Text to SRT: sync your script to audio or video
Paste a script or TXT file and get SRT captions timed to the speech.
10M+ files processed since 2021
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 script
A honeybee can visit dozens of flowers in a single trip. Back at the hive, the nectar slowly turns into honey. One teaspoon of honey is the life's work of about a dozen bees.
Voices in these examples are AI-generated.
Works in 60 languages
Detects the language automatically.
- English
- DeutschGerman
- FrançaisFrench
- EspañolSpanish
- ItalianoItalian
- NederlandsDutch
- 日本語Japanese
- 한국어Korean
Show all 60 languagesShow fewer
- 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 convert text to SRT
- 1
Add the recording, audio or video.
- 2
Paste the script, or upload a TXT, SRT, or VTT file.
- 3
Download the SRT or VTT captions.
Lining up, not transcribing
Audo's Text to SRT tool takes a recording, audio (WAV, MP3, M4A, AAC, FLAC, OGG, Opus, WebM, AIFF) or video (MP4, MOV, MKV, WebM, AVI), up to 100 MB without an account, and a script pasted in or as a TXT, SRT, or VTT file up to 2 MB, free for the first 2 minutes of each recording, 3 times a day, with no sign-up. A 2-minute recording is usually ready in about 5 seconds.
It finds the moment each word of your script is said and gives every word a start and an end time. You get SRT captions, VTT captions, and the time of every word. It suits scripted videos, voiceovers, lyrics, talks given from notes, and audiobooks read from the book.
An SRT file is a list of numbered captions, each with a start time, an end time, and its line of text. VTT is the same idea for players on web pages. Both upload to YouTube and most video players.
Questions
How do I turn my script into SRT captions timed to my video?
Add the video at the top of this page, then paste the script or upload it as a TXT file. Audo finds when each word is said, and you download SRT or VTT captions in your script's exact words.
Is there a free text to SRT converter?
Yes. Audo's text to SRT converter is free for the first 2 minutes of each recording, 3 times a day, with no sign-up. Longer recordings cost $0.02 a minute ($1.20 an hour) with no subscription: see pricing.
Can I convert a TXT file to SRT without the recording?
No. A TXT file has no times in it, so they have to come from the recording. Without it, a converter can only guess when each line is said.
How do I fix subtitles that are out of sync?
Add the recording, then add the old SRT or VTT file as the script. Your words stay the same, and you get new captions timed to the speech. The captions are made fresh, so their line breaks can change.
What if the recording doesn't match the script?
The result says how many of the script's words were found, such as 480 of 500, and warns you when it's under half. Lines the speaker skipped or changed won't line up well.
Why use my script instead of transcribing?
Your script keeps its exact words and spelling, so names, brands, and lyrics come out right. Transcribing works the words out from the sound and can get them wrong. No script? SRT file generator makes captions from the speech alone.
Do numbers and spellings have to match what's said?
Not in English. A script that says 25 matches someone saying twenty-five, colour matches color, and don't matches do not.
Which languages does it work in?
60 languages, the same ones Transcribe knows. The script has to be in the language spoken in the recording.
More tools
- Transcribe audioSpeech to text, who said what.
- Remove filler wordsCut the ums and uhs.
- Audio enhancerMake any recording sound studio‑quality.
- Remove noiseClears the background, keeps your voice.
- Remove echoMake voices sound close.
- Voice recorderRecord, then trim and clean up.
- Screen recorderRecord screen, camera, and sound.
- Webcam recorderRecord camera and mic online.
- Record computer audioRecord tab or system sound.
- Mic testTest your microphone and sound.
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
curl -F file=@talk.mp3 -F script=@script.txt -F format=srt https://audo.ai/api/try/align-script -D response.headers -o response.body