Video tools, organized by task.

Browse available tools for conversion, compression, editing, resizing, GIFs, frames, subtitles and video information.

Available video tools

Search by format or task, or jump to a category.

Convert.

Change format or codec. MP4, WebM, MOV, MKV and AVI, with H.264, H.265, VP9 and AV1.

Compress.

Make a video smaller by quality, or hit an exact size for email and chat.

Edit.

Trim, cut out sections, split, join, change speed, fade and swap the sound.

Resize & optimise.

Resize, crop, rotate, flip, change frame rate, reframe for vertical and remove metadata.

GIF tools.

Turn clips into GIFs, GIFs into video, and shrink heavy GIFs.

Thumbnails & frames.

Save a still, a set of thumbnails, a contact sheet, a storyboard or one frame per scene.

Subtitles.

Extract, add, burn in, sync and convert subtitles. No speech recognition is used.

Video information.

See exactly what is in a video, whether it will play, and whether it is damaged.

AI video ideas

Planned — not available yet. These ideas are on the roadmap. If built, each tool will say whether it works from speech, visuals, or both, and label machine-generated results.

  • Transcription

    From speech

    A timed transcript of what is said, exportable as subtitles.

    Machine-generated from the audio. It can contain errors, so check it before you rely on it.

  • Subtitle translation

    From speech

    Translate an existing subtitle file into another language.

    Machine-translated from the subtitle text only.

  • Spoken-content summary

    From speech

    A short summary of what is said in the video.

    Summarises the transcript only. It does not describe what is shown on screen.

  • Chapters and key moments

    From speech

    Suggested chapter titles and timestamps from the transcript.

    Suggested from the spoken words only. Visual scene changes are not used.

  • Clip finder

    From speech

    Find moments where a topic is spoken about, then save them as clips.

    Searches the transcript. It will not find moments that are only visible.

  • Visual description and Q&A

    From visuals

    Answer questions about what appears on screen, using sampled frames.

    Based on a limited set of sampled frames, not the whole video. It can miss things between frames.

  • Smart reframing

    From visuals

    Follow the subject when cropping to vertical or square.

    Subject tracking is a best guess and may need manual correction.

  • Auto-captions with styling

    From speech

    Burned-in animated captions from the transcript.

    Captions are machine-generated and may contain errors.