All tools · AI, Video

AI Subtitle Generator Beta

Upload a video or audio file and get accurately-timed subtitles, generated automatically by AI speech-to-text. Transcription runs server-side via an AI API — see the FAQ below for why.

Click to choose a file or drag audio/video here

Supports .mp3, .wav, .m4a, .aac, .ogg, .flac, .webm, .mp4, .mov, .mkv

Like the other AI-powered tools here, this one works differently from the rest of the site: your uploaded audio/video is sent to our server, which relays it to a speech-to-text API to transcribe it, then returns the result. Nothing is stored afterward — see the FAQ below for the full disclosure. Speech-to-text isn't perfect, so it's worth reviewing the result, especially names or jargon. Up to 200MB per file.

How it works

  1. Upload an audio or video file (.mp3, .wav, .m4a, .aac, .ogg, .flac, .webm, .mp4, .mov, .mkv).
  2. Wait while an AI speech-to-text model transcribes it — this can take a bit longer than the other AI tools, especially for longer files.
  3. Review the generated captions, then download them as .srt or .vtt.
  4. Want them burned into the video itself? Open the downloaded .srt in Add Subtitles to Video to fine-tune timing and burn it in.

Frequently asked questions

Does this run in my browser like the other tools here?

No — like AI Summarizer, AI Rewriter, and AI Translator, this tool genuinely needs a real AI model, so your uploaded file is sent to our server, which relays the audio to a speech-to-text API to transcribe it, then returns the result. It is not saved or logged anywhere afterward.

Why does this take longer than the other AI tools?

Transcribing audio takes real processing time proportional to the file's length, unlike a quick text request — a few minutes of audio typically finishes in well under a minute, but longer files can take a couple of minutes.

What file types can I upload?

Common audio formats (.mp3, .wav, .m4a, .aac, .ogg, .flac) and video formats (.webm, .mp4, .mov, .mkv) — the audio track is transcribed automatically from video files, no need to extract it yourself first.

What languages are supported?

The source language is auto-detected by default, and a wide range of languages are supported for transcription.

What do I get back?

A downloadable .srt and .vtt subtitle file with accurately-timed captions, plus a plain-text transcript. Since speech-to-text isn't perfect, it's worth reviewing the result before using it — especially for names, jargon, or noisy audio.

Is there a file size limit?

Yes — up to 200MB per upload.

Your files are never uploaded. Gotool.xyz runs entirely as JavaScript in your browser. Your files are processed in memory and never touch a server — nothing to breach, nothing to clean up. Close the tab and it's like it never happened. The only thing we count is which tool ran (just the name, e.g. "merge") so we know what people find useful — never your file, its name, its size, or anything in it.