VIDEO ANALYSIS API

Turn video into structured JSON

The video analysis API for developers. POST a file or share a recording link. Define the fields you need, get objects, actions, and scene data back as JSON in seconds.

No credit card required. 50 free credits to start.
POST /v1/videos
{ "damage_type": "dented_box", "severity": "moderate", "scene": "warehouse", "confidence": 0.97 }
200 OK · 2.4s

HOW IT WORKS

Video in, JSON out. Three steps.

01

Define your schema

List the fields you want back, like damage type, scene description, action detected, or severity. You choose them, the API fills them in.

02

Send the video

POST a file directly, or generate a recording link. Users record or upload from any browser, no app needed.

03

Get your JSON

A webhook fires the moment analysis finishes, with every field you defined already filled in.

ONE SCHEMA ENGINE

What you can pull out of a video

Define the fields you need. The API returns exactly those, structured as JSON, on every video.

UNIFIED SCHEMA

Define your fields once. Extract them from every video.

{ scene: string, action_detected: string, severity: enum }
OBJ
Objects

Products, vehicles, equipment, documents.

ACT
Actions

What's happening, sequences of events.

SCN
Scenes

Location type, conditions, context.

TXT
Text

Visible text, on-screen messages, error codes.

#
Counts

People, items, occurrences.

CND
Conditions

Damage type, severity, quality assessments.

HEX
Colors

Different shades, specific colors.

USE CASES

What teams build with the video analysis API

E-commerce / retail

Customers record what arrived versus what was expected. Extract defect type, condition, item count.

{ defect_type: "torn_packaging", item_count: 3 }
Property management

Tenants record the issue from their phone. Extract equipment type, location, urgency level.

{ equipment_type: "hvac_unit", urgency: "high" }
Insurance

Claimants film the damage in one continuous take. Extract damage type, severity, policy number.

{ damage_type: "collision", severity: "moderate" }
SaaS products

Users send a screen recording instead of a 200-word ticket. Extract error messages, reproduction steps.

{ error_code: "ERR_502", severity: "high" }
Automotive / dealerships

Sellers record a walkaround of the vehicle. Extract visible damage, mileage, VIN.

{ mileage: 42318, vin: "1HGCM82633A004352" }
Healthcare

Patients film symptoms over time, at home. Extract affected area, duration, severity.

{ affected_area: "left forearm", duration_days: 4 }

PRICING

Start free. Scale when you need to.

Pay as you go
50 credits free
then $1 per 10 credits
  • 1 credit per minute of video
  • Files auto-delete after 1 hour
  • Up to 3 assistants for different extraction tasks
  • Custom fields on every request
  • Recording links, up to 5 minutes each
Start free
Pro
$149/mo
2,000 credits included
  • Everything in Pay as you go
  • Shared workspace for up to 3 teammates
  • Unlimited assistants
  • Fine-tune extraction with your own data
  • Custom branding on recording links
  • Unlimited video length
Start free
Enterprise
Custom
for teams with scale or compliance needs
  • On-premise deployment
  • Custom-trained extraction models
  • Volume discounts
  • Priority support
Contact sales

FAQ

Questions, answered

How does the AI extraction work?

You define the fields you want, like issue type, severity, or visible text. When a video is uploaded, our AI analyzes it and fills those fields in, then delivers the result over webhook.

What video formats do you support?

MP4, MOV, and WebM. Users can record directly in their browser or upload from their device, no app installation required.

Do users need an account to submit video?

No. They open your link, record or upload, and submit. The entire process takes about 30 seconds with zero friction.

Where are the files stored?

Files are stored temporarily with a 1-hour expiry by default. You can configure a longer window or send files directly to your own storage.

How accurate is the extraction?

Most customers see 95 to 100 percent accuracy on well-defined fields. Accuracy depends on video quality and how specific your fields are.

Can I customize what gets extracted?

Yes, completely. You define custom extraction fields for each request, and the API returns exactly those fields from the video content.

Start analyzing video today

50 free credits. No credit card required.

Start free