Skip to content
Neattrim

SRT to voice-over

Give the tool an SRT file and it speaks each subtitle line at its cue time, so the audio can be laid over the video that the subtitles came from.

Runs on our servers. Your text is sent there to make the result. Results are kept in your library for 7 days when you are signed in with library saving on, otherwise for 24 hours; uploads are deleted after 24 hours.

Preset for this page

Input
SRT
Timed
Yes

The tool below starts with these settings. Change any of them in the tool.

Your text is sent to our servers to make the speech. If you are signed in with library saving on, the result is kept 7 days; otherwise it is deleted after 24 hours.

0 of 10000 characters

Voice
Standard voices
Better voices

Better voices need Pro. You can hear a sample, but not make speech with them.

Your own voice

Looking for your voice

How to

  1. Upload the SRT file. Add your .srt file. Make sure it is plain text with numbered cues and timestamps.
  2. Choose language and voice. Pick the language the subtitles are written in, then choose a voice and listen to the sample.
  3. Shorten cues that are too long. Edit lines that are too long for their time window, or the voice will have to speed up or overrun.
  4. Generate and align. Generate the timed audio and add it to your video at the start.

A voice that follows the timestamps

An SRT file is a list of numbered cues, each with a start time, an end time and a line of text. Instead of reading the text as one block, this preset reads each cue at its start time. The audio therefore matches the video that the subtitles describe, which is what dubbing and audio description both need.

The main challenge is fit. A spoken sentence needs more time than the same sentence takes to read in silence, and translated text is often longer than the original. If a cue is too long for its window, the voice can run over into the next cue. Check the preview, then shorten the cue text or extend its end time in the file. A faster speed setting can also help, but a very fast voice becomes tiring.

Other practical points: keep each cue to one idea, use a comma where the speaker would pause, and write numbers and abbreviations as you want them heard. If the subtitles are in another language than your audience speaks, translate the file first with the subtitle translator. For a dubbed video, mix the voice-over under the original audio or replace it in your editor. Disclose synthetic audio where the platform requires it.

Frequently asked questions

What if two cues overlap in my SRT file?
Overlaps make the voices collide. Fix the end time of the first cue, or merge the two lines before generating.
Can I use a VTT file instead?
Convert it to SRT first with the subtitle converter, then upload it here.
Will the voice read the cue numbers and timestamps?
No. Only the text lines are spoken. The numbers and times are used for timing.
Why does a line sound rushed?
Its cue window is too short for the text. Lengthen the window or shorten the line.
Is this the same as AI dubbing?
No. This speaks the text you provide. AI dubbing transcribes, translates and re-voices a whole video.

More tools

All tools