> For the complete documentation index, see [llms.txt](https://learn.firecut.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://learn.firecut.ai/features/add-zooms.md).

# Add zooms

## ❓ What is it?

Videos made with a single-camera setup can seem boring and monotonous. Adding zoom-in at key moments in the video is a popular way of adding some motion to this setup.

This FireCut feature uses AI to figure out these key moments in your video, and adds zooms automatically using [Adjustment Layers](https://www.softwarehow.com/add-adjustment-layer-adobe-premiere-pro/), on a new video track by default. It can also zoom in on every other cut or every other sentence instead.

## 🤔 How does it work?

With **Key phrases** (the default trigger), this feature works by:

* Breaking your sequence (or the selected scope if using In / Out points) into smaller chunks for processing
* Analysing these chunks one at a time for key moments based on what is being spoken
* For each chunk, adding one or more zoom-in Adjustment Layer clips
* Lining zooms up with nearby cuts in your sequence, and merging zooms that overlap
* Showing your transcript with the zooms highlighted, so you can adjust them (see [Editing your zooms](#editing-your-zooms))

With **Every other cut**, FireCut zooms into every other clip on the track you pick. With **Every other sentence**, it transcribes your audio and zooms into every other sentence.

FireCut saves an undo point before it adds zooms, so the **Undo** button at the top of FireCut takes your sequence back to how it was.

{% embed url="<https://www.youtube.com/watch?v=zwawmaUAIlA>" %}

## ⚙️ Settings

There are 8 main settings for adding zooms:

1. **Zooms trigger:** When to add zooms. This is in beta.
   * **Key phrases (default):** Zooms in when the speaker is saying something important, based on what is being spoken
   * **Every other cut:** Zooms into every other clip on the track you pick as the **Guidance video track**. This is handy for hiding jump cuts after you've cut out silences or takes
   * **Every other sentence:** Zooms into every other sentence being spoken
2. **Zoom frequency:** How often FireCut should add a zoom, on a scale from **Low (less frequent)** to **High (very frequent)**. This is only for **Key phrases**.
   * The low end is for slow-paced (typically long-form) content, and will add \~1 zoom per minute of video
   * The middle (default) will add \~2 zooms per minute of video
   * The high end is for fast-paced (typically short-form) content, and will add \~7 zooms per minute of video
3. **Zoom duration:** Roughly how long each zoom lasts, as a range of words (1 to 20). It's approximate, not a hard limit. Leave it on **Auto** to let **Zoom frequency** decide, or narrow the range for shorter or longer zooms. This is in beta, and only for **Key phrases**.
4. **Zoom style:** What the zooms look and feel like. The panel shows a frame from your sequence with a box where the zoom will land, and you can drag the box to move it.
   * **Scale:** How far in to zoom, from 100% to 300%. This works exactly like the Scale property on any video, where 100 is 1x size (or no scaling), and 200 is 2x size. **A good starting point is 120** (the default)
   * **Center X / Center Y:** Where in the frame to zoom in to. The default is the centre of the frame (50% and 50%)
   * **Use face detection:** When this is on, FireCut looks for the speaker's face for each zoom and zooms in on it. If no face is found, it uses **Center X / Center Y**. It's designed for single-person shots: if there are several faces, it uses the most prominent one. It's off by default
   * **Zoom curve:** How the zoom moves. The left side of the curve is the zoom in, the right side is the zoom out. Click a side to pick its shape: the left-most shape is a sharp cut with no animation, the next is a straight line, and the ones further right ease in and out more smoothly. Drag a side's edge to set how long it takes, from 0.1 to 1.5 sec (the default is 0.5 sec each way). You can also start from a preset: **Sharp cut**, **Smooth in, sharp out** or **Smooth in, ramp out**
5. **Extend duration for animation:** When this is on, the zoom in starts before the key phrase and the zoom out ends after it, so you're fully zoomed in the whole time the phrase is spoken. When it's off (the default), the animation happens inside the phrase, and a zoom too short for its animation is left out. It isn't available for **Every other cut**.
6. **Scope:** You can decide whether to run the operation on your **Full sequence** or only on a certain portion that you specify with **In/Out points** (you can place these in your sequence using the `I` and `O` hotkeys)
7. **Target video track:** The track the zoom clips go on. The default is **Add new track**, which adds a new video track at the top of your sequence. If you pick an existing track, FireCut deletes the clips on it where the zooms go, so it warns you first.
8. **Language:** We are constantly adding support for new languages. However, please note this is experimental and may create unpredictable results when compared with English. This is the case for every AI tool even if they don't mention it, because [training sets for AI tend to be in English](https://www.wired.com/story/chatgpt-non-english-languages-ai-revolution/). On occasion, this might cause the operation to fail. Please do let us know (<support@firecut.ai>) if this happens, so we can improve it for you!

## ⚒️ Editing your zooms

When FireCut has added your zooms with **Key phrases** or **Every other sentence**, it shows your transcript with each zoom highlighted in yellow. Changes you make here go straight to the zoom clips in your sequence.

* **Change when a zoom starts or ends:** Drag the handles at either end of its highlight
* **Add a zoom:** Select some words in the transcript, then click **Add new zoom**
* **Delete a zoom:** Click its highlight, then click **Delete**
* **Change one zoom's style:** Click its highlight, then click **Edit Zoom**. Change its **Scale**, where it zooms in to, and its **Zoom curve**, then click **Save**

Clicking a highlight also sets In / Out points around that zoom in your sequence, so you can find it easily.

You can also move, trim or delete the zoom clips directly in your sequence. **Every other cut** doesn't open the editor, so change those zoom clips in your sequence.

## 💡 Tips for best outcomes

* **Try your settings on a small portion of your sequence** before processing hours of footage
* **Be mindful of usage**, as this feature counts towards your AI quota
* **Remove any repetitions** / multiple takes in your video first
* **Ensure your audio is clear and loud**
* **Mute any tracks with music** / sound effects that might obscure the sound of the speaker
* **Don't work in the timeline** while FireCut is working in the background

## 🙋‍♂️ Common questions, issues, watch-outs

* **"I can't see the zoom clips / Adjustment Layers"** --> By default these are added to a new video track at the top of your sequence. This can often be hidden at the top of your sequence, so try scrolling up to make sure it's not hiding from you! If you picked a track in **Target video track**, they're on that track.
* **"Some of my clips disappeared from a track"** --> If you pick an existing track in **Target video track**, FireCut deletes the clips on it where the zooms go (it warns you first). Click **Undo** at the top of FireCut to bring them back, and choose **Add new track** next time.
* **"It didn't work on my non-English video"** --> Please drop a note at <support@firecut.ai>. We are keen to make sure this feature works reliably on all supported languages!
* **"The zooms were not placed at sensible points"** --> Make sure you have a clear, single speaker in the audio so that your script can be picked up and analysed. If there are any sound effects, multiple speakers, music, noise, etc., this can throw off the analysis on some occasions.
* **"Could not add zooms because no clear transcript could be made for this chunk"** --> FireCut needs at least 20 clearly spoken words in each chunk to find key phrases. Make sure your audio is loud and clear, with any music / sound effects muted.
* **"Not enough cuts could be found in the guidance video track"** --> With **Every other cut**, pick the track that has your cuts as the **Guidance video track**. If you're using **In/Out points**, only clips that sit fully between them count.
* **"Please select a valid scope for the zooms"** --> You chose **In/Out points**, but your sequence needs both an In point and an Out point, with the Out point after the In point. Set them with the `I` and `O` hotkeys, or choose **Full sequence**.
