{"rewrite":{"id":"r_5014cccbd466494fa4e8b5ac","clusterId":"c_91b116eb72091ad10c125738","slug":"elevenlabs-releases-dubbing-v2-ai-model-for-multilingual-audio","model":"deepseek-v4-flash","headline":"ElevenLabs Releases Dubbing v2 AI Model for Multilingual Audio","summary":"ElevenLabs has released Dubbing v2, an AI dubbing model that preserves the original speaker's emotion, tone, tempo, and speaking style across over 90 languages. The model generates audio directly from the speaker's performance rather than from a text script, aiming to produce natural-sounding dubbing that syncs with the original content.","whyItMatters":"Dubbing v2 shifts AI dubbing from text-script-based translation to performance-based generation, which could reduce the cost and complexity of professional multilingual localization for creators and companies.","webCardHtml":"\u003cp\u003eElevenLabs, the AI company founded by former Google engineers, has launched Dubbing v2, a model that reproduces the original speaker's emotions, tone, tempo, and speaking style in over 90 languages. Unlike conventional AI dubbing systems that relied on text scripts and often lost natural speech patterns, Dubbing v2 generates audio directly from the speaker's performance, capturing intonation and rhythm. The company says this approach solves long-standing problems in AI dubbing, making translated audio feel as if the person is actually speaking. A demonstration video shows YouTuber MrBeast's speech translated into multiple languages with closely matched voice atmosphere and tempo. Dubbing v2 is available on ElevenCreative and ElevenProductions, with API access planned later. One user noted the price: $22 per month for 9 minutes of dubbing.\u003c/p\u003e","blueskyPost":"ElevenLabs Dubbing v2 generates audio directly from the speaker's performance, not a text script. That bypasses the translation-to-speech pipeline most competitors use.","twitterPost":"ElevenLabs Dubbing v2 generates audio from the speaker's performance, not a text script. That skips the translation-to-speech pipeline.","threadsPost":"ElevenLabs Dubbing v2 generates audio directly from the speaker's performance, not a text script. Most dubbing AI goes through a translation-to-speech pipeline. This skips that step, which could change how natural the output sounds.","newsletterBlurb":"ElevenLabs released Dubbing v2, an AI model that reproduces the original speaker's emotions, tone, tempo, and speaking style in over 90 languages. Unlike conventional text-script-based dubbing, it generates audio directly from the speaker's performance. The model is available on ElevenCreative and ElevenProductions, with API access planned.","attributionJson":"[{\"source\":\"GIGAZINE\",\"url\":\"https://gigazine.net/news/20260601-elevenlabs-dubbing-v2/\",\"title\":\"ElevenLabs Releases 'Dubbing v2,' an Audio AI That Syncs with Content While Preserving Original Speaker's Emotion, Tone, and Pace in Over 90 Languages\"}]","lintFlagsJson":null,"lintHits":0,"costUsd":0,"inputTokens":3868,"outputTokens":599,"status":"published","repairAttempts":0,"nextRepairAt":null,"factsAttemptedAt":1780290911,"createdAt":"2026-06-01T05:04:29.000Z","publishedAt":"2026-06-01T05:08:10.000Z","updatedAt":"2026-06-01T05:08:10.000Z"},"cluster":{"id":"c_91b116eb72091ad10c125738","canonicalTitle":"90以上の言語でオリジナルの話者の感情・トーン・ペースを維持しながらコンテンツと同期する音声AI「Dubbing v2」をElevenLabsがリリース","representativeArticleId":"a_2293864f49b4a0df74c1c76f","sourceCount":1,"writtenSourceCount":1,"writeAttempts":0,"isSolo":true,"entitiesJson":"{\"anime_titles\":[],\"manga_titles\":[],\"work_titles\":[],\"studios\":[],\"people\":[],\"type\":\"news\",\"domain\":\"other\",\"is_roundup\":false}","contentType":"news","status":"published","firstSeenAt":"2026-06-01T03:27:00.000Z","lastSeenAt":"2026-06-01T03:27:00.000Z","updatedAt":"2026-06-01T05:08:10.000Z"},"attribution":[{"source":"GIGAZINE","url":"https://gigazine.net/news/20260601-elevenlabs-dubbing-v2/","title":"90以上の言語でオリジナルの話者の感情・トーン・ペースを維持しながらコンテンツと同期する音声AI「Dubbing v2」をElevenLabsがリリース"}],"entities":{"anime_titles":[],"manga_titles":[],"work_titles":[],"studios":[],"people":[],"type":"news","domain":"other","is_roundup":false},"keyFacts":["ElevenLabs launched Dubbing v2, an AI model that reproduces the original speaker's emotions, tone, tempo, and speaking style in over 90 languages.","Dubbing v2 generates audio directly from the speaker's performance rather than from a text script, capturing intonation and rhythm.","A demonstration video shows YouTuber MrBeast's speech translated into multiple languages with closely matched voice atmosphere and tempo.","Dubbing v2 is available on ElevenCreative and ElevenProductions, with API access planned later.","One user noted the price: $22 per month for 9 minutes of dubbing."]}