How to make SRT subtitles from a video with an AI assistant

An SRT file is plain text: numbered cues with a start time, an end time and the words. Most video tools read it. Ears returns real SRT with timestamps from any recording, so your assistant can hand you a file you can use right away.

This is what the first cues of our sample recording look like:

1
00:00:00,000 --> 00:00:04,380
Hello, this is a short sample recording for the EARS transcription service.

2
00:00:04,940 --> 00:00:08,520
Today is Monday, and the team meeting starts at 3.30.

1. Connect Ears once

Ears is a remote MCP server, so there is nothing to install. Add this address to your assistant:

https://useears.com/mcp

New accounts get 30 free credits, enough for 30 minutes of audio. No card is needed.

2. Ask for subtitles

Say that you want SRT. Without that, the assistant gets the text only, which keeps answers short.

Give me SRT subtitles for https://useears.com/sample.wav and save them as subs.srt.

Ears detects the language by itself. To force one, name it: “in Spanish”. For a video on your computer, ask the assistant to transcribe the file and it will send it through a one-time upload link.

3. Use the file

ffmpeg -i video.mp4 -vf subtitles=subs.srt -c:a copy out.mp4

Or to add them as a switchable track in an MP4:

ffmpeg -i video.mp4 -i subs.srt -c copy -c:s mov_text out.mp4

Tips

A 10-minute video costs 10 credits, which is €0.10. Failed jobs are not charged.

See the prices

More guides