Dub your YouTube videos into other languages with AI
Voixie turns the speech in a YouTube video into another language. It transcribes the original, translates it line by line and generates a new voice track timed to the picture. Paste a YouTube link of a video you own or have permission to use, or upload the file. You get a dubbed MP4, a separate audio track and subtitle files in both languages.
How to dub a YouTube video
- 1.
Paste the link or upload
Paste a youtube.com or youtu.be link, or upload the video. The spoken language is detected automatically (100+ source languages); you choose the target language. The longest video per upload depends on the plan: 10 minutes on Free, 15 on Starter, 30 on Pro, 45 on Pro+ and 150 on Business.
- 2.
Review the translation (optional)
Choose to review in the Studio before any voice is generated. Fix names and terms, add a glossary of words that must stay as they are, change a speaker's voice and listen to single lines.
- 3.
Generate and export
Voixie generates the voice, fits each line to the original timing and mixes it into the video. Optionally keep the original music and sound effects (+3 credits/min). Download the MP4, the audio track and SRT subtitles.
What you get for each video
- A dubbed MP4, with or without the original background sound.
- An audio-only track in the new language, for platforms that accept extra audio tracks.
- SRT subtitles in the original language and in the target language.
- Up to 10 speakers per video, each with their own voice.
- Optional lip sync for on-camera speakers, as a separate step.
Languages
Target languages include English (US and UK), Spanish (Spain and Latin America), Portuguese (Brazil and Portugal), French, German, Italian, Hindi, Arabic, Turkish, Indonesian, Vietnamese, Thai, Japanese, Korean and Chinese (Simplified and Traditional): more than 50 languages and regional variants in total.
Pricing
Dubbing costs 5 credits per minute of video with Native Accent (7 with Voice Match), billed in started 15-second blocks. Keeping the original music and sound effects adds 3 credits per minute. On Starter that is about $0.11 per minute, or $0.18 with the background. Downloading the dubbed audio or video requires a paid plan; subtitle and text files can be downloaded on Free.
| Plan | Price / month | Credits / month | Dubbing (voice only) | With original music & effects |
|---|---|---|---|---|
| Free | $0 | 50 at sign-up | 10 min | First dub without surcharge |
| Starter | $7.99 | 350 | 70 min | 43 min |
| Pro | $19.99 | 1000 | 200 min | 125 min |
| Pro+ | $39.99 | 2200 | 440 min | 275 min |
| Business | $69.99 | 4000 | 800 min | 500 min |
Tips for YouTube creators
- Start with a short video to hear the voices before you dub a full series.
- Clear speech with one person talking at a time gives the cleanest result.
- Upload the translated SRT to YouTube as subtitles, even if you also publish dubbed audio.
- Only dub videos you own or have the rights to translate.
Frequently asked questions
Can I dub a YouTube video by pasting the link?
Yes. Paste a youtube.com or youtu.be link on the dubbing page and Voixie downloads the video for processing. Use it only for videos you own or have permission to translate.
How much does it cost to dub a YouTube video?
5 credits per minute (7 with Voice Match), billed in started 15-second blocks, plus 3 credits per minute if you keep the original music and effects. A 10-minute video costs 50 credits (80 with background). New accounts get 50 free credits.
Can I add the dubbed audio to my YouTube video as another language?
Voixie gives you an audio-only track in the new language. Whether you can add it as an extra audio track depends on YouTube's multi-language audio feature being available for your channel; otherwise publish the dubbed MP4 as its own video.
Will the dubbed voice sound like the original speaker?
There are two voice modes. Native Accent, the default, aims for a natural accent in the target language. Voice Match stays closer to the original speaker's voice but can carry their accent. You can also pick a library voice per speaker.