Free AI dubbing · Open source · No account to try · Free sign-in to download · Nothing uploaded with the free voice
Your video, in 17 languages, in your own voice.
Free in this browser: on a computer or an Android phone, dub with a stock voice, with no app, no key and nothing uploaded, for videos up to 5 minutes. An English video can be dubbed free into 8 other languages (Portuguese too, in Chrome on a computer); a video in 13 other languages, into English. The first run downloads up to about 750 MB, once. To keep the speaker’s own voice, use OmniVoice in the OpenDub app on your computer (non-commercial use) or your own Higgs Audio or ElevenLabs key.
OpenDub (opendub.app) is AI dubbing for your own videos: free in the browser on a computer or an Android phone, a desktop app for Mac and Windows, and open source at gitlab.com/open-dubapp/OpenDub. Upload a video in one language and choose another. OpenDub separates the speech from the music, transcribes it, translates each sentence to fit its moment, and speaks it back in a clone of the original voice — then burns in subtitles in the new language.
- Open source. Every step is plain code you can read, run and replace.
- Local, except the voice models. In AI dubbing, separation, speech detection, timing, mixing and rendering run on your device. Your video never leaves it — only speech clips and text go to the voice model you choose.
- Powerful. AI dubbing in your own cloned voice in 17 languages, each line timed to your original speech and carrying your tone — surprise, enthusiasm, calm.
- 17 languages. English, 简体中文, 繁體中文, 日本語, 한국어, Español, Français, Deutsch, Português, Italiano, Русский, हिन्दी, Bahasa Indonesia, Bahasa Melayu, Tiếng Việt, ไทย, العربية. The language of the original video is detected automatically.
Other settings Cloned voice · tone matched per line
Speaking speed is not a setting: it is chosen per line so each one starts and ends with the speaker.
Replace the voice keeps the music and effects and swaps the speech. Voice-over leaves the original faintly underneath.
Dubbing
—
What it is doing
Done
—
Tap a block to play from there.
Lines
Each line as it was heard and as it was dubbed; tap a time to hear it. Here the lines can be read but not changed: to change a translation or its timing and dub just that line again, use the OpenDub app on a computer. A note such as “slowed to 0.84× to fit” is set automatically to fit the speaker's time; it is not a control.
Dub your own video
Or run OpenDub's AI dubbing on your own machine.
The AI dubbing card at the top dubs videos up to five minutes right in this tab. The app on your computer has no length limit, removes the voice faster, and lets you edit, re-tone or drag any line and re-dub it in about ten seconds.
Higgs STT, translation and a cloned voice with tone tags. The best quality, and what made the dub above.
Boson AI's usage prices
OmniVoice includes Higgs Materials. Built with Higgs Materials licensed from Boson AI USA, Inc., Copyright Boson AI USA, Inc., All Rights Reserved and Meta Llama 3 licensed under the Meta Llama 3 Community License, Copyright Meta Platforms, Inc., All Rights Reserved. Boson Higgs Audio 2 Community License · Meta Llama 3 Community License
Free AI dubbing with Whisper, a local language model and OmniVoice. Nothing leaves your computer and nothing is charged.
Works today: choose OmniVoice in the card at the top, with the OpenDub app running on your computer.
The Windows installer is not code-signed yet, so Windows SmartScreen may call the publisher unknown — open More info, then Run anyway. With Smart App Control on, Windows can block it outright until it is signed. Either way you can check the file is the real one before you run it: OpenDub 1.0.5 for Windows is a828082ed6522d4555502693ec304d52dda6d2f72d857f95e619cdebbe864245 (SHA-256), and the full checksums ship beside the installer — SHA256SUMS.txt.
Third-party licences in the downloads, including the GPL parts of the current Mac and Windows installers and how to get their source: Licences.
Also a browser extension for Chrome, Edge and Firefox: it dubs videos up to five minutes in the browser, with local OmniVoice or your own Higgs Audio key.
Open it and press Install. Python, ffmpeg and everything the app runs are already inside — no terminal, nothing else to install, and no key to find. The Mac build is for Apple Silicon.
Or install it with one linecurl -fsSL https://opendub.app/install.sh | bashmacOS and Linux. About 3.6 GB on a Mac and 6.5 GB on Linux, once; 3.3 GB of it is the voice model, which downloads on the first dub. It installs the free voice and starts it, so the AI dubbing card at the top can use it. Your videos never leave your computer.
All of it is open source, AGPL-3.0-or-later: gitlab.com/open-dubapp/OpenDub.
How AI dubbing works here
AI dubbing with four models, each doing the one thing it is best at.
- 01
Separate
Demucs splits the speech from the music and effects, so the soundtrack survives the AI dubbing and every model below hears a clean voice.
- 02
Listen
Silero VAD finds the speech. Higgs STT writes down the words in whatever language they are spoken; a local Whisper supplies only the timing, aligned word by word.
- 03
Translate to fit
The Higgs chat model translates whole sentences, each sized to how long the speaker took to say it — so the new voice starts and stops with the speaker.
- 04
Speak, then check
Higgs TTS clones the voice from a clean sentence of the original and delivers each line in the tone it was said in, read from the words and from how loud and fast the speaker was. Each line is transcribed back and regenerated if it drifted, then re-said or gently stretched to match the original length.
For every step of the AI dubbing in order, and what runs on your device, read How OpenDub dubs a video in your own voice.
For what you choose and what you get back when you translate a video, read How to translate a video into another language.
Cost and install
What is free, what is paid, and what you install.
- Free
OpenDub itself
Open source AI dubbing under AGPL-3.0-or-later, free to use. No account to try; downloading a dub takes a free sign-in. Subtitle files, the browser extension and the desktop apps need none.
- Free
Stock voice in the browser
Free AI dubbing in this browser on a computer or an Android phone: no key, nothing to install and no account to try (downloading the dub takes a free sign-in), for videos up to five minutes. It is a stock voice, not a clone of the speaker: an English video into 8 other languages (Portuguese too, in Chrome on a computer), a video in 13 other languages into English.
- Free
OmniVoice
The free cloned voice for AI dubbing. It runs in the OpenDub app on your computer, at about 15–35 seconds a line on a laptop CPU. Its model weights are licensed for non-commercial use only.
- Your own API key
Higgs Audio or ElevenLabs
Use your own API key and pay Boson AI or ElevenLabs directly. This AI dubbing route clones the speaker's voice and works in the card at the top of the page, with nothing to install.
- Paid
OpenDub credits
No key needed. Coming soon.
In the browser, the AI dubbing card at the top dubs videos up to five minutes. The app on your computer has no length limit: the Mac (Apple Silicon) and Windows downloads carry Python, ffmpeg and everything else inside, and macOS and Linux also have a one-line install.
Where the cloned voice comes from, and what each voice model does: Voice cloning for multilingual video dubbing.
Questions
What people ask about AI dubbing with OpenDub.
What is AI dubbing?
AI dubbing replaces the speech in a video with speech in another language, made by AI models. OpenDub's AI dubbing transcribes the original, translates each sentence to fit its moment and speaks it in a clone of the original voice, keeping the music underneath.
Is OpenDub free?
The AI dubbing software is free and open source (AGPL-3.0-or-later). In the browser on a computer or an Android phone it dubs for free in a stock voice, with no API key, for videos up to five minutes. The OmniVoice voice, which clones the speaker, is free and runs on your own computer, for non-commercial use. With Higgs Audio or ElevenLabs you use your own API key and pay that provider directly. Paid OpenDub credits are coming soon.
Do I need an account?
Not to try. Dubbing, the preview and the demo need no account. Downloading the dubbed video or its audio takes a free sign-in, and the download then continues on its own. The subtitle files and the voice sample, the browser extension and the desktop apps need none.
Do I have to install anything?
Not with your own Higgs Audio or ElevenLabs key: the AI dubbing runs in your browser tab, for videos up to five minutes. On a computer or an Android phone it is free with nothing to install, in a stock voice rather than a clone of the speaker: an English video into 8 other languages (Portuguese too, in Chrome on a computer), a video in 13 other languages into English. On iPhone that free voice is still a preview, at opendub.app/?phonevoice=1. Cloning the voice for free, with OmniVoice, needs the OpenDub app on your computer. The app has no length limit.
Can AI dubbing turn a video into Hindi for free?
Yes, between English and Hindi. In the browser on a computer or an Android phone, the free AI dubbing turns an English video into Hindi, or a Hindi video into English, in a stock voice with no key, for videos up to five minutes. Choose हिन्दी under Dub into. The free voice is not a clone of the speaker, and the original voice is turned down under it. Translate video to Hindi has the steps.
Does the AI dubbing work on iPhone?
Not by default yet. On iPhone, AI dubbing with the free voice is still a preview: to try it, open opendub.app/?phonevoice=1. Without that, the page on an iPhone offers to send the link to your computer, where the free AI dubbing runs in the browser and the OpenDub app runs on Mac and Windows.
Is my video uploaded?
No. During AI dubbing the video stays on your device. Only speech clips and text go to the voice model you choose.
Does it keep the background music?
Yes. Replace the voice keeps the music and effects and swaps only the speech. Voice-over leaves the original faintly underneath.
Which languages can it dub into?
AI dubbing into 17 languages: English, 简体中文, 繁體中文, 日本語, 한국어, Español, Français, Deutsch, Português, Italiano, Русский, हिन्दी, Bahasa Indonesia, Bahasa Melayu, Tiếng Việt, ไทย, العربية. The language of the original video is detected automatically.
Which video formats and lengths work?
MP4, MOV or WebM. Up to five minutes in the browser, and no length limit in the app on your computer.
What files do I get?
The dubbed MP4, the dub audio as WAV, subtitles in both languages as SRT, and the clip the voice was cloned from.
Can I run it from the command line?
Yes. From a clone of the repository, .venv/bin/python -m opendub.pipeline video.mp4 --to ja dubs a file with no page at all, once ./run.sh has set it up. This route uses a Higgs Audio key.
Does it change the lips in the picture?
No. OpenDub's AI dubbing replaces the voice and leaves the picture as it is. Each dubbed line is timed to last as long as the speaker took to say it. If you choose burned-in subtitles, they are added to the picture.
Where are the official site, the source code and support?
The official site is opendub.app and the source code is at gitlab.com/open-dubapp/OpenDub. OpenDub at opendub.app is AI dubbing in the browser and in a desktop app for Mac and Windows; other projects that use the name OpenDub are separate from it. For help, write to hello@opendub.app.