Upload a video and get accurate subtitles back — either burned into the picture or as an SRT file you can edit and reuse. Word-level timing, 90+ languages, no signup.
Drop your video here
MP4, MOV, WebM or MKV — up to 100MB
Uploading is free and needs no account. Free tier: 5 minutes of audio per month. Running this tool needs an account, because it uses real processing time.
5 minutes of audio per month
Example Output
Real captions from a real recording: word-level timings from the source audio, burned into the picture so they show on a muted autoplay. The words are what was actually said — nothing was typed by hand.
How It Works
Any MP4, MOV, WebM or audio file. The soundtrack is what gets transcribed — picture quality does not matter.
Speech is transcribed with word-level timestamps, so each word is timed individually rather than a whole line at once.
Take a video with the captions rendered into the picture, or an SRT file to drop into your own editor.
It listens to the audio in your video, writes down what was said, and works out when each word was said. That timing is the whole trick: a transcript on its own is just text, but a transcript with timestamps can be displayed in sync with the speaker.
The output comes in two shapes. Burned-in (or 'hard') subtitles are drawn into the video's pixels, so they always appear and always look the way you styled them. An SRT file is a separate text file of lines and timecodes — editable, translatable, and toggleable by the viewer, but styled by whatever player opens it.
Short-form video is watched on mute far more often than not, so captions are not an accessibility extra on TikTok, Reels or Shorts — they are how most of the audience receives the words at all. Burned-in captions are the norm there precisely because a muted autoplay viewer will never tap a subtitle button.
Why Use This Tool
Every word carries its own timestamp, which is what makes karaoke-style highlighting possible instead of whole lines appearing at once.
English, Spanish, Portuguese, Hindi, Arabic, French, German, Japanese and many more, with automatic language detection.
Download a subtitle file for your own editor, or a finished video with the captions already rendered.
Five minutes of audio a month without an account.
The SRT is plain text, so any wrong word can be fixed in seconds before you publish.
Your upload is used to produce your captions and nothing else.
On clear speech with decent audio, accuracy is typically in the high nineties. Heavy background music, crosstalk, strong accents and distant microphones all pull it down — which is why the output is editable rather than final.
Strictly, subtitles assume you can hear and just need the words, while captions also describe non-speech audio for deaf and hard-of-hearing viewers. In short-form video the two words are used interchangeably for on-screen text of the dialogue.
Burn them in for TikTok, Reels and Shorts — autoplay is muted and viewers will not tap a caption toggle. Use SRT for YouTube long-form and anywhere viewers may want to turn captions off or pick a language.
This one, up to five minutes of audio per month. Beyond that it needs an account, because transcription costs real money per minute of audio processed.
Yes, and it transcribes both. Labelling who said what is detected where the audio makes it possible, but overlapping speech is genuinely hard and is where accuracy drops most.
MP4, MOV, WebM, plus audio-only MP3, M4A and WAV.
This page captions the file you give it. ShortsHero captions every clip it cuts out of your recording — styled to your brand, positioned inside each platform's safe zone so nothing sits under the caption bar or the username, and timed word by word.
Caption a whole recordingFree to start · No credit card required
Keep Going
Convert video to text free. Upload an MP4 and get an accurate, timestamped transcript with speaker labels where detectable. Download as TXT or SRT.
Paste any YouTube URL and get the full transcript with timestamps. Copy it, or download as TXT or SRT. Free, unlimited, no login required.
Edit SRT subtitle files in your browser. Fix wrong words, shift every timecode to resync drifted captions, stretch timing for frame-rate changes, and re-download.
Translate SRT and VTT subtitle files into 90+ languages with every timecode preserved. Upload, pick a language, download a ready-to-use subtitle file.