Evergreen Tools
|
← Back to AI Tools

AI Dubbing Studio

Translate audio and video into 90+ languages in one pass, keeping each speaker's voice, emotion and timing while the original soundtrack stays untouched

Dubbing Studio Interface

Interactive tool will be available soon

Features

  • ✓ Translates across 90+ languages including English, Spanish, French, German, Japanese, Chinese and Arabic, selected via BCP-47 tags such as fr or es-MX in the API
  • ✓ Preserves each speaker's emotion, tone, timing and unique vocal character, so pacing and pauses follow the original performance instead of a flat read
  • ✓ Original background music and effects are retained, so there is no re-mixing when you switch languages
  • ✓ Upload a local file or paste a YouTube or TikTok link, with a web limit of 2GB and 180 minutes per file
  • ✓ Runs on the fully automatic Dubbing v2 model by default, and switches to the legacy v1 model plus Dubbing Studio when you need line-by-line editing

How to Use

  1. Open the dubbing page and upload an audio or video file, or paste a YouTube or TikTok URL
  2. Pick the source language and one or more target languages (billing is per language)
  3. Click generate and let the tool separate speakers, translate the script and synthesise the new dub
  4. Preview and download the result, or create a Dubbing Studio project to polish line by line first

FAQ

What is AI Dubbing Studio?

An online dubbing tool built on ElevenLabs Dubbing that translates audio and video across 90+ languages while preserving each speaker's emotion, timing, tone and the original background audio. Input: an audio/video file or video URL. Output: a dubbed audio or video file in the target language.

How many languages are supported?

Official documentation lists 90+ languages including English, Spanish, French, German, Japanese, Chinese and Arabic. The API takes a BCP-47 tag in source_language and target_language such as fr or es-MX; region-qualified tags must be among the dialects supported by Dubbing v2.

Will it still sound like the original speaker?

Yes. The system separates speakers, translates the text and rebuilds the recording to resemble the original vocal characteristics, aiming to recreate the same delivery in another language while the original background audio is retained, so no re-mixing is needed.

Are there file limits?

Per the official docs, Dubbing v2 on the web accepts files under both 2GB and 180 minutes. For bulk material, run the pipeline through the API instead.

What is the difference between automatic dubbing and Dubbing Studio?

New dubs use the fully automatic Dubbing v2 model, which produces no editable content. To edit translations or fine-tune lip sync, select the legacy v1 model and check the create-dubbing-project option to enter Dubbing Studio. An existing automatic dub cannot be converted into an editable project.

Can I dub into several languages at once?

Yes, select multiple target languages in the language picker, and you will be charged for each one. A good practice is to finalise edits in one target language first, then replicate them across the other languages so every version stays in sync.