sqwartHome

Auto Subtitle Generator

Make SRT and VTT subtitles from any video or audio with Whisper AI, on your own device.

  • Free
  • No upload
  • No watermark
  • No sign-up
  • AI runs on your device
How it works

How to use the auto subtitle generator

  1. 1

    Choose a video or audio file.

  2. 2

    Set the language, the model, and how long each subtitle line may be.

  3. 3

    Press Generate subtitles and check the timed lines as they appear.

  4. 4

    Download SRT for YouTube, Premiere, CapCut or VLC, or VTT for the web.

In detail

Subtitles that are easy to read

Whisper writes text in phrases with start and end times. This tool turns those phrases into subtitles that follow common broadcast practice: at most 42 characters per line (or 32, which suits vertical Shorts and Reels), one or two lines per subtitle, lines broken where they come out most even, and no subtitle overlapping the next. A phrase too long for one subtitle is split at a word and its time shared in proportion to the words, so the text stays close to the speech.

SRT is the format almost every editor and player accepts: YouTube Studio, Premiere Pro, DaVinci Resolve, Final Cut (via import), CapCut desktop and VLC. VTT is the web's own subtitle format, for the HTML video player and many course platforms.

How it works on your device

The tool runs Whisper, the open speech recognition model OpenAI trained on 680,000 hours of audio, inside your browser. Your file is decoded to 16 kHz mono audio on your computer, cut at quiet moments into pieces shorter than 30 seconds (Whisper's listening window), and each piece is written out with start and end times. Text appears as each piece finishes, so you can read along while it works.

Nothing is uploaded: the audio never leaves the tab. The first time, your browser downloads the model from Hugging Face (64 MB for Fast, 136 MB for Balanced, 250 MB for Accurate on a processor; a little more on a graphics card) and keeps it, so the next file starts at once. Where your browser has WebGPU (recent Chrome and Edge on most laptops and desktops) the model runs on the graphics card; everywhere else it runs on the processor with WebAssembly, which is slower but works.

Accuracy, speed and limits

  • Fast (Whisper tiny) suits clear English speech; Balanced (base) is a good default; Accurate (small) is the one to use for accents, noisy rooms and for Hindi, Tamil, Bengali and other Indian languages, where the smaller models make many mistakes.
  • On a typical laptop processor, Balanced transcribes a 10-minute file in roughly 3 to 5 minutes; Accurate takes about as long as the audio. With WebGPU it is usually several times faster.
  • Whisper understands about 99 languages. You can pick the language or let it guess from the first words; picking it is more reliable, especially for mixed Hindi and English.
  • It does not tell speakers apart, and it can mishear names, numbers and jargon. Read the text through before you publish it.
  • Very long files need memory: about 60 MB per hour of audio for the samples, plus the model. Phones may run out of memory on long recordings; a laptop is the safer choice.
FAQ

Questions, answered.

Is it really free, with no limit on minutes?

Yes. The model runs on your own device, so it costs us nothing per minute and there is no sign-up, watermark or daily cap. The only limit is your device's memory and patience on very long files.

Is my audio uploaded anywhere?

No. The file is read and transcribed inside your browser tab. The only download is the Whisper model itself, from Hugging Face, the first time you use it.

Which languages does it support?

Whisper was trained on about 99 languages, including English, Hindi, Urdu, Bengali, Tamil, Telugu, Marathi, Spanish, French, German, Arabic, Japanese and Chinese. Accuracy is best in English and the major European languages; for Indian languages choose the Accurate model.

Are the timings exact to the word?

Each subtitle is timed from Whisper's phrase timestamps, which are usually within a fraction of a second. Long phrases split into several subtitles share their time by word count, so the split points are close but not word-perfect.

Can I burn the subtitles into the video?

This tool makes the subtitle file. Sqwart's caption editor puts styled, word-timed captions on the video itself, with animated styles made for Shorts and Reels.

Can I make English subtitles for a Hindi video?

Yes. Turn on Translate to English and Whisper writes English subtitles for speech in Hindi or any language it knows. For other target languages, translate the SRT with the subtitle translator.

Keep going

More free subtitles & text tools