Skip to content
audo

Create an SRT file from video or audio

Turn your recording into an SRT file with timed captions.

10M+ files processed since 2021

Such as um and uh.

Speaker 1, Speaker 2, and so on.

Free for the first 2 minutes, 3 times a day. No sign-up.

Captions that keep time

Press play to see each caption on time.

Your SRT file

  1. 1
    00:00:00,480 --> 00:00:04,480    And this was a heavy animal enough to create a kind of a microseism
  2. 2
    00:00:04,920 --> 00:00:08,720    in the soil beneath, which gives you this concentric pattern, uh, to it.
  3. 3
    00:00:09,080 --> 00:00:13,299    We like to think of this as the grand matriarch of the herd of Colombian mammoth
  4. 4
    00:00:13,600 --> 00:00:16,360    that strolled through here about 100,000 years ago.

Made with Transcribe

Transcribes 60 languages

Detects the language automatically.

  • English
  • DeutschGerman
  • FrançaisFrench
  • EspañolSpanish
  • ItalianoItalian
  • NederlandsDutch
  • 日本語Japanese
  • 한국어Korean
Show all 60 languages
  • Afrikaans
  • العربيةArabic
  • ՀայերենArmenian
  • অসমীয়াAssamese
  • AzərbaycancaAzerbaijani
  • বাংলাBengali
  • BosanskiBosnian
  • БългарскиBulgarian
  • 粵語Cantonese
  • CatalàCatalan
  • 简体中文Chinese (Simplified)
  • ČeštinaCzech
  • DanskDanish
  • NederlandsDutch
  • English
  • EestiEstonian
  • Filipino
  • SuomiFinnish
  • FrançaisFrench
  • GalegoGalician
  • DeutschGerman
  • ΕλληνικάGreek
  • ગુજરાતીGujarati
  • עבריתHebrew
  • हिन्दीHindi
  • MagyarHungarian
  • ÍslenskaIcelandic
  • Bahasa IndonesiaIndonesian
  • ItalianoItalian
  • 日本語Japanese
  • ಕನ್ನಡKannada
  • Қазақ тіліKazakh
  • 한국어Korean
  • LatviešuLatvian
  • LietuviųLithuanian
  • МакедонскиMacedonian
  • Bahasa MelayuMalay
  • മലയാളംMalayalam
  • मराठीMarathi
  • नेपालीNepali
  • Norsk bokmålNorwegian Bokmål
  • ଓଡ଼ିଆOdia
  • فارسیPersian
  • PolskiPolish
  • PortuguêsPortuguese
  • ਪੰਜਾਬੀPunjabi
  • RomânăRomanian
  • РусскийRussian
  • SlovenčinaSlovak
  • SlovenščinaSlovenian
  • EspañolSpanish
  • KiswahiliSwahili
  • SvenskaSwedish
  • தமிழ்Tamil
  • తెలుగుTelugu
  • ไทยThai
  • TürkçeTurkish
  • УкраїнськаUkrainian
  • اردوUrdu
  • Tiếng ViệtVietnamese

How to create an SRT file

  1. 1

    Add a video or audio file, such as an MP4 or MP3.

  2. 2

    Choose the language, or leave it to detect automatically.

  3. 3

    Download the SRT file, ready to upload.

What's inside an SRT file

An SRT file is a list of captions in plain text. Each one has a number, a start and an end time, and the words to show. The example above is a scientist describing a mammoth trackway outdoors, and its SRT file is exactly what came back: four captions, each with its number and times.

A minute of audio is usually ready in about 7 seconds. Start from a clear recording for the best captions; for a noisy one, run it through Remove noise first. When several people talk, no caption mixes two of them, and the SRT names no one, so it stays clean on screen. You also get VTT captions, the plain text, and the time of every word.

Questions

Is it free?

Yes, for the first 2 minutes of each file, 3 times a day, with no sign-up. For longer files, see pricing.

Will the SRT work on YouTube?

Yes. Upload it to YouTube, or to most video players, as the video's captions. To caption a video that's already on your channel, download it from YouTube Studio first, then add the file here: links don't work.

Can I edit the SRT file?

Yes. It's plain text, so any text editor opens it. Fix a word or a name, keep the numbers and times as they are, and save it.

Which languages does it work in?

Any of 60 languages. Leave Language on Detect automatically, or choose it yourself before you start.

How are the captions timed and split?

Each caption gets the moment its words start and end. It holds at most two lines of up to 42 characters and stays on screen for up to 7 seconds. A pause of a second starts a new one, and captions end with sentences, breaking at commas where they can.

Can I do MP4 to SRT or MP3 to SRT?

Yes, and the same goes for any video or audio file: MP4, MOV, MKV, WebM, AVI videos, and WAV, MP3, M4A, AAC, FLAC, OGG, Opus, WebM, AIFF audio. Files can run up to 10 hours.

What if I already have the script?

Use Text to SRT. It times your own script to the recording and keeps your spelling exactly. This page starts from the speech instead, so you don't need a script.

What happens to my files?

They stay private. Files are deleted after 24 hours, and free results after 1 hour.

More tools

All tools

For AI assistants and developers

Ask ChatGPT, Claude, or a coding agent to do this for you, or call it from your own code. When an agent's free result is cut short, it gives you a link to finish the whole file, no sign-up.

Show the free API call
Free API · no key
curl -F file=@vlog.mp4 -F format=srt https://audo.ai/api/try/transcribe -D response.headers -o response.body