---
title: Cut, join, caption and convert video with the video tools
display: 'Cut, join, caption and convert *video* with the video tools'
thumb: video/video-tools/thumb.webp
nav_title: Video tools
summary:
  - "The video tools do exact jobs on videos you already have: join, caption, cut, resize and convert, the same way every time."
  - "Find them under Models › Tools, or in Create's model library under Capabilities › Tools. Each run makes a new file and leaves your original as it is."
  - "Join clips with Scenario Video Concat, pull frames with Video to Image Sequence, and add styled captions with Scenario Caption Studio."
description: "The video tools that do exact, repeatable jobs: join clips, pull frames, caption, cut and split, resize, extract audio and transcripts, key out a green screen and split a video into layers."
section: video
order: 100
type: guide
level: Build
roles: [all]
time: { read: 9, do: 10 }
needs: ["A video asset in your library"]
last_verified: 2026-11-12
models_checked: ["Scenario Video Concat", "Video to Image Sequence", "Scenario Caption Studio", "Video Cut", "Video Split", "Reverse Video", "Scenario Resize Video", "Auto Subtitles", "Audio Extract", "Speech to Text", "Audio to Text", "Sequence-to-Video", "Smart Clip Extraction", "Scenario Video to Mask", "Scenario Video Studio", "Video Chroma Key", "Video to Layers", "SAM 3.1 Video", "Pixelcut Video Background Removal"]
video: tutorials/video-tools.mp4
video_caption: Use the video tools
about: "Joining two clips, pulling out a frame or burning in captions should give the same result every time. The video tools do that: they join, caption, cut, resize and convert videos you already have, without generating anything new. This guide shows where they live, walks through three of them with one example each, and lists the settings that matter for every tool. The models and prices in this lesson are as of November 2026."
chapters:
  - { at: 0, title: "Find", image: "/media/images/video/video-tools/ch-01-find.webp" }
  - { at: 31.71, title: "Join", image: "/media/images/video/video-tools/ch-02-join.webp" }
  - { at: 54.48, title: "Frames", image: "/media/images/video/video-tools/ch-03-frames.webp" }
  - { at: 75.8, title: "Captions", image: "/media/images/video/video-tools/ch-04-captions.webp" }
related: [edit-video, upscale-and-finish-video, transcribe-and-subtitle, build-a-sequence-of-shots, batches-loops-and-logic, nodes-reference]
steps:
  - title: "Find the tools"
    text: "Open Models and choose the last tab, Tools, to list every tool. In Create › Videos, click the Model card › View all models and tick Tools under Capabilities: the tools that return a video. The ones that return images, audio or text (Video to Image Sequence, Audio Extract, Speech to Text) show after Clear filters."
  - title: "Join two clips"
    text: "Pick Scenario Video Concat and add the clips under Videos in the order they play: here the kitchen clip, then the park clip. Under Transitions, pick a Type (Fade here) and set its Duration (1 second), then click Generate. It cost 2 credits, and the 15- and 5-second clips came back as one 19-second clip, since the fade overlaps them."
  - title: "Pull frames from a clip"
    text: "Clear the library's filters and pick Video to Image Sequence (Create switches to Images), with the park clip under Video. Extract All Frames saves every frame; Frame Interval keeps one in every few instead (24 is one per second at 24 fps). Here it returned six frames, the last one included: use it as the first frame of your next shot."
  - title: "Add captions"
    text: "Pick Scenario Caption Studio and load the video under Input Video: it transcribes the speech for you. Set Style Preset (TikTok Bouncy here) and Max Words Per Caption (3), and Target Language to translate. Turn on Output SRT to get the captions as a file too. It cost 8 credits for the 7-second selfie clip."
  - title: "Make it repeatable"
    text: "Put the tools you repeat into a workflow around the paid steps: Video Cut before the paid edit, upscale or lip sync, then Caption Studio after the final cut and one Resize Video run per delivery format."
agent_steps:
  - title: "Connect the Scenario MCP"
    text: "Connect your agent and sign in once at [mcp.scenario.com](https://mcp.scenario.com). Then tell it which Scenario team and project to use, so every file lands there."
  - title: "Give the agent the clips"
    text: "The clips to join, in the order they play, and the clip to caption, with its speech. Upload them with upload_asset or give their asset IDs."
  - title: "Brief the agent"
    prompt: |-
      Run these video tools, reading model_schema_get for each one's parameter names first. 1. Scenario Video Concat (model_scenario-video-concat): join my two clips in this order with a 1-second fade, MP4, keep the audio. 2. Video to Image Sequence (model_scenario-video-to-image-seq) on the second clip with Extract All Frames on, and give me the last frame's asset ID. 3. Scenario Caption Studio (model_scenario-caption-studio) on the talking clip: style preset tiktok-bouncy, at most 3 words per caption, the transcription hint "Scenario", and an SRT file too. Quote the cost with a dry run first and wait for my go.
  - title: "Check and redo"
    text: "Accept when the joined clip plays in order with the fade and the sound, the last frame is the clip's real last frame, and the captions match the speech, word for word and in time. Reject a missing transition, captions that drift or misspell a name, or captions too small for a vertical video: raise the font size and lower the words per caption."
    prompt: |-
      Wait for the jobs with jobs_wait. Report the joined clip's duration and whether it has audio, how many frames came back and which one is last, and the caption text from the SRT. Show me the captioned clip.
  - title: "File and report"
    prompt: |-
      Create a collection with the source clips, the joined clip, the last frame and the captioned clip, and report the tools, the settings and every asset ID.
updated: 2026-11-12
canonical: https://learn.scenario.com/video/video-tools
---

Last updated: 2026-11-12

# Cut, join, caption and convert video with the video tools

> The video tools that do exact, repeatable jobs: join clips, pull frames, caption, cut and split, resize, extract audio and transcripts, key out a green screen and split a video into layers.

In short:

- The video tools do exact jobs on videos you already have: join, caption, cut, resize and convert, the same way every time.
- Find them under Models › Tools, or in Create's model library under Capabilities › Tools. Each run makes a new file and leaves your original as it is.
- Join clips with Scenario Video Concat, pull frames with Video to Image Sequence, and add styled captions with Scenario Caption Studio.


Joining two clips, pulling out a frame or burning in captions should give the same result every time. The video tools do that: they join, caption, cut, resize and convert videos you already have, without generating anything new. This guide shows where they live, walks through three of them with one example each, and lists the settings that matter for every tool.

:::note As of November 2026
The models, settings and prices in this article are the ones Scenario offered in November 2026. New models and updates arrive often, so check the model library for newer options before you choose.
:::

:::steps Quick version
1. Find the tools under **Models** › **Tools**, or in the model library of **Create** › **Videos** under **Capabilities** › **Tools**.
2. Load the video and set the few settings the tool has (times, sizes, formats, a style).
3. Run it. Each run makes a new file and leaves your original as it is.
4. Check the output's duration, size, format and audio before you use it.
5. Put the tools you repeat into a workflow, around the paid steps.
:::

## Before you start

- **What a video tool is.** A model that does an exact job with settings you give it: a start and end time, a width and height, a transition, a caption style. It doesn't read a prompt and doesn't invent pixels, so the same settings give the same result every time.
- **Your original is never changed.** Every run makes a new file. You can always go back to the source and try other settings.
- **They cost a few credits.** The price shows on **Generate** before you run one: joining two clips cost 2 credits, captioning a 7-second clip 8.
- **Times are in seconds.** 1:30 to 2:15 is 90 to 135.
- **You need a video** in your library: one you generated, or one you uploaded.

## Step 1: Find the tools

Open **Models** in the top menu and choose the last tab, **Tools**. It lists every tool, with **Category**, **Capabilities**, **Tags** and **Enterprise Status** filters.

![The Model Hub on the Tools tab, with Platform and Project tabs and filters for Category, Capabilities, Tags and Enterprise Status](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/4e4516a4d403d26b1c13ad30f9f919f712e2dfe5cb6f490407f4526a0577f670.webp "Models › Tools lists every tool.")

The tools run straight from **Create**, not only in workflows. In **Create** › **Videos**, click the **Model** card, then **View all models**, and tick **Tools** under **Capabilities**: the list shows the tools that return a video, with their typical time and cost.

![The model library with Tools ticked under Capabilities: Video Chroma Key, Video Split, Video Cut, Scenario Video Concat, Sequence-to-Video, Scenario Resize Video, Reverse Video, Scenario Video Studio and Smart Clip Extraction](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/9fcfba0e5c1009645b181c72f3794e6679de56ffa18b12bf2776177faafa924a.webp)

Tools that return images, audio or text are filtered out of the video library: **Video to Image Sequence**, **Audio Extract** and **Speech to Text**. Click **Clear filters**, or search for the tool by name, to find them. Most tools also work as nodes in **Workflows** (Step 5).

## Step 2: Join two clips

**Scenario Video Concat** joins 2 to 50 clips in the order you add them.

1. Pick **Scenario Video Concat** in the library.
2. Under **Videos**, add the clips in the order they play. Here: the 15-second kitchen clip from [Write video prompts](https://learn.scenario.com/methods/prompt-video.md), then a 5-second clip of the same girl and chameleon in a park.
3. Under **Transitions**, click **Add Transitions**, pick a **Type** and set its **Duration**, from 0.1 to 5 seconds. Add one transition per join: three clips take two.
4. Under **Settings**, **Preserve Audio** keeps each clip's sound, and **Output Format** gives MP4, MOV, WebM or GIF.
5. Click **Generate**.

![The Scenario Video Concat panel: the kitchen and park clips under Videos, Preserve Audio on, Output Format MP4, and one transition with Type fade and Duration 1](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/ba2147f8ea5ea64d96a88274acde61134290df7913bc2d2cbe0993beec905b17.webp)

There are 17 transitions besides a hard cut: fades (to black, to white), dissolve, wipes and slides in four directions, circle open and close, pixelize, radial and zoom in. Without a transition, the clips are joined with hard cuts.

![The joined clip across its 1-second fade: the kitchen, the two shots blended, then the park](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/0a196ec58b2ccce8bd628092e73bfbdfcc651f3d222b842e2fcbd5a92992b1e8.webp "Fade, 1 second: 2 credits. The 15- and 5-second clips came back as one 19-second clip, since the fade overlaps them.")

For titles over the picture, layered audio or more than a simple sequence, use **Scenario Video Studio** (see the table below).

## Step 3: Pull frames from a clip

**Video to Image Sequence** turns a clip into still images, for example to start the next shot from the last frame of this one.

1. Click **Clear filters** in the library and pick **Video to Image Sequence**. Create switches to **Images**, since the tool returns images.
2. Load the clip under **Video**.
3. Choose how many frames to keep: **Extract All Frames** saves every frame; **Frame Interval** keeps one frame in every few instead (24 by default, one per second at 24 fps).
4. Click **Generate** (2 credits here).

![Video to Image Sequence with the park clip under Video, Extract All Frames off and Frame Interval 24; the six frames it returned at the top of the session](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/c8e1bd2b6f2a81e2776848a054ceb58c897b02372f2d96bab06faa238a1c2fbd.webp "Frame Interval 24 on the 5-second park clip: six frames, the last one included.")

On this 5-second clip, Frame Interval 24 returned six frames, from the first to the last. On a clip of another length the last frame can fall between two intervals: turn on **Extract All Frames** when you need the very last one. Use it as the first frame of the next shot so the cut matches. See [Build a sequence of shots](https://learn.scenario.com/video/build-a-sequence-of-shots.md).

## Step 4: Add captions

**Scenario Caption Studio** transcribes the speech, can translate it into 18 languages, and renders the captions in a style you choose.

1. Pick **Scenario Caption Studio** and load the video under **Input Video**. It transcribes the speech for you.
2. Under **Style**, pick a **Style Preset**, or describe the look in plain words under **Style Prompt**.
3. Under **Segment Limits**, set **Max Words Per Caption**: 1 shows one word at a time, karaoke style.
4. Under **Translation**, set **Target Language** to translate the captions, or leave it on **Auto** to keep the spoken language.
5. Under **Output Settings**, turn on **Output SRT** to also get the captions as a file. **Output Subtitles** burns them into the picture (**Burn Into Video**) or adds a track viewers can switch on and off.
6. Click **Generate**.

![Caption Studio's Translation, Style and Segment Limits sections: Target Language Auto, Style Preset TikTok Bouncy, Max Words Per Caption 3](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/a8c49cd4c58dc09bd4aadaba63f1ae30811cb6fb0b63b5a9b5138fd7db9a42b2.webp)

![Caption Studio's Output Settings: Output Video on, Output SRT on, Output Subtitles Burn Into Video](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/b04a1d23c730e757d9f362690a4676af0573726c07d281e5e124e22666780c98.webp)

The example is a 7-second selfie clip made with Minimax H3, where she says one sentence. With the TikTok Bouncy preset, 3 words per caption, a font size of 110 px and "Scenario" as a hint under **Transcription Prompt**, the captions matched her words exactly. At the default size and length, they were too small for a vertical video.

![Four moments of the captioned selfie, with the captions Okay, my first video, with Scenario and, so](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/1bb43f26677f17e61182138817005e615eb0e1c51a93f85eeda4cd0097bd2bb4.webp "TikTok Bouncy, 3 words per caption, 110 px: 8 credits.")

Under **Layout**, set **Text Position**, **Font Size (px)**, **Max Lines** and **Text Width (%)** so captions don't cover the subject.

![Caption Studio's Layout section with Text Position, Font Size, Max Lines and Text Width](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/9d7a0bb185c0826224fbaa74f6a30367fe7f1abfb022b19d43a3d63a304641c7.webp)

### Your own text instead of the speech

Caption Studio doesn't have to listen to the audio. Under **Text Segments**, add a line with its **Start (s)** and **End (s)**, for a title or a hook over the clip. When text segments are set, it uses them and skips both the transcription and any **Subtitles (SRT)** file.

![Caption Studio's Text Segments section with one segment from 0 to 8 seconds](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/11bad26f425c5b3c9f6edac82400835d0119c6f249648ee87584c4eeb5e8c9eb.webp)

The segment's **Text**, as run:

```text
POV: your first boss fight
```

Full guide: [Transcribe and subtitle](https://learn.scenario.com/audio/transcribe-and-subtitle.md).

## All the video tools

| Job | Tool | Key settings |
| --- | --- | --- |
| Join clips | Scenario Video Concat | 2 to 50 clips; 17 transitions or a hard cut, 0.1 to 5 s each; keep audio; MP4, MOV, WebM or GIF |
| A clip to frames | Video to Image Sequence | Extract All Frames, or one frame in every N (Frame Interval, 24 by default) |
| Styled, translated captions | Scenario Caption Studio | 7 presets or a style prompt, 18 target languages, words per caption, your own SRT or text segments, burn-in or soft track |
| Burn in subtitles | Auto Subtitles | Font, colors, outline and shadow or a box; transcribes, and can translate to English only |
| Keep one section | Video Cut | Start and end time in seconds, frame-accurate; keep audio (on by default); MP4, MOV, WebM or GIF |
| Split into parts | Video Split | Cut points in seconds (N points give N+1 clips); keep audio; strict mode; MP4, MOV, WebM or GIF |
| Play backwards | Reverse Video | No settings; picture and sound reversed |
| Change size or format | Scenario Resize Video | Width, height, fit (contain, stretch, cover), maximum file size, frame rate 1 to 120, MP4, MOV, WebM or GIF, keep audio |
| Transcript and SRT | Speech to Text (Audio to Text) | Model size, language, transcribe or translate to English, voice activity filter |
| Pull out the soundtrack | Audio Extract | MP3, WAV or AAC; optional loudness normalization |
| Images to a clip | Sequence-to-Video | Frame rate 1 to 120, MP4 or GIF, compression, loop count, ping-pong, optional audio; up to 1,000 images |
| Best moments from long footage | Smart Clip Extraction | Clip length range, up to 200 clips, start and end time, scene threshold, quality filter |
| Remove a green or blue screen | Video Chroma Key | Key color, tolerance, softness, spill and edge; WebM or MOV with transparency, or MP4 over a color; clips up to 60 s |
| Split a clip into layers | Video to Layers | An instruction naming the subjects; each subject on its own layer plus a clean background, up to 10 layers |
| Cut out a subject | Pixelcut Video Background Removal, SAM 3.1 Video | Background removal with transparency; SAM 3.1 Video tracks the subjects you name and returns their masks |
| A grayscale mask from a clip | Scenario Video to Mask | Source channel, threshold 0 to 255, invert |
| Layer and compose | Scenario Video Studio | Up to 50 image, video and audio layers with position, scale, opacity, blend modes, masks, transitions; canvas size and frame rate |

The recipes below cover the other jobs that come up most.

### Trim before you pay for an edit

Edit, upscale, lip sync and translation models bill by input length. Cut the source first with **Video Cut**:

- **Start time** and **End time**, in seconds. The cut is frame-accurate.
- **Preserve audio** is on by default. Turn it off only for a silent clip: you can't get the audio back later without the source.
- **Output format**: MP4, MOV, WebM or GIF. Left empty, the source format is kept.

### Split a clip by scene

**Video Split** takes a list of **Cut points** in seconds, from earliest to latest. One cut point gives two clips; three give four. With **Strict mode** on, the run fails if the points are unsorted, duplicated or past the end of the clip; with it off, the tool fixes them for you. Leave it off when you work by hand.

A good order for long footage: split into rough sections with Video Split, then set the exact in and out points of each part with Video Cut.

### Play a clip backwards

**Reverse Video** has no settings. Picture and sound both play backwards, so speech and music sound reversed too. To reverse only part of a clip, cut it first. For a back-and-forth loop, place the original and the reversed copy one after the other. Splashes, smoke, falling objects and crowds read well in both directions.

### Make a vertical version

Run **Scenario Resize Video** with width 1080, height 1920 and **fit** set to cover. Fit only matters when you set both width and height:

| Fit | Result |
| --- | --- |
| cover | Fills the frame and crops the overflow from the center, with no way to shift the crop. For an off-center subject, use a generative reframe (Luma Video Reframe, see [Edit video](https://learn.scenario.com/video/edit-video.md)) |
| contain (default) | Keeps the whole frame and returns a smaller video, without bars. A 1280 x 720 clip in a 720 x 1280 box comes out at 720 x 406 |
| stretch | Forces the exact size and distorts the picture; rarely what you want |

Resize Video also changes the format (MP4, MOV, WebM or GIF), the frame rate (1 to 120) and can drop the audio, all in the same run. **maxSizeMb** shrinks the output until it fits under a file size, alone or with a width and height. It takes one video per run.

### Add simple subtitles

**Auto Subtitles** burns in captions in the spoken language, with few settings: font, colors, and an outline with a shadow or an opaque box. It can translate to English only; use Caption Studio for other languages. Keep the clean version: burned-in text is permanent.

### Get a transcript

**Speech to Text** returns a plain transcript and a timed SRT file. Set **Language** when you know it: auto-detect can drift on short or mixed clips. **Model size** goes from Tiny (fast) to Large-v3 (most accurate); Small or Medium suits most work. **Task** set to translate returns English only. An **initial prompt** with product names or unusual words helps the spelling.

### Pull out the soundtrack

**Audio Extract** saves the audio of a clip as MP3, WAV or AAC, with optional loudness normalization. It fails on a clip with no audio track; some generated clips are silent.

### Turn a sprite sequence into a preview

**Sequence-to-Video** takes ordered frames and returns an MP4 or a GIF. At 24 fps, 120 images make a 5-second clip. For a looping sprite preview, choose GIF, a low frame rate (8 to 12) and a loop count of 0 to loop forever. GIF has no audio and fewer colors, so use MP4 for anything else.

### Find the usable shots in long footage

**Smart Clip Extraction** detects cuts, drops static, shaky, blurry or duplicate shots, and returns the best ones as separate clips. **Start Time** and **End Time** skip an intro or the credits.

| Setting | Default (camera footage) | For AI-generated compilations |
| --- | --- | --- |
| Clip length | 5.5 s minimum, 14 s maximum | Default |
| Maximum clips | 20 (up to 200) | Default |
| Scene threshold | 27 | 12 to 18, so it catches the cuts |
| Filter strength | 1 | 0.25 to 0.4, so clean generated shots are kept |

### Key out a green screen

**Video Chroma Key** removes a green or blue background from clips up to 60 seconds. Set the key color, then **tolerance**, **softness**, **spill** and **edge** until the edges are clean. Export WebM or MOV to keep the transparency, or MP4 over a solid color.

### Make a mask from a clip

**Scenario Video to Mask** turns a clip's brightness into a grayscale mask clip. Leave **threshold** empty for soft tones, set it (0 to 255) for hard black and white, and turn on **invert** to swap light and dark. It reads brightness only: it doesn't track or cut out a subject. For that, use SAM 3.1 Video or Pixelcut Video Background Removal, or see [Edit video](https://learn.scenario.com/video/edit-video.md).

:::check
**Accept when:** durations, dimensions, frame rate and format match what you set, audio is there when you kept it, a transition sits where you put it, captions are in sync and spelled correctly, and your original is unchanged.
**Reject when:** a cut lands a frame early or late on an action, a resize cropped the subject, a GIF lost too many colors, or captions drift from the speech or are too small to read.
:::

## Step 5: Make it repeatable

The tools give the same result every time, so they make good workflow steps. A common chain: split, cut, then transcribe, each step making a new file while the source stays available.

:::flow Tools around the paid steps
Video Cut | trim before paying | video
Paid edit | edit, upscale, lip sync | video
Caption Studio | after the final cut | video
Resize Video | one run per delivery format | video
:::

Batch and loop nodes can run the same step on a list of clips. See [Batches, loops and logic](https://learn.scenario.com/workflows/batches-loops-and-logic.md).

## Common problems

| What you see | What to do |
| --- | --- |
| A tool isn't in the library | Tools that return images, audio or text are filtered out of the video library. Click Clear filters, or search by name |
| The joined clip is shorter than the clips added up | Each transition overlaps the two clips by its duration. Use a hard cut (Type none) to keep every frame |
| Captions too small on a vertical video | Raise Font Size (px) and lower Max Words Per Caption |
| A name is misspelled in the captions | Add it under Transcription Prompt and run again |
| The last frame is missing from the frames | Frame Interval skipped it. Turn on Extract All Frames |
| Cover cropped off the subject | Cover always crops from the center. Use a generative reframe, or reframe before you resize |
| Contain returned an odd size | Contain fits inside the box without bars. Check the output size; use cover or a reframe for the exact box |
| Fit made no difference | Set both width and height; with one, the aspect ratio is always kept |
| Video Split failed | Strict mode is on and a cut point is unsorted, repeated or past the end. Fix the list or turn strict mode off |
| Smart Clip Extraction returned zero clips | Lower the filter strength first, then the scene threshold. Very dark footage can be rejected even at the lowest setting |
| Audio Extract failed | The video has no audio track. Some generated clips are silent |
| Subtitles translated to the wrong language | Auto Subtitles and Speech to Text translate to English only. Use Scenario Caption Studio for other languages |
| Caption Studio showed the wrong text | Text Segments win over an SRT without an error. Remove the one you don't want |
| Reversed speech sounds wrong | Reverse Video reverses the audio too. Cut the part you need first, or drop the audio with Resize Video |
| A preview shows black where it should be transparent | The preview is MP4. Download the WebM or MOV file |

## What's next

Use the tools around the paid steps in [Edit video](https://learn.scenario.com/video/edit-video.md) and [Upscale and finalize video](https://learn.scenario.com/video/upscale-and-finish-video.md). To put a voice on a clip, go to [Lip sync and talking avatars](https://learn.scenario.com/video/lip-sync-and-talking-avatars.md); to join shots into a story, see [Build a sequence of shots](https://learn.scenario.com/video/build-a-sequence-of-shots.md).

Source: https://learn.scenario.com/video/video-tools