Subtitles & Text

Klipeo handles two kinds of words on screen: subtitles, which come from what's said, and text, which is anything you type.

Subtitles

Vibe can generate captions from either an audio track or the audio in a video track; detaching the video's audio first is not required.

Open the Captions tile on the rail and its Content tab. An empty panel has one button, Generate subtitles. It transcribes the clip with live progress and a cancel, and lays down a cue per line, timed to the speech. If there's nothing to hear you'll get a plain "No speech detected in the clip."

Transcription runs as a background job. Closing the panel or refreshing stops the local wait, not the provider job. Generate again for the same clip in the same tab to retrieve the saved request without submitting it again. Recovered captions are not automatically applied to a changed timeline. If upload metadata is still being prepared, the request waits for it before starting transcription.

You don't have to start there, though:

• Add cue at playhead drops an empty cue at the playhead.
• Import SRT brings in subtitles you already have.
• Export SRT takes them back out.

The cue list follows playback. The cue under the playhead is highlighted and the list scrolls to keep it in view. Click a cue to seek to it, edit its text in place, and set its start and end (cues stay at least 0.1 s long). Each cue's menu can Split cue at cursor, Merge with next cue, or Delete cue. Regenerate from audio sits in the panel menu behind a confirmation, since it replaces every cue.

The Style tab styles the whole set. Start from a preset, TikTok, MrBeast, Hormozi, Minimal, or Terminal, then adjust font size, position (Top, Center, or Bottom), alignment, the text, outline, and backdrop colour swatches, and backdrop opacity. Turn Highlight words on and each word lights up as it's spoken.

Prefer to ask? Vibe does this in one line:

Caption the whole video, big and centered.

When Vibe styles captions, it looks at your footage first and fits the preset to it. It picks a font for the video's tone, takes the highlight colour from something already in frame, adds a backdrop where the background is bright or busy, and keeps the words off faces and products. Ask for a specific font or colour and it uses that instead.

Translation

The Translation view offers two modes, Captions and Voice clone. The language picker lists Detect plus 53 languages.

Text and titles

The Text tab is for everything you type: titles, lower thirds, callouts, end cards. It ships with dozens of ready-made presets, and a Style dropdown narrows them to All, Viral, Headlines, Subtitles, or Broadcast. Drag one onto the timeline and it lands on a text track as a clip you can move and resize in time.

Style it in the properties panel: font, size, weight, color, alignment, spacing, line height, and an optional background with its own color, padding, and corner radius. Below that you'll find an Entrance animation picker and a drop-shadow toggle with its own color and blur. The font picker includes 17 additional display and multilingual faces for text inside your video. They do not change the Klipeo interface typography.

Style one piece of text the way you like, then ask Vibe to bring the rest in line:

Make all the titles match this one.