Video Reel

Combine multiple video clips into one seamless video with AI-picked transitions, narration, and background music.

Video Segments

Upload reference videos

Up to 10 short clips

Browse library

Narration Audio(optional)

Click to upload audio

or drag and drop

Browse library

Background Music(optional)

Click to upload audio

or drag and drop

Browse library

Output Aspect

Instructions(optional)

Still needed: Video Segments

Best for

•Final assembly of multiple video clips into one continuous video
•Adding narration and background music to video
•Applying transitions between segments (crossfade, dissolve, wipe, etc.)
•Always the LAST step in any video production pipeline

Tips

✓The AI picks transitions, speed, and color grading based on your instructions
✓Provide instructions like: 'cinematic crossfades, warm color grading, smooth transitions'
✓Mix segment types for engagement: AI-generated clips + text cards + stock footage
✓For best pacing, keep individual segments under 8 seconds each
✓Always provide both narration and music for narrated videos

Recipes using this pipeline

One prompt → a vertical AI dance reel

Generate a labeled dance-move grid with GPT Image 2, hand it to Seedance 2 Pro as a reference so the choreography actually follows the moves, then stitch it into a music-synced vertical reel.

6 pipelines · CLI

Articles about this pipeline

Video Reel API

Call this pipeline from your own code. One request dispatches a run; the model is an input field, not a separate endpoint.

5 inputs

1 required

1 credits

TypeScript Python Go CLI

bun add @pipe2-ai/sdk

import { createClient } from "@pipe2-ai/sdk";

const client = createClient(process.env.PIPE2_TOKEN!);

const { run_pipeline } = await client.RunPipeline({
  pipeline_slug: "video-reel",
  input: {
    video_urls: [],
  },
});

pip install pipe2

import asyncio
import os

from pipe2 import Pipe2Client

client = Pipe2Client(token=os.environ["PIPE2_TOKEN"])

run = asyncio.run(client.run_pipeline(
    pipeline_slug="video-reel",
    input={
        "video_urls": [],
    },
))

go get github.com/pipe2-ai/sdk-go

client := pipe2.NewClient(os.Getenv("PIPE2_TOKEN"))

input := json.RawMessage(`{
  "video_urls": []
}`)

run, err := pipe2.RunPipeline(context.Background(), client, "video-reel", input)
if err != nil {
    log.Fatal(err)
}

brew install pipe2-ai/tap/pipe2

pipe2 pipelines run \
  --pipeline video-reel \
  --input-json '{"video_urls": []}' \
  --wait

Get an API token →

Parameters

video_urls required: Public URLs of the clips to assemble, in order.

array
instructions: Optional hints for AI montage style

string
music_url: Public URL of a background music track. Leave unset for no music.

string

Show all 5 inputs

narration_url: Public URL of a narration track to lay over the reel.

string
target_aspect: Match the first video, or pick an explicit aspect

auto9:1616:91:14:54:3 default auto

Use it from an AI agent

Point any MCP client at pipe2 and your agent gets these tools. It finds this pipeline, reads the same schema above, then runs it.

list_pipelines
get_pipeline_schema
run_pipeline
get_pipeline_run_status
request_upload

https://mcp.pipe2.ai/mcp

{
  "mcpServers": {
    "pipe2ai": {
      "url": "https://mcp.pipe2.ai/mcp",
      "headers": { "Authorization": "Bearer YOUR_TOKEN" }
    }
  }
}

Full API reference MCP setup CLI reference

Frequently Asked Questions

How many segments can I combine?

1 to 10 segments. The final video length is the sum of all segment durations minus crossfade overlaps.

How does AI decide the transitions?

AI picks the transition type and its duration, from a 0s hard cut up to a 1.5s slow dissolve, based on your instructions and content type. Cinematic content gets slow dissolves, energetic content gets quick cuts.

Can I add audio?

Yes, optionally add narration audio and/or background music. Both get mixed into the final video.

How does the AI set music volume?

If narration is provided, AI keeps music soft (0.1-0.3). Without narration, music is more prominent (0.3-0.5). You can guide this with instructions.

Does this cost credits?

1 credit per reel.

Explore more pipelines

See all →

from 9.5

Video Generator →

Generate AI videos from a text prompt, image, or reference clip. Cinematic shots, product reveals, lifestyle ads, with synchronized audio and natural motion.

Veo 3.1 Seedance 2.0

0.2-6.4

Image Generator →

Generate AI images from text or reference photos. Product shots, character art, posters with readable text, photoreal portraits, high resolution in seconds.

Nano Banana 2 Nano Banana Pro GPT Image 2