Tools › On-device AI

Auto subtitles and speech to text

Generate subtitles automatically with OpenAI’s Whisper in your browser: fix any line, then download SRT, VTT or TXT or burn them into the video. No upload.

The speech model downloads once to your device; your recording never leaves it. Nothing starts until you choose a file.

Model

Turn speech into timed captions

Whisper listens to a recording and proposes caption lines with start and end times. Because recognition runs in the browser, there is no transfer to a transcription server. Review the draft alongside the picture. A line can contain the right words and still need a timing change when a speaker stops or the shot changes.

How it works

  1. Drop a video or audio file, then select the spoken language or leave detection on.
  2. Choose Fast or Accurate and enable Translate to English if you want captions in English from another spoken language.
  3. Start recognition and review the draft when it is ready. Correct names, wording and timestamps against playback.
  4. Download SRT, VTT or TXT, or open the subtitle burner to put the caption lines into the picture.

Edit captions for the way people watch

On a software demo, check that the name of a menu appears while the menu is on screen. For a workshop, fix specialist terms and break up long lines so viewers can read them while following the speaker’s hands. Play through introductions and exchanges between speakers, where the first word of a line is especially easy to miss.

Pick a caption file or a video with subtitles

Export SRT for editors and players that accept an accompanying subtitle file, VTT for web players, or TXT for a copy of the words. To make the lines part of the picture, open the subtitle burner from the result. Caption translation has one target, English. Free accepts files up to 3 GB each. The Pro size cap is lifted on the device where you sign in. Model speed depends on the hardware and the recording.

Your recording stays on your device

The first time you choose a Whisper model, the browser downloads its files and can reuse the cached copy. The browser reads the sound and builds the cues locally. Your recording stays off Nibbo’s server.

Questions

How do I generate subtitles for a video for free?

Drop the video on Nibbo auto subtitles. Whisper listens on your device and writes timed lines; fix any word, then download SRT, VTT or TXT. Free, no account, nothing uploaded.

Can it translate the subtitles?

Into English, yes: choose Translate to English and speech in any of Whisper’s 99 languages becomes English subtitles. Other target languages are not offered.

How do I put the subtitles on a TikTok or Reels video?

Press Burn into the video: the subtitle burner opens with your lines and video loaded. To make it vertical, use reframe video.

Is my video uploaded?

No. The speech model downloads once from Hugging Face and is stored on your device; your file never leaves this tab.

How big is the download?

Fast is about 41 MB and Accurate about 77 MB without WebGPU. With WebGPU the graphics-card builds are about 120 MB and 206 MB. Both stay cached for next time.

How long does it take?

With WebGPU it is usually much faster than the recording plays. On a processor, Fast needs about half the length of the recording and Accurate about the full length, plus the one-time download.

Which model is used?

Whisper tiny (Fast) and Whisper base (Accurate) by OpenAI, released under the MIT licence, in the ONNX builds published by Hugging Face. You can use the subtitles commercially.

Can I put the subtitles on my video?

Yes. Burn into the video opens the subtitle burner with your lines and your video already loaded, ready to style and export.