No account
- Price
- Free
- Files
- Your first file
- Transcribed per file
- First 5 minutes
- Read, edit and copy
- Yes
- TXT, DOCX, PDF, SRT and VTT
- No
- Translation
- No
Subtitle generator for SRT and VTT files
Upload a video and the Kotosay video subtitle generator writes subtitles timed to the speech. Fix any word in the editor, then download SRT or VTT with Unlimited and add them in YouTube Studio, Vimeo or your video editor.
SRT and VTTTimed to the speech90+ languages
See the cues before you download.
00:00:10,020
I recorded voice notes between meetingsand never listened to them again.
Characters per line42
Lines per cue2
13 00:00:10,020 --> 00:00:13,600 I recorded voice notes between meetings and never listened to them again.
How each cue is cut.
2lines per cue, never more
42characters per line at most
1 to 7 son screen per cue
17characters per second, easy to read
Breaks fall on pauses and punctuation and avoid splitting a name or a number.
How to generate subtitles for a video automatically
- 1
Upload the video
MP4, MOV, WEBM, MKV or AVI. Your browser normally sends only the sound.
- 2
Fix the words
Correct names and terms in the editor. The timing of each line stays as it is.
- 3
Download SRT or VTT
Export with Unlimited and add the file to your video platform or editor.
Works where you edit
YouTube Studio
Upload SRT or VTT under Subtitles for any video on your channel.
Vimeo
Add the file as a caption or subtitle track in the video settings.
Video editors
Premiere Pro, DaVinci Resolve and Final Cut Pro import SRT files.
Web players
VTT is the format HTML5 video players read.
Subtitles per plan
| No account | Free account | Unlimited | |
|---|---|---|---|
| Price | Free | Free | $9.99 a month, or $119 paid once a year |
| Files | Your first file | 3 a day | 3 at once |
| Transcribed per file | First 5 minutes | First 5 minutes | Up to 10 hours |
| Read, edit and copy | Yes | Yes | Yes |
| TXT, DOCX, PDF, SRT and VTT | No | No | Yes |
| Translation | No | No | Yes |
Free account
- Price
- Free
- Files
- 3 a day
- Transcribed per file
- First 5 minutes
- Read, edit and copy
- Yes
- TXT, DOCX, PDF, SRT and VTT
- No
- Translation
- No
Unlimited
- Price
- $9.99 a month, or $119 paid once a year
- Files
- 3 at once
- Transcribed per file
- Up to 10 hours
- Read, edit and copy
- Yes
- TXT, DOCX, PDF, SRT and VTT
- Yes
- Translation
- Yes
SRT and VTT downloads come with Unlimited, which cancels in one click and shows your renewal date in your account. For one video, Single file includes them for $4.99.
What happens to your file
The sound of your video is transcribed on secure servers and deleted automatically 24 hours later. Your subtitles stay in your account until you remove them or close the account.
GUIDE · 3 min read
Using a subtitle generator for your videos
An AI subtitle generator that starts from the transcript
Kotosay works as an auto subtitle generator. It transcribes the speech, times every line and turns the transcript into cues. Use it as a caption generator for your own channel, or as a subtitle generator from video files you edit for clients.
What is an SRT file?
An SRT file is a plain text file of subtitles. Each cue has a number, a start and end time, the text, and a blank line before the next cue. You can open it in any text editor, which makes small fixes easy.
What is the difference between SRT and VTT?
Both hold the same cues. VTT starts with the line WEBVTT, uses a dot before the milliseconds, and can carry styling for web players. SRT is the older and more widely accepted format.
Use SRT for YouTube, Vimeo and video editors, and VTT for HTML5 players on a website. With Unlimited you can download both from the same transcript.
How do I add subtitles to a video?
The way you add subtitles to video depends on where it lives. On YouTube, open YouTube Studio, choose the video, go to Subtitles and upload the SRT or VTT file. On Vimeo, add it under the video's caption settings. In an editor such as Premiere Pro or DaVinci Resolve, import the SRT as a caption track.
How long each cue is
The subtitle generator keeps a standard cue to 2 lines of up to 42 characters each, timed at about 17 characters per second. That leaves viewers time to read a cue before the next one appears.
Vertical video needs less text at once, because the picture is narrow and captions often sit over faces. For those clips, a short mode makes cues of one line with about 20 characters, each on screen for 1 to 7 seconds.
Subtitles people can read
Good subtitles are short. Keep each cue to a line or two and break lines at a pause or a comma, and try not to split a name. Fix names and technical terms in the editor before you export, because a typo on screen stays visible for the whole cue.
TipNeed to move a cue by a few frames? Open the SRT in a free subtitle editor such as Subtitle Edit or Aegisub and shift the timing there.
A separate track or burned into the picture
A subtitle track is a separate file that viewers switch on or off, and you can replace it after a fix. YouTube, Vimeo and web players work this way.
Burned-in subtitles become part of the picture and are always visible. Reels and TikTok clips usually get them, so the words show even with the sound off. Import the SRT into an editor such as CapCut, Premiere Pro or DaVinci Resolve, style the text, then export the finished clip. Keep the subtitle export, so a typo spotted later means a quick re-export, not a full redo.
What is the difference between subtitles and closed captions?
Subtitles give viewers the spoken words, often in another language. Closed captions also describe sounds, such as music or laughter, for viewers who cannot hear the audio, and viewers can switch them on or off. An SRT file can serve as either, depending on what you write into it.
Adding sounds for viewers who cannot hear
For closed captions, add the sounds that matter to the story in square brackets, such as [door slams] or [audience laughs]. Type them into the nearest line in the editor before you export, and they come out at that line's time.
Subtitle questions
How do I generate subtitles for a video automatically?
Upload the video on this page and Kotosay transcribes the speech with a time for every line. Fix any word in the editor, then download the subtitles as SRT or VTT with Unlimited. The auto subtitle generator works for 90+ languages and detects the spoken language for you.
What is an SRT file?
An SRT file is a plain text subtitle file. Each cue holds a number, a start and end time and the text to show, followed by a blank line. Almost every video platform and editor reads SRT, and you can open the file in any text editor.
What is the difference between SRT and VTT?
They hold the same cues in slightly different formats. VTT starts with WEBVTT, uses a dot in the timecodes and can carry styling for web players. SRT is the older format that YouTube, Vimeo and most editors accept. Unlimited exports both from one transcript.
How do I add subtitles to a video?
Upload the SRT or VTT to the platform where the video lives. In YouTube Studio, open the video and go to Subtitles. On Vimeo, use the caption settings of the video. In Premiere Pro, DaVinci Resolve or Final Cut Pro, import the SRT as a caption track.
Can I edit the timing of subtitles?
Fix the words in the Kotosay editor, and each line keeps its timing to the speech. For frame-level changes, open the SRT in a free subtitle editor such as Subtitle Edit or Aegisub, or adjust the caption track in your video editor after you import it.
Can I make subtitles in another language?
Yes, with Unlimited. Upload the video on the translate page, and each translated line keeps the timing of the original speech. The translated SRT and VTT come from the same generator as your other subtitles, so you can add the file as a second track in YouTube Studio.
Do subtitles work on YouTube, TikTok and Instagram?
On YouTube, upload the SRT or VTT in YouTube Studio. TikTok and Instagram add captions inside their own apps, so for those, import the SRT into a video editor that burns captions into the picture, then upload the finished clip. The video subtitle generator gives you the text for all three.
What is the difference between subtitles and closed captions?
Subtitles show the spoken words, often translated for viewers who speak another language. Closed captions also describe sounds like music or applause, for viewers who cannot hear the audio, and can be switched on or off. An SRT file can hold either kind.
Are SRT exports free?
SRT and VTT downloads are part of Unlimited, at $9.99 a month, or $119 paid once a year. On the free plan you get the timed transcript for the first 5 minutes of each file, 3 files a day, and you can read, edit and copy it.
Can I make subtitles from an MP3?
Yes. Upload the MP3 and export the transcript as SRT or VTT with Unlimited. That is useful when you edited the audio of a video separately, or when you want timed captions for an audiogram or a podcast clip you publish as a video.
Does the timing match the speech?
Yes, each cue starts and ends with the words it shows, because the timing comes straight from the transcript. Fixing a word in the editor leaves the timing as it is. When people talk over each other, read those cues once before you publish.