What this looks like in mydubly




Each speaker's own voice
There is no voice to choose. mydubly works out who speaks when, takes a short, clean sample of each person from your file — music and background noise removed — and speaks their lines in a copy of their voice, in any of 19 languages (all supported languages except Czech and Vietnamese, which get subtitles and translated transcripts).
- Voice
- Each person copied from their own speech in your file
- Pronunciation
- Natural for the target language
- Several speakers
- Up to 8 people, each in their own voice
- Too little clean speech
- The copied voice of a similar-sounding person in the file, or a stock voice matching the speaker
Only upload voices you have the right to use. The voice sample is deleted with the rest of the job's files. Translating a video in your own voice explains how the copy is made, what carries over into the new language and how to record for a better result.
Timed to your video
Translations are often longer than the original — Spanish, French and German usually run longer than English. Lines that belong to one sentence are joined first, so each sentence is translated and voiced whole. It is then placed where the original was spoken and sped up by at most 1.15× when it needs to fit, with the pitch kept natural. Very dense speech can still sound brisk, so slower, clearer originals dub best. Sentence-level dubbing explains the timing in detail.
What dubbing works best for
- Spoken content: explainers, tutorials, lectures, training, product demos, interviews and conversations.
- Long videos where reading subtitles would be tiring.
- Audiences who prefer dubbed content or can't read subtitles comfortably.
For heavy crosstalk, or when viewers would rather hear the original voices, subtitles are a good choice. Not sure? Read subtitles vs dubbing.
A 12-minute explainer dubbed into Japanese costs 1,440 credits ($1.44), and the run also includes Japanese subtitles and both transcripts.
Fix the dub before you publish
When the dub finishes, it opens in the dub editor. The translated script sits next to what was originally said, and a Review tab points at lines that are empty, look untranslated or will be rushed to fit. Retype a word, ask for another take or a calmer reading, nudge a line's timing, lower the music or set a loudness target, then re-process once. Only reworded lines are voiced again, at the dubbing rate for those seconds with a 60-credit minimum, so fixing a name in a 30-minute video costs cents, not a new dub. Level, timing, background and loudness changes are free.
How it works
- Drop in a video. Your browser reads it and pulls out only the audio — the video file never leaves your device.
- The audio is processed in 30-second chunks: speech is transcribed and the spoken language is detected automatically.
- Each segment is translated into your chosen language.
- The different people speaking are told apart (up to 8), and each person's lines are spoken in a copy of their own voice, taken from a short clean sample of their speech. Each line is fitted to the original timing — sped up by at most 1.15× with natural pitch.
- AI vocal separation removes the original speech, and the translated voice is mixed over the remaining music and effects, which dip automatically while the new voice speaks.
- Your browser combines the original picture with the new audio and saves an MP4.
- The dub editor opens on the finished dub. Fix words, move a line's timing, change a line's level, the background, the cleanup of leftover original speech or the loudness, and style subtitles, then re-process once: only changed lines are voiced again (free for timing, levels, background, leftover-speech cleanup, ducking, loudness and subtitles; re-voiced lines cost 120 credits per minute of those lines, minimum 60 credits per re-process).
- Download the results. A dub's audio, script and voice files stay on our servers for 120 minutes after it finishes or after you last use the editor, so you can fine-tune it, and are then deleted; the editor's "Delete files" button removes them at once.
What you get
- Translated video
- MP4 with your original picture and the translated voice over your original music and effects (MKV when the original video codec can't go in an MP4)
- Translated audio
- M4A with the same mix: translated voice over your original music and effects
- Transcript
- Plain text (.txt) of what was said
- Timestamped transcript
- Every line prefixed with its time, e.g. [12:04]
- Subtitles
- SRT and VTT, in the language you select
Pricing
- Transcript and subtitles
- 5 credits per minute (0.5¢), minimum 25 credits per file
- YouTube link transcript
- 15 credits per minute (1.5¢), minimum 75 credits per link
- Translated voice (includes everything above)
- 120 credits per minute (12¢), minimum 2 minutes per file
- Text to audio
- 120 credits per minute (12¢), minimum 2 minutes per file
- Corrections in the dub editor
- free for timing, levels, background, leftover-speech cleanup, ducking, loudness and subtitles; re-voiced lines cost 120 credits per minute of those lines, minimum 60 credits per re-process
- Credits
- $1 buys 1,000 credits; each top-up lasts 30 days
- Free credits
- 240 credits when you sign in with Google
Good to know
- Each person is dubbed in a copy of their own voice (up to 8 people per file), with natural pronunciation for the new language. Telling people apart is automatic, so crosstalk, very short interjections or two very similar voices can end up in the wrong voice, and overlapping speech overlaps in the dub by at most about two seconds. Someone with too little clean speech to copy gets the copied voice of a similar-sounding person in the file, or otherwise a stock voice matching their voice (female or male). There is no lip-sync.
- Music and sound effects are kept by AI vocal separation, which isn't perfect: in dense mixes faint traces of the original voice can remain, and sung lyrics are removed along with the speech.
- The dub editor corrects the dub mydubly made: it doesn't import your own SRT or script, and a dub can be re-processed up to 40 times while its files are kept.
- No speaker labels — transcripts don't say who is speaking.
- File uploads stay file-based: no Instagram or TikTok links, and no live audio. For a YouTube link transcript only, use the YouTube transcript tool — and only for videos you have the right to transcribe.
- Subtitles come as SRT/VTT files; to burn them into the picture, use the free subtitle editor.
Sponsored · mydubly
AI video dubbing deal
Dub any video for just 12¢ a minute
Was 240 credits/min — now only 120. Cloned voices, timed to your picture, at half the list price.
When dubbing earns its cost, and when to skip it
Dubbing pays off when the audience listens instead of reads: viewers on phones while doing something else, people who read the target language slowly, long training sessions where a full hour of subtitles is tiring, and younger audiences. At 120 credits per minute it costs fifty times as much as subtitles, so it's worth asking whether the audience would really miss the voice.
Skip it, or test it on one video first, when the speaker's own voice is the point (a personality-led channel), when several people talk at once, when music carries the video, or when the picture is full of text that will stay untranslated anyway. In those cases translated subtitles from the subtitle generator usually serve better.
If you're unsure, trim a representative two-minute section, dub it for 100 credits (10¢) and show it to a few people from the target audience before committing a whole series.
Recording with a dub in mind
When you control the source, a few habits make the translated voice easier to follow. Speak in complete, moderately short sentences and leave a breath between them: each translated line is placed where the original was spoken, so pauses give a longer translation somewhere to go. Say product names clearly and the same way every time. Avoid jokes that depend on wordplay, and don't rely on what's in the picture to finish a sentence ("click here, then this one"). Keep background music low during speech: the dub keeps your music and effects, but a loud bed makes both recognition and the separation of voice from background harder. Producing videos that translate cleanly goes further, and what text expansion does to dubbed audio explains why some languages need more room than others.
Where the dubbed voices come from
- Voice source
- A short, clean sample of each person, up to about 10 seconds, taken automatically from your file with music and background noise removed
- What carries over
- Timbre, pitch and how each person sounds, plus the pace and energy of each original line; pronunciation follows the target language, so the original accent stays behind
- Several speakers
- Up to 8 people are told apart automatically, and each is dubbed in a copy of their own voice; crosstalk, very short interjections or similar-sounding voices can put a line in the wrong voice
- Too little clean speech
- Someone with under about 3 seconds of clean speech gets the copied voice of the person they sound most like, if they sound alike, or else a stock voice matching theirs (female or male)
There is no voice picker: every dub uses the copies, at the same 120 credits per minute. Clean, close-mic speech copies best, so the recording habits above improve the voice as well as the translation. Only dub voices you have the right to use, and for a well-known host consider telling viewers that the translation uses an AI copy of their voice. More on how audiences respond to synthetic voices in picking the right AI voice.
Reviewing a dub before it goes live
- Play the preview at 1.5× for a first pass, listening for dropped lines and obvious mistranslations.
- Slow to 0.75× for passages with names, numbers and product terms.
- Read the subtitles. In dub mode they follow what the voice actually says, including lines shortened to fit the timing, so the SRT is a fast written copy of the spoken script.
- Listen to the ends of long sentences, where a fast original leaves the translated line the least room.
- Check how names and acronyms are pronounced; when the voice says a name wrong explains where those errors start.
- Compare original and translated text side by side on the result screen for anything that reads oddly.
A fuller pre-release list is in the AI dub quality checklist.
What the dubbed file contains, and how to finish it
The translated MP4 holds your original picture, the translated voices and your original background: the original speech is removed by AI vocal separation, and the music, room tone and sound effects that remain are mixed under the new voices and lowered while they speak. The audio is mono. Separation isn't perfect: in dense or loud mixes faint traces of the original voice can remain and the background can sound slightly thinner, and sung vocals are removed along with the speech. For most videos that's fine as delivered. If you have your edit project and want stereo music or your own levels, export a dialogue-only version and dub that; the translated audio (M4A) then comes back as essentially the voices alone, and you mix it with your clean music stem in an editor. Adding the stem to the M4A of a normal dub would double the music. Finishing an AI dub in your editor walks through it in common editors.
The same M4A is what you'd add as an extra language track on platforms that support several audio tracks per video; YouTube's multi-language audio explains how that works where it's available. If the download is an MKV because your video codec doesn't fit an MP4, check that your editor or platform accepts it before you build a timeline around it.
Costs at realistic lengths
Billed at the 2-minute minimum: 100 credits (10¢). If you have several clips from one recording, dubbing the full recording once and cutting the clips afterwards avoids paying the minimum on each.
3,000 credits ($3.00), including translated subtitles and the original-language transcript.
4,500 credits ($4.50). Long recordings are where reviewing the subtitle file instead of re-watching the whole dub saves the most time.
Each target language is its own run at the same rate.
Going further
The AI dubbing guide covers a first run step by step, and the online course use case shows dubbing across a whole curriculum. Language pages explain what changes in the target language, for example French, Korean or Hindi.
Dub video into…
See also
Learn more
Articles that go deeper on the technology and workflows behind this tool.
- Translating interviews, panels and podcasts with more than one speaker
- Background Music in Translated Videos: What Stays and How to Perfect It
- When translations grow or shrink: what text expansion does to subtitles and dubbed audio
- Text to Speech, Explained: From Robot Voices to Neural TTS
- Inside a Synthetic Voice: The Neural TTS Pipeline Step by Step
- Chatterbox TTS: Resemble AI's Open-Source Voice Model, Explained
- AI or Human Dubbing? How to Decide for Each Project
- Dubbing, Voice-Over or Narration? The Differences That Matter
- AI Lip Sync Explained: Re-Rendering Mouths to Match New Audio
- Choosing an AI Voice When the Dub Copies the Speaker
- Cloned Voices or Preset Voices? How to Decide for Dubbed Video
- What Separates a Convincing AI Voice from a Robotic One
- Why AI Dubbing Is Harder Than It Looks
- Using Synthetic Voices Without Deceiving Anyone
- Why Synthetic Voices Sometimes Stress the Wrong Word
- How One TTS Model Speaks Many Languages
- AI Dubbing Quality: How Good It Is, and How to Check a Dub Before It Goes Live
- Sentence-Level Dubbing: Why AI Dubs Translate and Voice One Sentence at a Time
- How YouTube's Multi-Language Audio Tracks Work, and How to Make One
- One Voice or Many? Choosing a Dubbing Approach
- Keeping a Translated Voice in Time With the Original Speaker
- Translating Children's Videos Into Other Languages
- How to Build One Video File with Original and Translated Audio
- Finishing an AI Dub in Premiere, Resolve, Final Cut or a Free Editor
- Can Text to Speech Be Your Pronunciation Model? Uses, Limits and Shadowing
- Selling in the Buyer's Language: Translating Sales Videos
- Translating Gaming Videos: Commentary, Game Audio and Gamer Slang
- What to Do With Sponsor Reads When You Translate or Dub a Video
- How to Translate a Video Essay Without Losing Its Argument
- Loudness Normalization: LUFS, True Peak and Consistent Speech Levels
- When the Synthetic Voice Says a Name Wrong: Finding Where It Broke
- A Short History of Dubbing and Subtitles, From Title Cards to AI
- How to Improve Dialogue Clarity in Video So Everyone Can Follow the Speech
- The M&E Track: Why Every Project Should Export Music and Effects Without Dialogue
- Does Your Music License Cover the Translated Version of a Video?
- Hearing Two Voices at Once: Fixing Doubled Audio in a Video
- How to Record a Voiceover in Another Language From a Translated Script
- What Is Dubbing? How Dialogue Gets Replaced in Another Language
- What Is Voice Cloning? How AI Copies a Voice, and Where It's Used
Sponsored · mydubly
240 free credits + 50% off
Try free, then buy minutes at half price
New accounts get 240 credits (enough for a 2-minute dub). When you top up, you keep these sale rates.
Frequently asked questions
Does AI dubbing keep my voice?
Yes. Each person's lines are spoken in a copy of their own voice, taken from a short clean sample of their speech in your file. Someone with too little clean speech gets the copied voice of a similar-sounding person in the file, or otherwise a stock voice matching their voice.
Is there lip-sync / AI lip sync?
No. The dub works like a traditional voice-over; lips on camera won't match the new language. Timing still follows each sentence of the original.
Is AI dubbing good enough to publish?
For explainers, tutorials, training and product demos with clear speech, yes for many channels — especially after a pass in the dub editor. Dense crosstalk, heavy music or flagship ads still benefit from a human review.
What is automatic / auto video dubbing?
Automatic dubbing means the tool transcribes the speech, translates it, and speaks a new track without you casting voice actors. mydubly does that for recorded videos (not live streams), with each speaker copied from their own voice.
Can I dub audio files too?
Yes — use the audio dubbing tool for podcasts and recordings.
Can I correct a word the AI got wrong?
Yes. Retype the line in the dub editor and re-process: only that line is voiced again, in the same copied voice, at 120 credits per minute of re-voiced speech with a 60-credit minimum.
Can different speakers get different voices?
Yes. Each person, up to 8 per file, is dubbed automatically in a copy of their own voice, so interviews and panels keep their speakers distinct. Heavy crosstalk is where voices can get mixed up; for that, or when viewers prefer the original voices, translated subtitles remain a good fit.
Will the original voice be audible underneath the dub?
No. The original speech is separated out and removed; your music and sound effects stay underneath, lowered while the translated voices speak. In dense or loud mixes faint traces of the original voices can remain.
Can I choose a different voice for the dub?
No. Each person is dubbed in a copy of their own voice; someone with too little clean speech to copy gets the closest-sounding copied voice or a matching stock voice. Running the file again is billed again, so dub a short clip first to hear the copied voices in your target language before you start a long video.
Sponsored · mydubly
Transcripts & subtitles deal