Ask an AI about this
Studio lets you dub over a video: bring in a clip, let Tranzio read its subtitles off the picture, and record your voice on top of them, line by line.
Studio: matching video & dubbing
Studio lets you dub over a video: bring in a clip, let Tranzio read its subtitles off the picture, and record your voice on top of them, line by line.
Studio answers a different question than the rest of the Workspace. Audio Lab dubs the voices inside a game; Studio dubs a video: a trailer you want to release alongside your translation, a cutscene, a tutorial, a walkthrough. You bring in a clip, and Studio lays out a video's subtitles and audio on a timeline so you can record your voice over it, line by line.

What Studio is, and who can use it
Game audio arrives as thousands of separate lines with no picture and no context. Studio plays a video of the game and lays its lines on a timeline, so you dub each one against the scene. A plain audio editor knows nothing about which line you are recording; a live translation overlay can only put text on the screen. Studio links every take to the game's own line, so the next build puts your voice where the original was.
Studio comes with the Pro and Studio plans, which start with a free trial you can cancel any time. On the Free plan the sound editor on the Audio page still records one line at a time.
Your videos
Once a game has a video, Studio opens on its library: three big cards to a row, newest first, filtered to YouTube or your own files with the buttons above them. Each card says where that video stands and leads with the one thing worth doing next, so nothing hides behind a hover:
- Read to 3:44:10 means a read was stopped part way. Continue reading carries on from there, and the green line under the picture shows how far it got.
- Subtitles read with a count of lines means it is ready. Open and dub goes straight to the editor.
- Not read yet leads with Read subtitles, with Open beside it for working without them.
A Part chip means the video is focused on one stretch. The ⋯ menu holds the rest: read the subtitles again, open the video on YouTube, or delete it.
Your videos
3Hollowtide Full Walkthrough, No Commentary
Read to 3:44:10 · 1,204 linesAdded 2 h agoHollowtide, the quiet ending
Subtitles read · 98 lines Part 05:40:02 → 05:54:24Added yesterdayLantern Bay intro capture
Not read yetAdded 3 days ago
Bringing a video in
Pick a video
Paste a YouTube link into the bar above your videos and press Add video, or press Choose file or drop a file anywhere on the page. Not found one yet? While the bar is empty it offers Find “game gameplay”, which opens that search on YouTube. A game with no videos yet shows the same two ways as two cards instead. Either way Tranzio only asks the host for the name and the length. The subtitles come from the picture, so a link and a file behave the same from here on.
Paste a YouTube linkAdd videoVideo readyHollowtide Full Walkthrough
6:02:26 · from YouTube
Which part has the lines you want?2:10:28From 1:05:12to 3:15:40Read the subtitles off the pictureabout 1.4 hoursStart readingPasting a link and adding it. What comes back is the video ready pane: the part to read and whether to read it. Drop a video here
or click to browseMP4, MOV, and WebM work bestThe drop area for your own clips. MP4, MOV, and WebM all work. Choose the part and whether to read it
Which part has the lines you want? shows the whole video as a strip. Drag its two handles to the stretch you care about, or type the times as hours, minutes and seconds (
1:05:12, or5:12for minutes). The arrow keys move a handle a second at a time and a minute with Shift, and Whole video puts it back. Focusing hides nothing permanently; widen it later and the rest comes back. Then decide whether to read the subtitles off the picture. Leave it on and Tranzio watches the part you chose and turns every line it finds into a timed entry waiting to be translated and voiced. The switch says how long that takes before you agree to it: a few minutes for a scene, hours for a whole playthrough read over a link. You can stop and carry on later, or turn it off and read later from the card.Open in the editor
The editor opens with everything lined up: the video on top, the lines that were read and your recordings below it on a shared timeline.
Tranzio never keeps the video. It plays from YouTube where it lives. Reading a link's subtitles does stream it through, but nothing is written to disk except small crops of the subtitle band, and each of those is deleted the moment it has been read. What is left at the end is the text. Import the same link twice and you get two separate sources, so you can focus one on the intro and the other on the ending.
Reads shared by others
Reading a long video takes hours, so nobody should have to read the same one twice. When you read a YouTube video’s subtitles, what the read found is shared for this game: only which game line is spoken when. Not the words, which stay on your computer like the rest of the game’s text, not pictures, and not your name. The next person who adds that video gets those lines in seconds, with the words filled in from their own copy of the game.
Everything works inside the part you chose. Pick 0:30 to 1:00 of a six-hour video, and the pane says how much of that half hour others already read. Two choices follow. Get the lines and read the rest (or just Get the lines when nothing is left) downloads them and then reads only the minutes nobody has read, and those minutes are shared back, so the read grows with every person who uses it. Read it all myself reads the whole part here; parts that were already shared are not stored twice.
Under your own videos, Shared for this game lists videos others read that you have not added. Add to my videos shows how much of the video is read and adds its lines. Pictures for the Text page are taken by your own app afterwards, in the background. If a game update renamed or removed some lines, those are skipped and the window says how many. Sharing can be switched off under Settings, Privacy, with Share my Studio reads; you can still get lines others shared.
Deleting a video only removes it from this computer, with your takes. What was shared stays for everyone, a read that was still waiting to be shared is sent first, and the video appears under Shared for this game again, ready to add back.
Shared for this game
1Read by others. Add one to skip reading it yourself.- YouTube6:02:26
Hollowtide Full Walkthrough, No Commentary
1,204 linesread by 3 people
Reading the subtitles off the picture
Games burn their subtitles into the video rather than shipping a caption track, so there is usually nothing to download. Tranzio watches the bottom of the picture instead and reads each line it finds, along with the moment it appeared and the moment it went away. That is where the timings come from, so they are measured rather than guessed, and it works the same on a link and on a clip you recorded yourself.
38 lines found, 29 matched to the game's own text. The rest wait in the unmatched queue.
GIFThe box says what is a subtitle; the reader looks at everything.Text inside the box that matches one of the game’s spoken lines becomes a line on the timeline, with the game’s own recording next to it. The rest of the picture is read too, on a slower rhythm: a menu, a chapter title, an objective or a loading screen that matches the game’s text is photographed for the Text page, so you can see where a string is used, and never becomes a line. A string keeps at most three pictures, never two of the same moment. The frame test in the region editor shows both: what the box read, and what the rest of the picture turned out to be.
It reads only the stretch you focused on. A playthrough recording runs for hours and almost never needs reading end to end, so setting a start and end on the import screen is the difference between a couple of minutes and most of an afternoon. A local file reads several times faster than a link, because a link is being fetched as it goes.
When it finishes, the lines are matched against the game's own text automatically. Anything that matched nothing is still placed on the timeline and waits in the unmatched queue in the editor, where you can attach it by hand.
Each line also gets the original delivery attached. Where a line matched a string the game has audio for, it gets the game's own recording, which is the line by itself. That covers every way a game links the two: a clip recorded for one line, a single clip covering a whole conversation, and a game whose clips were linked against a different language than the one being translated, which is commoner than it sounds. Everything else is cut out of the video using the times the read worked out, which carries whatever music and gunfire were playing over it but is still far better than nothing. Either way you can hear how a line was said before recording your own, and neither one asks you to attach a file by hand. A video with no audio track simply gets no clips, and those lines work as they always did.
Those clips stay on your machine. They are the video's audio rather than anything you made, so they are stripped out of an adaptation before it is published, along with every other local path.
Stopping is safe, and you can carry on later. The dialog keeps every line found up to that point and remembers where it got to, so the source shows a Continue button with the time it reached. Pressing it starts again from there and adds to what is already on the timeline rather than replacing it. That is what makes a long recording workable: read a scene, stop, come back to it.
Every imported source also carries a read button, which asks whether to carry on from where the last read stopped or to read the whole focused stretch again. The second replaces the lines already read from that video; the first only adds. Both say roughly how long they will take before you choose. Nothing needs deleting and re-importing to be read a second time.
While it runs the dialog shows the actual strip of the picture being read and the words got out of it. That is the quickest way to tell a working read from one aimed at scenery, and it is worth a glance in the first few seconds. Under it are how far it has got and roughly how long is left, then three numbers: lines found, how many are in the game’s text, and how many come with the game’s audio. They climb as it goes, because every line is looked up the moment it is read rather than all at once at the end. Last lines found lists the newest few, each marked In the game or Not in the game, which is the plainest proof the box is right. If it is not, Stop and change the box is always in the corner: it keeps what was read and takes you straight back to the box.
Each answer is remembered for that video, so a subtitle held on screen for four seconds is looked up once rather than twenty times, and a phrase that comes back an hour later is not looked up again at all. That record is kept beside the video's clips and is deleted with the source, which is also why carrying on a stopped read is cheap: it does not re-ask anything the first attempt already answered.
If a game puts its subtitles somewhere else, say so first. The reader looks at the bottom middle, which is right for nearly every game and useless for the rest. The read chooser on a source has a Set where the subtitles are option: it shows a frame and walks you through three steps on the right. Find a moment with a subtitle by dragging the timeline or stepping with the buttons, since a silent shot proves nothing either way; it covers the stretch the source is focused on, because that is the only part that will be read. Put the box over it: drag the green box (its middle moves it, its corners resize it), or start from one of the little pictures of the usual places. Under that, What the reader sees shows the inside of the box, enlarged, as you move it, so a box that cuts a line in half shows it straight away. Then Test it. The answer leads with one line, Looks right, Read, but not the game’s text or Nothing found here, and under it the exact strip the reader read, the words it got, the game’s own wording of the line those words matched, and its recording to play back. Reading the two lines side by side is what catches a region one line too high, which can still match something.
GIFOnly what is inside the box, with the ignored part blacked out. If the words look cut off, make the box bigger.
Tranzio read a line here and found it in the game's text.
The lighthouse has been dark for a week.
Speaker read as MARGOT
The lighthouse has been dark for a week.
- Hollowtide Harbourgame text, will be pictured
The reader keeps a picture of each line as well.The moment a line matches one of the game’s strings it keeps one frame of the video where the line is said, so the Text page and the Audio page can show the moment beside the string: who says it, to whom, in what room. Beside the pictures, each video the line was found in plays right there from that moment, in the editor’s own player, for as long as the video is still in Studio. One picture per line per video, however long the line stays up and however many times the same video is imported; a different playthrough adds another. They are kept sealed with the rest of the vault and open in a gallery from the line’s row or its rail.
The same editor can ignoreparts of the picture. Games put ammo counters, objective markers and keybind prompts in the same strip as their subtitles, and a recording often carries the channel’s watermark on top of that. All of it reads as text. Press Ignore a part of the picture and a red box appears in a corner, where watermarks usually sit, saying Drag me over the logo. Move it and resize it like the green one; press again for another, which takes the next free corner. Whatever it covers is painted over before the picture is read, which is more certain than filtering its words out afterwards. The boxes are saved with the region and listed, each with a picture of what it covers, so you can remove one.
The first read downloads the reading models, which takes a moment and happens once per language. After that everything runs on your own machine, so no frame of the video is ever sent anywhere.
The editor
The editor pairs the video with a multi-track timeline. Each caption becomes a line you translate and voice, and your recording sits on the lane underneath, split into chunks, one per line. Seeing them stacked is the whole point: you can tell at a glance whether your delivery lands where the original did.
GIFA bar across the top walks you through the four steps in order, and the editor changes its advice as you move along it:
- Watch
Play the clip end to end first. Get the rhythm, the pauses, the order the lines come in. Scrub the ruler to jump around.
- Record
Record all your lines in one continuous take rather than one line at a time. The original audio ducks while you record so you can hear the timing you're matching, and gaps are fine because the next step splits on them.
- Split
Your take gets cut into chunks at the silences, one chunk per line. Review the cuts. To add one, scrub to the moment and press ⌘ + B (or the Split at playhead button on the rail), or take the split tool and click a chunk: the blade snaps to the playhead and shows how long each piece will be. Merge two that shouldn't have been separated.
- Match
Point each chunk at the line it replaces. This is what turns a long recording into a set of dubbed lines.
The video and its captions
The line being spoken sits on the picture in a caption card: your language large, the original small under it if you want it. The ring beside it counts down to the end of the line, so you know how long you have to say it. On the right, Now playing repeats the current line and Up next lists the ones coming, each with a countdown and a bar that fills over the last ten seconds before it starts. The next one is lit, so you can take a breath before it arrives.
Now playing
The tide is turning, we have to go.
潮が変わる、もう行かないと。
00:00:02 · 4.0s
Up next
Not without the map.
Then find it, and quickly.
The tide is turning, we have to go.
潮が変わる、もう行かないと。
The pill in the top corner says what you are hearing: Preview plays the video with your recordings over it, and Recording (in red, with the running time) means your microphone is live. It also names both languages and the playback speed. The gear in the control bar sets the size and height of the captions, their background, whether the original line, overlapping lines and the countdown ring show, and whether the side panel is there and how many lines it lists. None of it changes the game, only what you see here.
Matching chunks to lines
Matching is the step that makes the rest count, and it's mostly automatic. Auto-match walks every unmatched chunk and links it to the nearest caption in time, which is right almost every time when you recorded along with the video. What it gets wrong you fix by clicking a chunk and then clicking the line it belongs to, or by dragging the chunk onto it. The whole auto-match is one undo, so trying it costs nothing.
- 0:04It never rains here.Take 1
- 0:09Not since the harbour closed.Take 1
- 0:14Come inside, you're soaked.Take 1
- 0:19I'll put the kettle on.Take 1
GIFLines are yours to reshape, too. Split one that runs too long for a single breath, merge two that are really one sentence, or add a line by hand when the captions missed something. Short lines are the secret; nobody dubs a paragraph in one breath.
The Subtitles tab under the video lists every line with a dot for where it stands: dubbed, not dubbed, not linked to the game, or a match to check. The chips above it count each and narrow the list. Pick a line and it opens beside the list, to change when it starts and ends, fix its words, translate it, and hear the original against your dub. The arrows step to the next line, so a run of fixes never leaves the keyboard for long.
The inspector on the right changes with what you pick, and its header says which it is. An original line shows its text, timing and original clip. A dub, a piece of your take linked to a line, shows that line on top (the original and your translation) so you can check it says what it should, then its waveform and voice. An unlinked take shows where it would best fit, so linking it is one click.
Attaching the original clip
A line can carry the game's own recording of it, which is what the A / B waveforms in the inspector compare: the original above, your take below. Press Attach original audio and a search opens over every clip the game scan found.
Search matches what is said first, then event, bank and file names, so a few words of the line usually finds it. When Tranzio already ties a clip to this line it is pinned to the top and marked Suggested. Arrow keys move through the results and Enter attaches, so a scene can be linked without leaving the keyboard, and the filters narrow to the suggestion or to clips nothing is linked to yet.
Nothing to search means the game's audio has not been scanned. Run a scan from the Audio page first, and the clips appear here.
The original clip is also what opens the full controls. At the top of the inspector, Open in the DAW for full control takes the selected take or line into the sound editor, next to the original, to trim it and shape its voice by hand. Until the line has its original clip the button stays greyed out and says what to link first.
It works the other way too. A line whose original clip you already dubbed in the sound editor (or on the Audio page) shows that dub here: when the video opens, it lands on your take row where the line is said, named DAW dub and already linked, so nothing you did there is missing here. Each dub comes in once; delete its take and it stays gone, until you dub that line again in the sound editor.
The tools down the left
Six tools, one at a time. Select is the normal pointer: click a piece to pick it, drag it to move it. Hand drags the timeline itself, so you can look at another moment without moving anything. Split cuts a take in two where you click, so you can keep the good half; the cut deletes nothing. Volume shapes how loud a take is over time, point by point. Link ties a piece of video to the line of text it shows, and the number on it is how many pieces are still unlinked. Record records your voice from where the playhead is, after a short countdown. The letter on each tool is its key.
Select V
Click a piece to pick it. Drag it to move it.
One tool is active at a time. The letter is its key.
Above the tools sit Undo and Redo. They take back or put back the last cut, move, link or recording. If a tool did something you did not expect, undo first and read this page second.
Play, pause and move around
The bar along the bottom is how you move through the video. The big button plays and pauses (so does Space). The two arrows beside it skip ten seconds back or forward. Loop plays the current line's moment over and over, which is the easiest way to rehearse before you record. Speed slows the video down to catch fast speech or speeds it up to skim; recording always runs at normal speed. The clock shows where you are and how long the video is; click it to type a time or jump to one of your scenes.
Recording lives in one box at the right, the same as in the sound editor: the microphone you are using (click it for its setup), a few bars showing its level while you record, and Record, which R also presses.
Takes: every attempt, kept
Each time you record a line, the recording is kept as a take. You can record the same line five times and pick the best one; the others cost nothing and sit in the Takes list until you delete them. Play each take, keep the one you like, and that is the one that goes into the game.
The Takes tab shows every take as a card, the same card the sound editor uses: its colour and name, where it came from (Recorded, AI voice, DAW dub or Imported), how many lines it dubs, and where it sits. Current marks the take new recordings go into. Play it from the card, jump to it on the timeline, or narrow the cards by kind.
Line 214 · MELINA_GREET_01
ああ、褪せ人よ。黄金樹のふもとで、ずっと待っていた。
- Take 10:03
- Take 20:03Kept
- Take 30:04
Editor shortcuts
Recording goes much smoother when play, pause, and record are on keys. The full list lives in Keyboard shortcuts; these are the ones you'll use every minute:
| Shortcut | Action |
|---|---|
| Space | Play / pause |
| R | Start or stop recording |
| ← / → | Skip back / forward 5 seconds |
| Ctrl+K | Auto-match every unmatched chunk |
| Ctrl+B | Split the chunk under the playhead |
| V / H / S / L | Tools: select, hand, split, link |
| Ctrl+Z | Undo |
Going back to an earlier version
Studio keeps a version of this video's document, the chunks, the lines they are matched to and the scene markers, after every change you make, and keeps them for 30 days. Undo only reaches back as far as the editor has been open; this reaches back days. Open it with the History button at the bottom of the tool rail, under undo and redo.
The panel lists your versions by day, newest first, with what was done and at what time. The one at the top is the video as it stands now. Click any other and it appears on the timeline, marked at the top as a version you are only looking at: playback works, but nothing you do can change it. Restore this version makes it the video again, and Back to current leaves it alone. Escape does the same as Back to current.
Restoring is not destructive. The version you were on before is still in the list, so restoring the wrong one costs you a click, not a take. Your recordings are never deleted by a restore either: the audio files stay on disk, so a version from last week still plays.
This history is private to this computer. It is never uploaded, never shared with the rest of the adaptation, and never shipped in a build.
Rule of thumb for which tool: Studio for a video, Audio Lab for the game. If the thing you're dubbing has a play button and a duration, it's Studio. If it's spoken lines the game triggers while playing, it's Audio Lab.
The two rooms do meet in one place. If a line in Studio is attached to the game's own audio file, the chunks you matched to it are mixed down and packed into the patch when you build, under the step called Compiling studio recordings. So a cutscene dubbed here can ship inside the game, not just alongside it.