Upload the interview from the sound recorder or the camera, correct names on the transcript, and download an SRT to import into your edit, plus a timestamped DOCX for the paper edit.
How it works
If sound was recorded separately, upload the recorder's file from the lav or boom rather than the camera's guide track. WAV, MOV and MP4 files all work.
Interviewees' names, places and organisations are where errors cluster. Correct them on the transcript; every download carries the change.
Import the SRT into Premiere Pro, DaVinci Resolve or Final Cut Pro against the clip, and take the DOCX, with a timestamp on every line, for the paper edit.
Timecode
Cue times count from the first moment of the file you upload, starting at 00:00:00. Camera and recorder files carry their own source timecode, often time of day, and many edit sequences start at 01:00:00:00. So:
Editor steps: Premiere Pro, DaVinci Resolve, Final Cut Pro.
A working file, not a delivery file
Each cue holds at most two lines of about 42 characters and stays on screen for one to seven seconds, so the file reads as subtitles in the edit straight away. That is what selects, a rough cut screened with subtitles, and a subtitler's first pass need.
Long interviews
One file can be up to 10 hours or 5 GB. In our production records for 2026-07-06 to 2026-10-04, recordings of 1 to 2 hours finished 98.9% of the time and 2 to 4 hours 99.2%; the longest public run is 9.31 hours, on long-file proof.
Camera originals over 5 GB do not upload. Take the soundtrack out with the free extract audio from video tool and upload that; the cue times still match the picture because the audio keeps the same timeline. For a day of rushes already in Google Drive, import the folder: documentary footage from Google Drive.
Before you rely on it
Each cue holds at most two lines of about 42 characters and stays on screen for one to seven seconds, breaking at the end of a sentence or clause where it can. The words are exactly the transcript's; only the breaks are chosen for the screen.
Cue times are taken from the recording itself, so the file lines up with the video or audio you uploaded. If you trim the start of the video afterwards, shift the cues by the same amount in your editor.
On public test recordings, about 7 words in 100 differed from the reference for clean English read speech, between 4 and 9 in 100 for Spanish, Portuguese, Russian, French and German, and about 21 in 100 for Hindi. Noisy rooms, music and crosstalk do worse. Method and every number: the benchmark.
Open the transcript, correct a misheard name or number on its line, and the SRT and VTT you download carry the correction with the timing unchanged.
You get the subtitle file. Fonts, colours, position and captions drawn into the picture are done in your video editor or player, which reads this file.
Up to 10 hours or 5 GB per recording. The box on this page takes files up to 500 MB; larger ones continue on the upload page. 99+ languages, detected automatically.
Speakers are identified and named in the summary, key quotes and chapters. The cues in the subtitle file carry the words and their timing only.
Pricing
The preview is free. When the full transcript needs a pack, one-time packs are $6 for 500 minutes, $8 for 1,000 minutes, $12 for 2,000 minutes, $24 for 5,000 minutes. Credits never expire, which comes to about $0.29 to $0.72 per hour of audio. Twenty one-hour interviews are 1,200 minutes, which fits the $12 pack of 2,000 minutes.
| Recording | $6 or $8 pack | $12 pack | $24 pack |
|---|---|---|---|
| 90-minute sit-down interview | $0.72 | $0.54 | $0.43 |
| A shoot day with 5 hours of interviews | $2.40 | $1.80 | $1.44 |
| 20 one-hour interviews | $9.60 | $7.20 | $5.76 |
Figures are the share of a pack each recording uses. A button opens secure checkout for that pack. Every export format is included; full details on the pricing page.
FAQ
Usually because the SRT starts at 00:00:00 and your sequence or the clip's source timecode does not. Line the subtitles up with the start of the clip, or shift every cue by the sequence start, for example one hour, in a subtitle editor before importing.
The recorder file from the lav or boom. It is the cleanest audio, so it transcribes best. The cue times follow that file and match the picture once the clips are synced in your edit.
Treat it as the working file. Delivery specs set their own formats and style rules, so the final subtitles are usually conformed to picture lock and converted to the format the spec names.
No. The cues carry the words and their timing. Speakers are identified and named in the summary, key quotes and chapters; add names to the subtitles in your editor where the picture does not make it clear.
Yes, in the language spoken: 99+ languages are detected automatically. The subtitles are not translated; give the timed SRT to a translator so the translation keeps the original timing.
Up to 10 hours or 5 GB per file. Interviews of 2 to 4 hours finished 99.2% of the time in our production records.
Every page in this set uses the same upload box and the same export. All subtitle pages
Free preview. SRT, VTT and a timestamped DOCX from one upload; packs from $6, credits never expire.