Niravi Cloud API

Search, recall, and analyze a corpus of video — over a simple HTTP API, with first-class Python & TypeScript SDKs and an MCP server for Claude.

Everything is one base URL — https://api.niravi.io — and one credential, an API key (nv_…). A key is scoped to a single workspace; every call operates on that workspace’s videos.

1. Get an API key

Create one in the dashboard → Settings → Developer. Pick the scopes (read and/or write) and an optional expiry. The secret is shown once — store it somewhere safe.

2. Make your first call

curl https://api.niravi.io/api/v1/search \
  -H "X-API-Key: $NIRAVI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query": "a person walking at sunset", "limit": 5}'

Every response is a typed envelope — { "success": true, "data": … } on success, { "success": false, "error": { code, message, status } } on failure.

3. Or use an SDK

# pip install niravi
import niravi
client = niravi.connect("nv_...")
for hit in client.search("a person walking at sunset", limit=5):
    print(hit.video_id, hit.timestamp, hit.score)

// npm install @niravi/sdk
import { connect } from "@niravi/sdk";
const niravi = connect("nv_...");
const hits = await niravi.search("a person walking at sunset", { limit: 5 });

Where to next

ConceptsKeys & scopes, workspaces, pagination, errors, rate limits. SearchSemantic search + typed "magic" search by character, location, music, emotion. Recall & ChatAsk natural-language questions grounded in your video. SDKsPython & TypeScript — generated from the same OpenAPI spec. MCP for ClaudeExpose your corpus to Claude as tools. API ReferenceEvery endpoint, grouped, with try-it.

Demo without a key? The interactive API Reference lets you browse every endpoint and its schemas. To run live calls you’ll need a key.