Summarise a video
An hour of footage rarely needs to stay an hour once someone just wants to know what was said. This endpoint watches and listens to a video and returns a written summary of its content, so a meeting, lecture, or long-form video can be understood in the time it takes to read a page instead of the time it takes to watch it.
Run it online
Run this on our servers with your account. Free tools run in your browser; this one bills your KIT balance per the price above.
The problem of video that nobody has time to watch
Recorded meetings pile up, webinars get archived and forgotten, long interviews sit unwatched because reviewing them takes as long as they run. The video summarizer api endpoint is built for exactly that backlog: anyone who needs the substance of a video without spending its full runtime finding out whether it's even relevant, or worth forwarding to someone else.
What the endpoint actually does
POST /video/summarize takes a link to your video, processes both its spoken content and its visual context, and returns a structured written summary that captures the main points, in the language and level of detail the content calls for, rather than a generic sentence-by-sentence rewrite of a transcript that still takes ten minutes to read.
How the request and response work
As with every task on the platform, this call is asynchronous: you submit the video and get a task_id immediately, the summarization happens in the background, and the finished summary reaches you through a signed webhook the moment it's ready or through a signed link you can retrieve yourself within 24 hours, whichever fits your integration better.
Why summarizing video is a different problem than summarizing text
A written document only has words to work with, but a video carries meaning in what's said, in tone, and often in what's shown on screen, a slide, a demo, a chart, so a genuine video summary has to account for spoken content and visual context together rather than transcribing audio and calling it done; that combination is what separates a useful one-page summary from a wall of loosely condensed dialogue.
Where it fits into a bigger system
Because the summary comes back as structured, billed-on-success output, it's designed to sit inside automated pipelines: a meeting recorder that summarizes every call automatically, a content team that triages a queue of submitted videos by summary before deciding what to watch in full, or a knowledge base that indexes video content by its written summary instead of its raw runtime.
What you can do with it
Meeting recap automation
A company automatically summarizes every recorded internal meeting so team members who missed it can read a one-page recap instead of watching the full recording.
Webinar and course triage
An education platform summarizes submitted lecture recordings so editors can quickly judge relevance and quality before deciding which ones to feature.
Video content moderation support
A review team uses summaries to get quick context on flagged videos, helping prioritize which ones need a full manual watch.
Searchable video knowledge base
An internal wiki stores the written summary of each training video alongside its link, making the archive searchable by content instead of by title alone.
FAQ
How do I summarize a video using the API?
Send a POST request to /video/summarize with a link to your video; you get a task_id right away and the written summary later via webhook or signed link.
Does the summary account for what's shown on screen, not just spoken audio?
Yes, it processes visual context alongside spoken content, which is what makes it a real video summary rather than a transcript rewrite.
Is there a free trial for the video summarizer?
There's no free tier — free tiers get abused and slow everyone down. Access runs on a prepaid ForHosting KIT balance: top up from $10.00 (it never expires) and each request is charged at its published price, so a call with no balance returns HTTP 402. No subscription, no tokens, no invented credits, and a failed task is never charged.
What language is the summary written in?
The summary follows the language and level of detail the content calls for; specify your preference in the request if you need a particular output language.
How much does summarizing a video cost?
It's $0.084 per request plus $0.023 per minute of video processed, published openly with no hidden token pricing.
Is this different from just running a transcript through a text summarizer?
Yes, a transcript-only summary misses visual content like slides or demos; this endpoint processes both audio and visual context together.
What happens if the summarization job fails?
It's retried automatically up to three times, and a job that still fails is never billed, returning a clear error instead.
Is the video summary endpoint available now?
It's in final deployment and not yet accepting jobs; it will be available very soon under the endpoint and pricing described here.
For developers — API access
Everything on this page is available programmatically. This section is for teams who want to wire it into their own systems; everyone else can just use the tool above.
API endpoint
Prefer to automate it? One authenticated POST creates the task; the result comes back by webhook or a signed link. The same capability also runs here on the web, and soon from our app, email and Telegram.
Call it from your stack
curl -X POST https://api.kit.forhosting.com/video/summarize \
-H "Authorization: Bearer $KIT_KEY" \
-H "Content-Type: application/json" \
-d '{"audio":"https://ejemplo.com/audio.mp3"}'const res = await fetch("https://api.kit.forhosting.com/video/summarize", {
method: "POST",
headers: {
"Authorization": `Bearer ${process.env.KIT_KEY}`,
"Content-Type": "application/json"
},
body: JSON.stringify({
"audio": "https://ejemplo.com/audio.mp3"
})
});
const { task_id } = await res.json();import os, requests
res = requests.post(
"https://api.kit.forhosting.com/video/summarize",
headers={"Authorization": f"Bearer {os.environ['KIT_KEY']}"},
json={
"audio": "https://ejemplo.com/audio.mp3"
},
)
task_id = res.json()["task_id"]<?php
$res = file_get_contents("https://api.kit.forhosting.com/video/summarize", false, stream_context_create([
"http" => [
"method" => "POST",
"header" => "Authorization: Bearer " . getenv("KIT_KEY") . "\r\nContent-Type: application/json",
"content" => '{"audio":"https://ejemplo.com/audio.mp3"}',
],
]));
$task = json_decode($res, true);body := bytes.NewBufferString(`{"audio":"https://ejemplo.com/audio.mp3"}`)
req, _ := http.NewRequest("POST", "https://api.kit.forhosting.com/video/summarize", body)
req.Header.Set("Authorization", "Bearer "+os.Getenv("KIT_KEY"))
req.Header.Set("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)Example request
{
"audio": "https://ejemplo.com/audio.mp3"
}Example response
{
"task_id": "tsk_a1b2c3d4e5f6a1b2c3d4e5f6",
"type": "video.summarize",
"status": "queued",
"_links": {
"result": "/tasks/tsk_…/result"
}
}The API is asynchronous: the call returns a task_id immediately and the result arrives by webhook. Polling is capped at 1 req/s per task.
Pricing
Published price — no tokens, no invented credits. A failed task is never charged.
Limits
max_mb | 500 |
max_minutes | 60 |
max_megapixels | 3.9 |
Errors
| HTTP | Code | Meaning |
|---|---|---|
401 | unauthorized | Missing or invalid API key. |
402 | insufficient_balance | Your balance doesn't cover the task price. |
404 | unknown_type | That task type doesn't exist. |
429 | rate_limited | Too many requests. Use the webhook instead of polling. |
422 | task_failed | The task failed after 3 retries. You are never charged for it. |