Upload the video or paste a link. The legendas come back in Portuguese — the words as spoken, never an English version — timed from word-level timestamps and ready to import. Files over 500 MB continue on the upload page. A pack from $4 opens the full transcript · packs from $4 for 500 minutes.
How it works
The soundtrack is read out of the video; nothing to extract by hand.
MP4, MOV or WebM into the box above, or paste a public link. Over 500 MB, continue on the upload page.
Cues are built from the timestamp on each word, so a line lands as it is said. Your first transcript opens in full at any length.
SRT for an editor or a platform upload, VTT for a player on the web, and TXT, DOCX, MD and JSON from the same job.
Readable lines
The timings arrive done. Line length and trimming are editorial calls you make in a subtitle tool.
Portuguese usually needs more characters than the English of the same dialogue, so a line that was comfortable in an English cut can spill. Budget time to trim a share of the cues.
That is the common ceiling per line and per cue. What comes out of here is speech timed to the frame; where the break falls is yours to decide.
Roughly 17 characters a second is the usual limit for adult programming. Split a fast cue rather than letting the viewer read half of it.
ã, õ and ç are written into the file. Import and save as UTF-8 or the marks arrive in the editor as broken characters.
Sidecar or burned in
You download the sidecar; the burn-in happens in your editor.
SRT or VTT remains separate: viewers switch it off, platforms read the words, and fixing a name later costs one upload rather than a whole re-export.
When the legendas must be permanent — social cuts, mostly — bring the SRT into Premiere Pro or DaVinci Resolve and render it into the picture.
SRT and VTT carry words and timings only. A two-hander that needs names on screen gets them in the editor; JSON holds the speaker of each segment.
Upload the audio alone when the video file is huge. The timeline is unchanged, so the cues still fall where they belong.
Pricing
A pack from $4 opens the full transcript. After that, one-time packs: $8 for 1,000 minutes, $12 for 2,000 minutes and $24 for 5,000 minutes. Credits never expire.
A 15-minute video is $0.12 on the $8 pack. A back catalogue of sixty of them is 900 minutes and still fits that same pack.
FAQ
Yes. The file holds the Portuguese that was spoken. Nothing is turned into English: Portuguese video produces Portuguese cues.
Yes, with no extra charge for the second format. Each job exports SRT, VTT, TXT, DOCX, MD and JSON.
Every word carries its own timestamp and the cues are built from those, so lines appear when they are spoken rather than on an even division of the running time.
No. Numbered speaker labels appear in the transcript view on screen. SRT and VTT hold words and timings; JSON is the export that keeps the speaker of each segment.
There is nothing to set. Both are captioned in Portuguese, and the spelling follows the speaker rather than being standardised to one side of the Atlantic.
Usually. Public video links are fetched, though some sources refuse to release their audio — Spotify, Podbean and Kick VODs among them — and those you upload.
Up to 10 hours or 5 GB per file. The box takes 500 MB, larger files continue on the upload page, and your first transcript reads in full at any length.
Instant preview, no signup. A pack from $4 opens the full transcript.