Introducing Dubbing v2
ElevenLabs launched Dubbing v2, an AI dubbing model focused on preserving performance across languages.
ElevenLabs introduced Dubbing v2, a new AI dubbing model that preserves tone, pacing, delivery, and emotional intent from the original speaker. It supports more than 90 languages and uses sync-aware translation to make dubbed speech feel more natural. The product is available in ElevenCreative and ElevenProductions, while API access is coming soon.
ElevenLabs announced the launch of Dubbing v2 on its blog, positioning it as a new version of its AI dubbing model whose core goal is to solve the common AI-dubbing problem of "the translation is correct but it doesn't sound like the original person speaking." The company states that traditional AI dubbing systems rely heavily on transcripts, and while they can produce understandable translated speech, they often lose the emotion, pauses, emphasis, energy, and rhythm of human speech. Dubbing v2 instead conditions directly on the original performance, attempting to transfer the speaker's intonation, rhythm, emotional intent, and manner of expression into other languages, so that the output is closer to professional dubbing rather than flat text-to-speech.
Free shows the 3-line summary; Pro unlocks the full deep summary (~300 words) so you never have to click through.
See Pro plans →Want the original English / full article?
Read on ElevenLabs Blog →Related
Summaries are AI-generated; the original article is authoritative.