How to translate subtitles, step by step

This is the practical version: which button, in which order, and what each screen will show you. It takes about five minutes to read and covers the whole path from upload to two subtitle files that line up.

Before you start

Two things decide which route you need.

If all you want is English out of non-English audio, you can skip most of this. In the transcribe dialog, tick Transcribe to English. It runs inside the speech model itself, so the transcript comes out in English directly. There's a dedicated page for that route: translate audio to English.

For any other language, or English alongside the original, translate the finished transcript. That's the route this guide covers. It works on every plan, free included, and covers 134+ target languages, because the translation itself is done by Google Translate. You pick the language after the transcript is finished, so there is nothing to decide before you upload. Only the text is translated: every line keeps its original start and end time.

Step 1 — Transcribe as usual

Open Transcribe file, pick your audio or video and start the job. If there is more than one voice in the recording, expand Speaker detection & more settings and tick Detect speakers. Subtitles then break where the speaker changes instead of mid-answer, which makes the translated track much easier to read.

Step 2 — Proofread the original first

Open the transcript. Click any line to play the audio from that point, which is the fast way to check a name or a number you're unsure about.

Do this before you translate. A misheard name in the original becomes a mistranslated name in every language you make from it, and editing the original afterwards does not re-translate it. The page flags that case with a warning that the translation may be out of date. It does not fix the translation for you.

Step 3 — Open Translate

In the panel next to the transcript, click Translate. A new tab opens with your transcript inside Google Translate. Pick the target language in the Google Translate bar at the top of that page.

The link to the transcript page is signed and expires. If you come back to an old tab and see "Link expired or invalid", click Translate in ScribeToAny again.

Step 4 — Save the translation back

On the translated page, click Save to ScribeToAny subtitles. Check the language it detected, then confirm. Two things to know:

Translate the page first. What gets saved is the translated text currently on screen. If the page is still in the original language, that's what you'll save.
The original is never touched. The translation is stored as a separate language track. Saving the same language again replaces that track, not your transcript.

ScribeToAny opens in a new window and adds the track. If nothing happens, your browser probably blocked the pop-up. Allow pop-ups for the page and click again.

If you only need the files and not the track in ScribeToAny, the same page has Download buttons for the translated TXT, SRT, VTT and CSV.

Step 5 — Switch between the two versions

Once a translation is saved, a row of buttons appears above the transcript: Original, then one per language.

Clicking a language swaps the text and nothing else. Timestamps and speaker labels stay where they were, so click-to-play works the same way in the translated view. You can fix a clumsy translated line right there without changing the original.

Step 6 — Export both tracks

Here's the mechanic that isn't obvious: export gives you whichever version is currently on screen.

So getting a bilingual pair is two exports, not one:

Stay on Original → export SRT.
Click your language → export SRT again.

You now have two files whose cue times match line for line. That's what makes them stackable: in Premiere, Final Cut or DaVinci put them on two separate subtitle tracks, one above the other. On YouTube, upload them as two subtitle tracks and let the viewer pick. The same pair of files works for translating a YouTube video.

If you'd rather start from an existing subtitle file than from the video, the SRT translator page covers that path.

The same applies to all eight formats. If you want the translation as a document rather than subtitles, switch to the language first, then export PDF or DOCX.

Three things that will bite you

Proofread before you translate. Worth repeating: edits to the original don't flow into a translation you've already saved. You'd have to translate and save again.

Line lengths change. A line that fits comfortably in English can overflow in German or Spanish, while Chinese and Japanese usually come out shorter. If your platform enforces a character limit, shorten the translated lines in the language view before you export.

Machine translation is a draft. Google Translate handles everyday speech well, but idioms, jokes and technical terms deserve a read-through by someone who knows the language before the subtitles go public.

When a human translator is worth it

Machine translation plus your own read-through is enough for most internal videos, lectures, interviews and social clips. Some jobs need more than that:

Anything going on air or into cinemas. Broadcasters and distributors have their own subtitle specifications, and professional subtitlers work to them.
Marketing and brand copy. Slogans, wordplay and tone rarely survive a line-by-line translation. They need adapting, not just translating.
Legal, medical and other regulated material. A wrong term has consequences, and you may need a certified translation.
Languages nobody on your team reads. If you can't proofread the result, you can't vouch for it.

For those, hand the job to a professional translation and subtitling agency such as Atenao. ScribeToAny still helps with the first step: a timed transcript and an SRT of the original give the translator clean source text and cue times to work from.

Ready to try it? Start from subtitle translation if you're working from video, or translate video to text if you want the transcript as a document rather than as cues.