> For the complete documentation index, see [llms.txt](https://monkey-gun.gitbook.io/monkeygun/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://monkey-gun.gitbook.io/monkeygun/use-cases/footage-to-video.md).

# Footage to video

Dump in what you already shot. Lightning Cut indexes it, finds the moments, and cuts videos from your footage instead of generating pictures.

[![A karaoke venue's own phone footage, indexed once, cut into a 15-ad campaign (Micdrop, a Lightning Cut customer).](https://lightningcut.com/deck/micdrop.jpg)](https://lightningcut.com/deck/v-micdrop-datenight.mp4)

{% embed url="<https://lightningcut.com/deck/v-micdrop-datenight.mp4>" %}
A karaoke venue's own phone footage, indexed once, cut into a 15-ad campaign (Micdrop, a Lightning Cut customer).
{% endembed %}

## 1. Get the files in

{% tabs %}
{% tab title="By URL" %}

```bash
curl -X POST https://api.monkeygun.com/v1/library/upload -H "Authorization: Bearer $MK_KEY" \
  -d '{ "url": "https://cdn.yourapp.com/shoot/clip-01.mp4", "filename": "clip-01.mp4" }'
# { "assetId": "778324edbbef508c", ... }
```

Any public https file, or a post on X, YouTube, TikTok or Instagram. 250 MB per file.
{% endtab %}

{% tab title="Google Drive" %}

```bash
curl -X POST https://api.monkeygun.com/v1/tools/import_drive -H "Authorization: Bearer $MK_KEY" \
  -d '{ "url": "https://drive.google.com/drive/folders/…" }'          # lists files
curl -X POST https://api.monkeygun.com/v1/tools/import_drive -H "Authorization: Bearer $MK_KEY" \
  -d '{ "url": "https://drive.google.com/drive/folders/…", "all": true }'   # imports them
```

The folder must be shared to anyone with the link.
{% endtab %}

{% tab title="Base64" %}
`{ "filename": "clip.mp4", "data": "<base64>" }` on the same upload endpoint.
{% endtab %}
{% endtabs %}

## 2. Index it (once)

```bash
curl -X POST https://api.monkeygun.com/v1/tools/index_footage -H "Authorization: Bearer $MK_KEY" \
  -d '{ "assetIds": ["778324edbbef508c"], "quoteOnly": false }'
```

20 credits per minute of footage. Indexing finds scene cuts, describes every scene, and transcribes the speech, so the director can cut from it by content ("the shot of the crowd", "where she says the price"). `quoteOnly: true` prices it first.

For footage without speech (gameplay, b-roll, events, music), `find_highlights` (5 credits per minute) returns the moments: loudness peaks, cuts, and a one-line look at each, with start and end times.

For talking-head clips, `clean_footage` (10 credits per minute) drops filler words and dead air with clean cut edges, and lands a new clip in the library.

## 3. Cut from it

```bash
curl -X POST https://api.monkeygun.com/v1/videos/from-data -H "Authorization: Bearer $MK_KEY" \
  -d '{ "brief": "A 20-second ad for date night at the venue. Use the crowd shots and the duet; end on the booking CTA.",
        "cta": "Book at micdrop.com", "libraryAssetIds": ["778324edbbef508c", "1025aba083607904"],
        "format": "9:16", "targetSeconds": 20, "images": "library", "brand": { "pack": "bold" } }'
```

`images: "library"` tells the engine to place your files rather than stills or generated images. The director sets `clipRef: { assetId, start, duration }` on scenes to pick the exact seconds. In an authored script you set `clipRef` yourself. An audio file in `libraryAssetIds` becomes the music bed.

## Batches from one shoot

Index once, then call `from-data` once per angle with a different brief. There is nothing to batch server-side; each call is independent and the footage index is reused. A 15-ad campaign from one shoot is 15 calls.

## Your users' footage

In the [embedded studio](/monkeygun/guides/embedded-studio.md), users drop their own files in the chat and the same indexing runs on your account's credits. Uploads that go straight to a feed should pass through a [brand pass and a review hold](/monkeygun/guides/upload-and-brand-pass.md).


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://monkey-gun.gitbook.io/monkeygun/use-cases/footage-to-video.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.