Video Trim

From 0.1 credits

Trim a video to an exact start and end, snapping each cut to a sentence boundary from your SRT so clips never break mid-word. Returns the clip plus a matching transcript, ready to caption.

Video

Click to upload video

or drag and drop

Browse library

Transcript (SRT)

Click to upload document

or drag and drop

Browse library

Start (seconds)

End (seconds)

Still needed: Video, Transcript (SRT), Start (seconds), End (seconds)

How to use Video Trim

A compact decision guide for placing this pipeline in a workflow.

Best for

Cutting long videos to an explicit window already chosen upstream
Chaining after highlights: highlights picks the moment, video-trim slices it
Producing a clean, sentence-aligned clip plus its matching transcript in one call

When to use

Always after transcription + highlights (or any caller that already knows the window)
Before captions, the returned transcript already lines up with the trimmed clip and feeds the captions step directly

Tips

Pair with highlights (count=N, style=...) to get authoritative editorial picks
Cuts are snapped to SRT segment boundaries, pass a slightly tight window and let snapping widen it to a full sentence
The returned transcript already lines up with the trimmed clip, feed it straight into captions

Video Trim API

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

Get an API token

inputs: 4
required: 4
Pricing: 0.1 credits

Language

TypeScript Python Go CLI

bun add @pipe2-ai/sdk

Run a pipeline

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

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

const { run_pipeline } = await client.RunPipeline({
  pipeline_slug: "video-trim",
  input: {
    video_url: "https://example.com/interview.mp4",
    transcript_url: "https://example.com/interview.vtt",
    start_sec: 12,
    end_sec: 48,
  },
});

pip install pipe2

Run a pipeline

import asyncio
import os

from pipe2 import Pipe2Client

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

run = asyncio.run(client.run_pipeline(
    pipeline_slug="video-trim",
    input={
        "video_url": "https://example.com/interview.mp4",
        "transcript_url": "https://example.com/interview.vtt",
        "start_sec": 12,
        "end_sec": 48,
    },
))

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

Run a pipeline

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

input := json.RawMessage(`{
  "video_url": "https://example.com/interview.mp4",
  "transcript_url": "https://example.com/interview.vtt",
  "start_sec": 12,
  "end_sec": 48
}`)

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

brew install pipe2-ai/tap/pipe2

Run a pipeline

pipe2 pipelines run \
  --pipeline video-trim \
  --input-json '{"video_url": "https://example.com/interview.mp4", "transcript_url": "https://example.com/interview.vtt", "start_sec": 12, "end_sec": 48}' \
  --wait

Per page

Input	Type	default	Description
`end_sec`required	number	default—	Window end (exclusive). Must be greater than start_sec.
`start_sec`required	number	default—	Window start. Typically supplied by an upstream picker (e.g. highlights).
`transcript_url`required	string	default—	SRT transcript of the source, required. The window is snapped to its segment boundaries and the sliced SRT is returned for downstream captioning.
`video_url`required	string	default—	Source video to trim.

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" }
    }
  }
}

MCP setup

Full API reference CLI reference

Recipes using this pipeline

Show all recipes

Long video → multiple captioned clips, in one command

Slice any long video into N captioned shorter clips. Transcribe once, auto-pick the moments with AI, trim + caption each in parallel. Optionally reformat to vertical (9:16) for TikTok / Reels / Shorts, square (1:1) for Instagram, or portrait (4:5); the caption anchor auto-adjusts.

6 pipelines one CLI command

Open recipe
1. 1 Transcription
2. 2 Highlights
3. 3 Video Trim
4. 4 Video Reframe
5. 5 Captions
6. 6 Watermark
Open recipe

Articles about this pipeline

Show all articles

Frequently Asked Questions

How is the window chosen?

You supply it. The highlights pipeline (or any other picker) gives you a start and end time, and Video Trim cuts to exactly that window. It makes no editorial choice of its own, the decision of which moment to keep lives in the picker.

Why does it require a transcript?

The transcript is what lets the cut land on a full sentence instead of mid-word. Video Trim keeps every line of the transcript that overlaps your window, trims the video to match, and returns that same slice of the transcript lined up to the new clip, so the captions step can reuse it as-is.

Can it run without a transcript?

No. An earlier version guessed the cut from the video frames alone, but it kept drifting from the window you actually wanted, so it was removed. Transcribe the source first, the transcription pipeline reuses past results for the same file, so re-runs are free.

Does this cost credits?

0.1 credits per trim, flat.

What if the start or end time is outside the video?

The window is matched against your transcript, not the raw video. If it overshoots the end, the cut is snapped back to the last sentence in the transcript.