足以视为所有场景的通用替代方案。","nextStep":"后续观察：应关注文字描述对目标音色、口音和表达方式的稳定呈现，也需要留意候选语音转换后的使用边界、30 天保留期限，以及自定义语音槽位限制对实际部署的影响。","evidenceRefs":["title","summary","articleBody","source"],"status":"published","aiGenerated":true,"autoApproved":true,"generatedBy":"aioga-editorial:gpt-5.6-sol","reviewedBy":"aioga-editorial-review:gpt-5.6-sol","generatedAt":"2026-09-09T07:47:51.444Z","sourceHash":"adaa68a880680ef1","review":{"approved":true,"groundedness":94,"clarity":92,"duplicationRisk":10,"blockingIssues":[],"notes":["“未转换候选保留 30 天”可更精确表述为“未转换候选将在 30 天后删除”。","“候选语音转换后的使用边界”表述较宽泛，来源明确提到的是转换会清除过期限制，并占用一个与克隆语音共享的自定义语音槽位。","“稳定呈现”属于合理的后续观察方向；来源还明确指出生成具有非确定性，同一描述即使固定种子也可能生成不同语音。"]},"validation":{"passed":true,"mode":"ai-auto","revisions":0,"checks":["schema","length","source-attribution","editorial-labels","inference-boundary","low-source-overlap","no-html","independent-ai-review"]}},"tags":["行业动态","MarkTechPost（RSS）"],"translations":{"zh-CN":{"title":"Gradium 发布 Voice Design：写一段描述文字，几秒生成全新合成语音","summary":"巴黎语音 AI 公司 Gradium（从 Kyutai 研究实验室分拆）推出 Voice Design，输入 1 到 500 字符的描述即可在 3 到 5 秒内生成 1 到 5 个候选语音，无需参考音频，支持英法西葡德 5 种语言，已在 Gradium API 和 Studio 全部套餐免费开放。","category":"行业动态","source":"marktechpost.com","aggregationSource":"MarkTechPost（RSS）","pageTitle":"Gradium 发布 Voice Design：写一段描述文字，几秒生成全新合成语音 - Aioga AI资讯","description":"巴黎语音 AI 公司 Gradium（从 Kyutai 研究实验室分拆）推出 Voice Design，输入 1 到 500 字符的描述即可在 3 到 5 秒内生成 1 到 5 个候选语音，无需参考音频，支持英法西葡德 5 种语言，已在 Gradium API 和 Studio 全部套餐免费开放。","url":"https://www.aioga.com/news/cmtts42qy0l51rofp2l51yxoh/","articleBody":["语音代理团队不断碰到同样的障碍。目录中有400个声音，而简报要求的是目录中没有的：蒙特利尔经销商的一位魁北克女接待员，一位六十多岁的叙述员，拥有讲堂般的权威感。简报的数量超过任何目录，而克隆则以每次一个说话者的方式弥合差距，每个都拥有来源、同意和许可。","Gradium：https://gradium.ai/，这家总部位于巴黎的语音AI公司由Kyutai研究实验室分拆出来，已经提供了另一种解决方案。Voice Design：https://gradium.ai/voice-design 可以读取书面描述，并在几秒钟内返回完整的新声音。无需参考音频，无需说话者，无需权利清除。","它可以部署吗？可以，Voice Design 已在 Gradium API 和 Studio：https://studio.gradium.ai/voices/design 上上线，包括免费套餐在内的每个计划都可使用，保留的声音在与目录声音相同的流式文本转语音端点运行，具有相同的延迟和输出格式。","描述是模型获得的唯一输入。Gradium 的文档：https://docs.gradium.ai/guides/voices/voice-design 列出了模型可以响应的属性，它们读起来像是选角通知：性别、年龄段、口音或出处、音高、语速、能量、音色和共鸣、声域和方式，以及声音正在执行的工作。描述长度为1到500个字符，可以使用英语、法语、西班牙语、葡萄牙语或德语。Gradium 建议以预期用途结尾，因为这会引导语音的表现和声域，而不仅仅是声音的颜色。","一次请求返回1到5个候选，通常在3到5秒内准备就绪。它们是单一角色的变体，因此不同的角色意味着不同的描述，而不是更多的样本。","流程包含四次调用。POST /voice-generator/generate 会生成候选 id 并设置 ready: false。GET /voice-generator/embeddings 会轮询直到状态改变。每个候选通过普通 TTS 端点进行试听，使用候选 id 作为 voice_id。POST /voices/from-embedding 会提升你选择保留的那个声音。","候选人有三项限制，而已转换的语音没有：试听文本限制为100个字符，他们仅能通过REST使用，且TTS WebSocket和语音对语音功能不支持他们。未转换的候选人在30天后会被删除。转换是免费的，可以清除过期时间，并使用一个与克隆共享的自定义语音槽。免费套餐可存放5个，自付套餐可存放1,000个。","采样是故意非确定性的。Gradium团队会首先扩展描述，这个扩展在每次请求中都不同，因此相同的提示即使使用固定种子仍会生成不同的语音。","Gradium对六种通过公共API可访问的语音设计系统和五种语言的口音提示进行了盲对比听力测试。母语者听两个未标记的音频片段，并选择更接近的匹配，或者判定为平局。在7,627次对比中，Gradium报告胜率为72.6%，比ElevenLabs的eleven_ttv_v3的59.0%高出13.6个百分点，随后是Inworld的44.8%、Fish Audio的36.7%和MiniMax的31.7%。胜率计算为胜利加半数平局，因此50%为基准。Gradium在五种语言中均位居第一。最显著的优势出现在多数目录处理过的区域口音：魁北克法语97%，里约拉普拉塔西班牙语86%，巴伐利亚德语85%，哥伦比亚西班牙语及非洲葡萄牙语83%。","基于相同提示集的模型评审结果一致。Gemini 3.1 Pro对每个未标记音频片段进行1到5的评分，并得出相同排序：Gradium 4.06，ElevenLabs 3.86，Inworld 3.64，Fish Audio 3.51。另据产品页面称，InstructTTSEval英文分集的提示遵循率为83.4%：https://arxiv.org/abs/2506.16381，这是TTS中遵循指令的学术基准。（注：所有这些数据均由供应商设计并运行。）","需要与我们合作推广您的GitHub仓库或Hugging Face页面或产品发布或网络研讨会等？请联系我们： https://forms.gle/wbash1wF6efRj8G58","Michal Sutter是一名数据科学专业人士，拥有帕多瓦大学数据科学硕士学位。凭借统计分析、机器学习和数据工程的扎实基础，Michal擅长将复杂的数据集转化为可操作的洞见。","以实践者为先的AI/ML新闻与分析，每月有超过100万开发者和研究人员阅读。"]},"en":{"title":"Gradium launches Voice Design: write a descriptive text and generate a brand-new synthetic voice in seconds","summary":"Paris-based voice AI company Gradium (spun off from Kyutai Research Lab) has launched Voice Design. By typing a description of 1 to 500 characters, it can generate 1 to 5 candidate voices in 3 to 5 seconds, without the need to reference audio. It supports five languages: English, French, Spanish, Portuguese, and German. It is now available for free in all Gradium API and Studio packages.","category":"Industry","source":"MarkTechPost（RSS）","aggregationSource":"MarkTechPost（RSS）","pageTitle":"Gradium launches Voice Design: write a descriptive text and generate a brand-new synthetic voice in seconds - Aioga AI News","description":"Paris-based voice AI company Gradium (spun off from Kyutai Research Lab) has launched Voice Design. By typing a description of 1 to 500 characters, it can generate 1 to 5 candidate...","url":"https://www.aioga.com/en/news/cmtts42qy0l51rofp2l51yxoh/","contentTranslated":true,"sourceHash":"465beae8b91352f9","translatedAt":"2026-09-09T07:41:20.384Z"},"ja":{"title":"GradiumがVoice Designを発表:説明文を書き、数秒で新しい合成音声を生成する","summary":"パリに拠点を置く音声AI企業Gradium(Kyutai研究所から分社)がVoice Designを立ち上げました。1文字から500文字の説明を入力することで、音声を参照せずに3〜5秒で1〜5の候補声を生成できます。英語、フランス語、スペイン語、ポルトガル語、ドイツ語の5言語に対応しています。現在、すべてのGradium APIおよびStudioパッケージで無料で利用可能です。","category":"業界動向","source":"MarkTechPost（RSS）","aggregationSource":"MarkTechPost（RSS）","pageTitle":"GradiumがVoice Designを発表:説明文を書き、数秒で新しい合成音声を生成する - Aioga AIニュース","description":"パリに拠点を置く音声AI企業Gradium(Kyutai研究所から分社)がVoice Designを立ち上げました。1文字から500文字の説明を入力することで、音声を参照せずに3〜5秒で1〜5の候補声を生成できます。英語、フランス語、スペイン語、ポルトガル語、ドイツ語の5言語に対応しています。現在、すべてのGradium APIおよびStudioパッケージで...","url":"https://www.aioga.com/ja/news/cmtts42qy0l51rofp2l51yxoh/","contentTranslated":true,"sourceHash":"465beae8b91352f9","translatedAt":"2026-09-09T07:41:21.213Z"},"ko":{"title":"그라디움, Voice Design을 출시: 설명 텍스트를 작성하고 몇 초 만에 새로운 합성 음성을 생성할 수 있습니다","summary":"파리에 본사를 둔 음성 AI 회사인 Gradium(큐타이 연구소에서 분사)이 Voice Design을 출시했습니다. 1에서 500자 사이의 설명을 입력하면 오디오를 참조하지 않고도 3초에서 5초 만에 1개에서 5개의 후보 음성을 생성할 수 있습니다. 영어, 프랑스어, 스페인어, 포르투갈어, 독일어 등 5개 언어를 지원합니다. 현재 모든 Gradium API 및 Studio 패키지에서 무료로 이용할 수 있습니다.","category":"업계 동향","source":"MarkTechPost（RSS）","aggregationSource":"MarkTechPost（RSS）","pageTitle":"그라디움, Voice Design을 출시: 설명 텍스트를 작성하고 몇 초 만에 새로운 합성 음성을 생성할 수 있습니다 - Aioga AI 뉴스","description":"파리에 본사를 둔 음성 AI 회사인 Gradium(큐타이 연구소에서 분사)이 Voice Design을 출시했습니다. 1에서 500자 사이의 설명을 입력하면 오디오를 참조하지 않고도 3초에서 5초 만에 1개에서 5개의 후보 음성을 생성할 수 있습니다. 영어, 프랑스어, 스페인어, 포르투갈어, 독일어 등 5개 언어를 지원합니...","url":"https://www.aioga.com/ko/news/cmtts42qy0l51rofp2l51yxoh/","contentTranslated":true,"sourceHash":"465beae8b91352f9","translatedAt":"2026-09-09T07:41:30.335Z"},"es":{"title":"Gradium lanza Voice Design: escribe un texto descriptivo y genera una voz sintética completamente nueva en segundos","summary":"La empresa parisina de IA por voz Gradium (derivada del Laboratorio de Investigación de Kyutai) ha lanzado Voice Design. Al escribir una descripción de 1 a 500 caracteres, puede generar de 1 a 5 voces candidatas en 3 a 5 segundos, sin necesidad de consultar audio. Soporta cinco idiomas: inglés, francés, español, portugués y alemán. Ahora está disponible gratuitamente en todos los paquetes API y Studio de Gradium.","category":"Industria","source":"MarkTechPost（RSS）","aggregationSource":"MarkTechPost（RSS）","pageTitle":"Gradium lanza Voice Design: escribe un texto descriptivo y genera una voz sintética completamente nueva en segundos - Aioga Noticias de IA","description":"La empresa parisina de IA por voz Gradium (derivada del Laboratorio de Investigación de Kyutai) ha lanzado Voice Design. Al escribir una descripción de 1 a 500 caracteres, puede ge...","url":"https://www.aioga.com/es/news/cmtts42qy0l51rofp2l51yxoh/","contentTranslated":true,"sourceHash":"465beae8b91352f9","translatedAt":"2026-09-09T07:41:30.350Z"},"fr":{"title":"Gradium lance Voice Design : écrire un texte descriptif et générer une toute nouvelle voix synthétique en quelques secondes","summary":"La société parisienne d’IA vocale Gradium (issue du laboratoire de recherche de Kyutai) a lancé Voice Design. En tapant une description de 1 à 500 caractères, elle peut générer de 1 à 5 voix candidates en 3 à 5 secondes, sans avoir besoin de référence audio. Elle prend en charge cinq langues : anglais, français, espagnol, portugais et allemand. Elle est désormais disponible gratuitement dans tous les packages API et Studio de Gradium.","category":"Industrie","source":"MarkTechPost（RSS）","aggregationSource":"MarkTechPost（RSS）","pageTitle":"Gradium lance Voice Design : écrire un texte descriptif et générer une toute nouvelle voix synthétique en quelques secondes - Aioga Actualités IA","description":"La société parisienne d’IA vocale Gradium (issue du laboratoire de recherche de Kyutai) a lancé Voice Design. En tapant une description de 1 à 500 caractères, elle peut générer de...","url":"https://www.aioga.com/fr/news/cmtts42qy0l51rofp2l51yxoh/","contentTranslated":true,"sourceHash":"465beae8b91352f9","translatedAt":"2026-09-09T07:41:39.797Z"},"de":{"title":"Gradium bringt Voice Design auf den Markt: Schreibe einen beschreibenden Text und generiere innerhalb von Sekunden eine brandneue synthetische Stimme","summary":"Das in Paris ansässige Voice-AI-Unternehmen Gradium (ausgegliedert vom Kyutai Research Lab) hat Voice Design gestartet. Durch das Eingeben einer Beschreibung von 1 bis 500 Zeichen kann es in 3 bis 5 Sekunden 1 bis 5 Kandidatenstimmen erzeugen, ohne Audio referenzieren zu müssen. Es unterstützt fünf Sprachen: Englisch, Französisch, Spanisch, Portugiesisch und Deutsch. Es ist jetzt kostenlos in allen Gradium API- und Studio-Paketen verfügbar.","category":"行业动态","source":"MarkTechPost（RSS）","aggregationSource":"MarkTechPost（RSS）","pageTitle":"Gradium bringt Voice Design auf den Markt: Schreibe einen beschreibenden Text und generiere innerhalb von Sekunden eine brandneue synthetische Stimme - Aioga KI-News","description":"Das in Paris ansässige Voice-AI-Unternehmen Gradium (ausgegliedert vom Kyutai Research Lab) hat Voice Design gestartet. Durch das Eingeben einer Beschreibung von 1 bis 500 Zeichen...","url":"https://www.aioga.com/de/news/cmtts42qy0l51rofp2l51yxoh/","contentTranslated":true,"sourceHash":"465beae8b91352f9","translatedAt":"2026-09-09T07:41:39.334Z"},"pt-BR":{"title":"Gradium lança o Voice Design: escreva um texto descritivo e gere uma nova voz sintética em segundos","summary":"A empresa parisiense de IA de voz Gradium (derivada do Kyutai Research Lab) lançou o Voice Design. Ao digitar uma descrição de 1 a 500 caracteres, é possível gerar de 1 a 5 vozes candidatas em 3 a 5 segundos, sem necessidade de consultar áudio. Suporta cinco idiomas: inglês, francês, espanhol, português e alemão. Agora está disponível gratuitamente em todos os pacotes API e Studio da Gradium.","category":"行业动态","source":"MarkTechPost（RSS）","aggregationSource":"MarkTechPost（RSS）","pageTitle":"Gradium lança o Voice Design: escreva um texto descritivo e gere uma nova voz sintética em segundos - Aioga Notícias de IA","description":"A empresa parisiense de IA de voz Gradium (derivada do Kyutai Research Lab) lançou o Voice Design. Ao digitar uma descrição de 1 a 500 caracteres, é possível gerar de 1 a 5 vozes c...","url":"https://www.aioga.com/pt-BR/news/cmtts42qy0l51rofp2l51yxoh/","contentTranslated":true,"sourceHash":"465beae8b91352f9","translatedAt":"2026-09-09T07:41:48.761Z"},"ru":{"title":"Gradium запускает Voice Design: напишите описательный текст и создайте совершенно новый синтетический голос за считанные секунды","summary":"Парижская компания Gradium (выделенная из Kyutai Research Lab) запустила Voice Design. Введя описание от 1 до 500 символов, она может генерировать от 1 до 5 кандидатов голосов за 3–5 секунд без необходимости ссылаться на аудио. Поддерживает пять языков: английский, французский, испанский, португальский и немецкий. Сейчас он доступен бесплатно во всех пакетах Gradium API и Studio.","category":"行业动态","source":"MarkTechPost（RSS）","aggregationSource":"MarkTechPost（RSS）","pageTitle":"Gradium запускает Voice Design: напишите описательный текст и создайте совершенно новый синтетический голос за считанные секунды - Aioga Новости ИИ","description":"Парижская компания Gradium (выделенная из Kyutai Research Lab) запустила Voice Design. Введя описание от 1 до 500 символов, она может генерировать от 1 до 5 кандидатов голосов за 3...","url":"https://www.aioga.com/ru/news/cmtts42qy0l51rofp2l51yxoh/","contentTranslated":true,"sourceHash":"465beae8b91352f9","translatedAt":"2026-09-09T07:41:49.069Z"},"ar":{"title":"تطلق Gradium مشروع تصميم الصوت: اكتب نصا وصفيا وتولد صوتا اصطناعيا جديدا في ثوان","summary":"أطلقت شركة Gradium للذكاء الاصطناعي الصوتي ومقرها باريس (المنبثقة من مختبر أبحاث كيوتاي) مشروع تصميم الصوت. من خلال كتابة وصف من 1 إلى 500 حرف، يمكنه توليد 1 إلى 5 أصوات مرشحة خلال 3 إلى 5 ثوان، دون الحاجة إلى الرجوع إلى الصوت. يدعم خمس لغات: الإنجليزية، الفرنسية، الإسبانية، البرتغالية، والألمانية. وهو الآن متاح مجانا في جميع حزم Gradium API وStudio.","category":"行业动态","source":"MarkTechPost（RSS）","aggregationSource":"MarkTechPost（RSS）","pageTitle":"تطلق Gradium مشروع تصميم الصوت: اكتب نصا وصفيا وتولد صوتا اصطناعيا جديدا في ثوان - Aioga أخبار الذكاء الاصطناعي","description":"أطلقت شركة Gradium للذكاء الاصطناعي الصوتي ومقرها باريس (المنبثقة من مختبر أبحاث كيوتاي) مشروع تصميم الصوت. من خلال كتابة وصف من 1 إلى 500 حرف، يمكنه توليد 1 إلى 5 أصوات مرشحة خلال...","url":"https://www.aioga.com/ar/news/cmtts42qy0l51rofp2l51yxoh/","contentTranslated":true,"sourceHash":"465beae8b91352f9","translatedAt":"2026-09-09T07:41:58.362Z"},"hi":{"title":"ग्रैडियम ने वॉयस डिज़ाइन लॉन्च किया: एक वर्णनात्मक पाठ लिखें और सेकंड में एक नई सिंथेटिक आवाज उत्पन्न करें","summary":"पेरिस स्थित वॉयस AI कंपनी ग्रैडियम (क्यूताई रिसर्च लैब से अलग) ने वॉयस डिज़ाइन लॉन्च किया है। 1 से 500 वर्णों का विवरण टाइप करके, यह ऑडियो को संदर्भित करने की आवश्यकता के बिना, 3 से 5 सेकंड में 1 से 5 उम्मीदवार की आवाज़ें उत्पन्न कर सकता है। यह पांच भाषाओं का समर्थन करता है: अंग्रेजी, फ्रेंच, स्पेनिश, पुर्तगाली और जर्मन। यह अब सभी ग्रैडियम एपीआई और स्टूडियो पैकेजों में मुफ्त में उपलब्ध है।","category":"行业动态","source":"MarkTechPost（RSS）","aggregationSource":"MarkTechPost（RSS）","pageTitle":"ग्रैडियम ने वॉयस डिज़ाइन लॉन्च किया: एक वर्णनात्मक पाठ लिखें और सेकंड में एक नई सिंथेटिक आवाज उत्पन्न करें - Aioga AI समाचार","description":"पेरिस स्थित वॉयस AI कंपनी ग्रैडियम (क्यूताई रिसर्च लैब से अलग) ने वॉयस डिज़ाइन लॉन्च किया है। 1 से 500 वर्णों का विवरण टाइप करके, यह ऑडियो को संदर्भित करने की आवश्यकता के बिना, 3 स...","url":"https://www.aioga.com/hi/news/cmtts42qy0l51rofp2l51yxoh/","contentTranslated":true,"sourceHash":"465beae8b91352f9","translatedAt":"2026-09-09T07:41:58.300Z"},"it":{"title":"Gradium lancia Voice Design: scrivi un testo descrittivo e genera una nuova voce sintetica in pochi secondi","summary":"La società parigina di voice AI Gradium (scorporata dal Kyutai Research Lab) ha lanciato Voice Design. Digitando una descrizione da 1 a 500 caratteri, può generare da 1 a 5 voci candidate in 3-5 secondi, senza bisogno di fare riferimento all'audio. Supporta cinque lingue: inglese, francese, spagnolo, portoghese e tedesco. Ora è disponibile gratuitamente in tutti i pacchetti API e Studio di Gradium.","category":"行业动态","source":"MarkTechPost（RSS）","aggregationSource":"MarkTechPost（RSS）","pageTitle":"Gradium lancia Voice Design: scrivi un testo descrittivo e genera una nuova voce sintetica in pochi secondi - Aioga Notizie IA","description":"La società parigina di voice AI Gradium (scorporata dal Kyutai Research Lab) ha lanciato Voice Design. Digitando una descrizione da 1 a 500 caratteri, può generare da 1 a 5 voci ca...","url":"https://www.aioga.com/it/news/cmtts42qy0l51rofp2l51yxoh/","contentTranslated":true,"sourceHash":"465beae8b91352f9","translatedAt":"2026-09-09T07:42:07.224Z"},"nl":{"title":"Gradium lanceert Voice Design: schrijf een beschrijvende tekst en genereer binnen enkele seconden een gloednieuwe synthetische stem","summary":"Het in Parijs gevestigde voice AI-bedrijf Gradium (afgesplitst van Kyutai Research Lab) heeft Voice Design gelanceerd. Door een beschrijving van 1 tot 500 tekens te typen, kan het 1 tot 5 kandidaatstemmen genereren in 3 tot 5 seconden, zonder dat audio hoeft te worden geraadpleegd. Het ondersteunt vijf talen: Engels, Frans, Spaans, Portugees en Duits. Het is nu gratis beschikbaar in alle Gradium API- en Studio-pakketten.","category":"行业动态","source":"MarkTechPost（RSS）","aggregationSource":"MarkTechPost（RSS）","pageTitle":"Gradium lanceert Voice Design: schrijf een beschrijvende tekst en genereer binnen enkele seconden een gloednieuwe synthetische stem - Aioga AI-nieuws","description":"Het in Parijs gevestigde voice AI-bedrijf Gradium (afgesplitst van Kyutai Research Lab) heeft Voice Design gelanceerd. Door een beschrijving van 1 tot 500 tekens te typen, kan het...","url":"https://www.aioga.com/nl/news/cmtts42qy0l51rofp2l51yxoh/","contentTranslated":true,"sourceHash":"465beae8b91352f9","translatedAt":"2026-09-09T07:42:07.575Z"},"tr":{"title":"Gradium, Voice Design'ı başlattı: tanımlayıcı bir metin yaz ve saniyeler içinde yepyeni bir sentetik ses oluştur","summary":"Paris merkezli ses yapay zeka şirketi Gradium (Kyutai Araştırma Laboratuvarı'ndan ayrılmış) Voice Design'ı başlattı. 1 ila 500 karakterlik bir açıklama yazarak, 3 ila 5 saniyede 1 ila 5 aday ses üretebiliyor ve ses referansına gerek kalmadan. Beş dili destekliyor: İngilizce, Fransızca, İspanyolca, Portekizce ve Almanca. Artık tüm Gradium API ve Studio paketlerinde ücretsiz olarak mevcut.","category":"行业动态","source":"MarkTechPost（RSS）","aggregationSource":"MarkTechPost（RSS）","pageTitle":"Gradium, Voice Design'ı başlattı: tanımlayıcı bir metin yaz ve saniyeler içinde yepyeni bir sentetik ses oluştur - Aioga AI Haberleri","description":"Paris merkezli ses yapay zeka şirketi Gradium (Kyutai Araştırma Laboratuvarı'ndan ayrılmış) Voice Design'ı başlattı. 1 ila 500 karakterlik bir açıklama yazarak, 3 ila 5 saniyede 1...","url":"https://www.aioga.com/tr/news/cmtts42qy0l51rofp2l51yxoh/","contentTranslated":true,"sourceHash":"465beae8b91352f9","translatedAt":"2026-09-09T07:42:16.716Z"},"vi":{"title":"Gradium ra mắt Voice Design: viết một văn bản mô tả và tạo ra một giọng tổng hợp hoàn toàn mới chỉ trong vài giây","summary":"Công ty AI giọng nói Gradium có trụ sở tại Paris (tách ra từ Phòng thí nghiệm Nghiên cứu Kyutai) đã ra mắt Voice Design. Bằng cách gõ mô tả từ 1 đến 500 ký tự, nó có thể tạo từ 1 đến 5 giọng ứng viên trong 3 đến 5 giây mà không cần tham chiếu âm thanh. Nó hỗ trợ năm ngôn ngữ: tiếng Anh, tiếng Pháp, tiếng Tây Ban Nha, tiếng Bồ Đào Nha và tiếng Đức. Hiện đã có sẵn miễn phí trong tất cả các gói API và Studio của Gradium.","category":"行业动态","source":"MarkTechPost（RSS）","aggregationSource":"MarkTechPost（RSS）","pageTitle":"Gradium ra mắt Voice Design: viết một văn bản mô tả và tạo ra một giọng tổng hợp hoàn toàn mới chỉ trong vài giây - Tin tức AI Aioga","description":"Công ty AI giọng nói Gradium có trụ sở tại Paris (tách ra từ Phòng thí nghiệm Nghiên cứu Kyutai) đã ra mắt Voice Design. Bằng cách gõ mô tả từ 1 đến 500 ký tự, nó có thể tạo từ 1 đ...","url":"https://www.aioga.com/vi/news/cmtts42qy0l51rofp2l51yxoh/","contentTranslated":true,"sourceHash":"465beae8b91352f9","translatedAt":"2026-09-09T07:42:16.800Z"},"id":{"title":"Gradium meluncurkan Desain Suara: tulis teks deskriptif dan hasilkan suara sintetis baru dalam hitungan detik","summary":"Perusahaan AI suara yang berbasis di Paris, Gradium (yang dipisahkan dari Kyutai Research Lab) telah meluncurkan Voice Design. Dengan mengetik deskripsi 1 hingga 500 karakter, Voice Design dapat menghasilkan 1 hingga 5 kandidat suara dalam 3 hingga 5 detik, tanpa perlu merujuk audio. Mendukung lima bahasa: Inggris, Prancis, Spanyol, Portugis, dan Jerman. Sekarang tersedia gratis di semua paket API dan Studio Gradium.","category":"行业动态","source":"MarkTechPost（RSS）","aggregationSource":"MarkTechPost（RSS）","pageTitle":"Gradium meluncurkan Desain Suara: tulis teks deskriptif dan hasilkan suara sintetis baru dalam hitungan detik - Berita AI Aioga","description":"Perusahaan AI suara yang berbasis di Paris, Gradium (yang dipisahkan dari Kyutai Research Lab) telah meluncurkan Voice Design. Dengan mengetik deskripsi 1 hingga 500 karakter, Voic...","url":"https://www.aioga.com/id/news/cmtts42qy0l51rofp2l51yxoh/","contentTranslated":true,"sourceHash":"465beae8b91352f9","translatedAt":"2026-09-09T07:42:25.807Z"},"th":{"title":"Gradium เปิดตัว Voice Design: เขียนข้อความบรรยายและสร้างเสียงสังเคราะห์ใหม่ในเวลาไม่กี่วินาที","summary":"บริษัท Voice AI จากปารีส Gradium (แยกตัวออกมาจาก Kyutai Research Lab) ได้เปิดตัว Voice Design โดยการพิมพ์คําอธิบายตั้งแต่ 1 ถึง 500 ตัวอักษร สามารถสร้างเสียงผู้สมัคร 1 ถึง 5 เสียงได้ภายใน 3 ถึง 5 วินาที โดยไม่ต้องอ้างอิงเสียง รองรับ 5 ภาษา ได้แก่ อังกฤษ ฝรั่งเศส สเปน โปรตุเกส และเยอรมัน ปัจจุบันสามารถใช้งานได้ฟรีในทุกแพ็กเกจ Gradium API และ Studio","category":"行业动态","source":"MarkTechPost（RSS）","aggregationSource":"MarkTechPost（RSS）","pageTitle":"Gradium เปิดตัว Voice Design: เขียนข้อความบรรยายและสร้างเสียงสังเคราะห์ใหม่ในเวลาไม่กี่วินาที - ข่าว AI Aioga","description":"บริษัท Voice AI จากปารีส Gradium (แยกตัวออกมาจาก Kyutai Research Lab) ได้เปิดตัว Voice Design โดยการพิมพ์คําอธิบายตั้งแต่ 1 ถึง 500 ตัวอักษร สามารถสร้างเสียงผู้สมัคร 1 ถึง 5 เสียงไ...","url":"https://www.aioga.com/th/news/cmtts42qy0l51rofp2l51yxoh/","contentTranslated":true,"sourceHash":"465beae8b91352f9","translatedAt":"2026-09-09T07:42:26.114Z"},"pl":{"title":"Gradium wprowadza projekt Voice Design: napisz opisowy tekst i wygeneruj zupełnie nowy syntetyczny głos w kilka sekund","summary":"Paryska firma zajmująca się sztuczną inteligencją głosową Gradium (wyodrębniona z Kyutai Research Lab) uruchomiła projekt Voice Design. Wpisując opis od 1 do 500 znaków, może wygenerować od 1 do 5 głosów kandydatów w 3 do 5 sekund, bez potrzeby odwoływania się do dźwięku. Obsługuje pięć języków: angielski, francuski, hiszpański, portugalski i niemiecki. Obecnie jest dostępny bezpłatnie we wszystkich pakietach API Gradium i Studio.","category":"行业动态","source":"MarkTechPost（RSS）","aggregationSource":"MarkTechPost（RSS）","pageTitle":"Gradium wprowadza projekt Voice Design: napisz opisowy tekst i wygeneruj zupełnie nowy syntetyczny głos w kilka sekund - Aioga Wiadomości AI","description":"Paryska firma zajmująca się sztuczną inteligencją głosową Gradium (wyodrębniona z Kyutai Research Lab) uruchomiła projekt Voice Design. Wpisując opis od 1 do 500 znaków, może wygen...","url":"https://www.aioga.com/pl/news/cmtts42qy0l51rofp2l51yxoh/","contentTranslated":true,"sourceHash":"465beae8b91352f9","translatedAt":"2026-09-09T07:42:35.156Z"}},"evidenceTier":"verified-news","reviewStatus":"automated-ingest","indexable":true,"editorialCover":""}}