Video Intelligence API

Build with video intelligence

Natural language video search, multimodal analysis, and structured outputs in your own applications. One REST API, JSON in and out.

Get an API key View capabilities

quickstart.sh

# Create an index
curl -X POST https://www.ceptory.com/api/v1/indexes \
  -H "Authorization: Bearer your_api_key" \
  -H "Content-Type: application/json" \
  -d '{"name": "security-footage"}'

# Add a video by URL
curl -X POST https://www.ceptory.com/api/v1/indexes/idx_abc123/videos \
  -H "Authorization: Bearer your_api_key" \
  -H "Content-Type: application/json" \
  -d '{"url": "https://example.com/footage.mp4"}'

# Search video content
curl -X POST https://www.ceptory.com/api/v1/indexes/idx_abc123/search \
  -H "Authorization: Bearer your_api_key" \
  -H "Content-Type: application/json" \
  -d '{"query": "red sedan entering loading dock after midnight"}'

quickstart.sh

# Create an index
curl -X POST https://www.ceptory.com/api/v1/indexes \
  -H "Authorization: Bearer your_api_key" \
  -H "Content-Type: application/json" \
  -d '{"name": "security-footage"}'

# Add a video by URL
curl -X POST https://www.ceptory.com/api/v1/indexes/idx_abc123/videos \
  -H "Authorization: Bearer your_api_key" \
  -H "Content-Type: application/json" \
  -d '{"url": "https://example.com/footage.mp4"}'

# Search video content
curl -X POST https://www.ceptory.com/api/v1/indexes/idx_abc123/search \
  -H "Authorization: Bearer your_api_key" \
  -H "Content-Type: application/json" \
  -d '{"query": "red sedan entering loading dock after midnight"}'

quickstart.py

import requests

API = "https://www.ceptory.com/api/v1"
HEADERS = {"Authorization": "Bearer your_api_key"}

# Create an index
index = requests.post(f"{API}/indexes", headers=HEADERS,
                      json={"name": "security-footage"}).json()

# Add a video by URL
requests.post(f"{API}/indexes/{index['id']}/videos", headers=HEADERS,
              json={"url": "https://example.com/footage.mp4"})

# Natural language search
results = requests.post(f"{API}/indexes/{index['id']}/search", headers=HEADERS,
                        json={"query": "red sedan entering loading dock after midnight"}).json()
print(results)

RESTful API

Standard HTTP endpoints with JSON responses

Enterprise Security

SOC 2 Type II, GDPR compliant, encrypted at rest

99.9% Uptime SLA

Enterprise-grade reliability and support

Multi-region

Deploy in US, EU, or private cloud

Usage Analytics

Real-time dashboards and monitoring

Team Management

Role-based access control and audit logs

Capabilities

Everything you need for video intelligence

Create an index, add videos, then search and analyze them. Authenticate with a Bearer API key from your dashboard.

Natural Language Search

Query video content using natural language. Find scenes, actions, objects, spoken phrases, and event sequences without manual tagging.

POST /api/v1/indexes/{indexId}/search

Multimodal Analysis

Extract structured insights from visual, audio, and speech signals. Scene classification, object detection, speaker diarization, and sentiment analysis.

POST /api/v1/indexes/{indexId}/analyze

Indexes

Group footage into indexes per site, camera fleet, or project. Each index keeps its own videos, embeddings, and search scope.

GET · POST /api/v1/indexes

Video Ingestion

Add a video by URL. Ceptory fetches it, indexes scenes and speech, and reports processing status per video.

POST /api/v1/indexes/{indexId}/videos

Structured Outputs

Get JSON-formatted results ready for downstream systems. Summaries, transcripts, timecoded events, and confidence scores.

JSON responses

Processing Status

Check each video's indexing status, then search or analyze it as soon as it is ready.

GET /api/v1/indexes/{indexId}/videos/{videoId}

Developer experience

Plain HTTPS, JSON, and copyable examples

No SDK to install. Call the REST endpoints from any language with a Bearer API key, and read JSON back.

Bearer API keys, created in the dashboard
JSON errors with clear messages and status codes
Per-video processing status you can poll
cURL, Python, and JavaScript examples

Talk to the team

quickstart.js

const API = "https://www.ceptory.com/api/v1";
const headers = {
  Authorization: "Bearer your_api_key",
  "Content-Type": "application/json",
};

// Create an index
const index = await fetch(`${API}/indexes`, {
  method: "POST",
  headers,
  body: JSON.stringify({ name: "security-footage" }),
}).then((res) => res.json());

// Add a video by URL
await fetch(`${API}/indexes/${index.id}/videos`, {
  method: "POST",
  headers,
  body: JSON.stringify({ url: "https://example.com/footage.mp4" }),
});

// Natural language search
const results = await fetch(`${API}/indexes/${index.id}/search`, {
  method: "POST",
  headers,
  body: JSON.stringify({ query: "red sedan entering loading dock after midnight" }),
}).then((res) => res.json());
console.log(results);

Pricing

Simple, prepaid pricing

Start with 10 free indexed minutes, then add prepaid balance for indexing and search.

Free

For evaluation and early workspace setup

Free

10 indexed video minutes included
Developer dashboard and workspace setup
Early search and retrieval evaluation
Upgrade path into Stripe billing

Create account

Developer

Enterprise

For large-scale deployments and compliance

Custom

Unlimited video processing
Private cloud deployment
Dedicated support
Custom SLAs
On-premise option
Custom model training

FAQ

API questions, answered

Talk to our team

What video formats does the API support?

Ceptory supports all major video formats including MP4, MOV, AVI, MKV, WebM, and more. We handle transcoding automatically so you can upload videos in any format and resolution.

How does natural language search work?

Our multimodal AI models analyze visual content, audio, speech, and on-screen text to create semantic embeddings. When you search, we match your query against these embeddings to find relevant scenes, actions, objects, and spoken phrases.

Can I deploy Ceptory in my own infrastructure?

Yes. Enterprise customers can deploy Ceptory in private cloud environments (AWS, GCP, Azure) or fully on-premise. This ensures data never leaves your security boundary.

What are the API rate limits?

Rate limits vary by plan. Starter tier allows 60 requests/minute. Pro and Enterprise tiers have higher limits and can be customized based on your needs.

How do I authenticate?

Create an API key in the Ceptory dashboard and send it as a Bearer token in the Authorization header of every request.

Do you offer SDKs?

Not yet. The API is plain HTTPS with JSON bodies, so any HTTP client works. This page shows cURL, Python, and JavaScript examples you can copy.

Get started

Ready to build with video intelligence?

Create a workspace, generate an API key, and run your first search in minutes. Talk to us about enterprise deployment.

Get an API key Contact sales

An architecture diagram of an index exposed through an API to apps, with the key step highlighted in coral.