> ## Documentation Index
> Fetch the complete documentation index at: https://docs.memories.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

> Visual Intelligence — stateless REST APIs for video scraping, transcription, video/image understanding, embeddings, and live-stream processing.

<Warning>
  **API 1.0 will be sunset on August 13, 2026.** These pages are kept for reference — don't start new integrations against them.

  Everything moves to **[API 2.0 — Video Datalake](/overview)**: one host, one key, one OpenAPI spec for ingest, search, and moment reads. Use the version selector next to the logo at the top of the page to switch between 1.0 and 2.0 at any time.
</Warning>

Visual Intelligence is a collection of **stateless REST APIs** you call directly on your own video, image, and audio data. No persistent library, no indexing — pick the endpoint that matches your task, send a request, get a result.

If you want a persistent, indexed video + image library you can query by natural language or image, you want the [**Visual Search**](/visual-search/introduction) product instead.

## Core Capabilities

<CardGroup cols={3}>
  <Card title="Video Scraping" icon="bug">
    Metadata, transcripts, captions, and comments from TikTok, YouTube, Instagram, and X/Twitter.
  </Card>

  <Card title="Video Processing" icon="film">
    Upload, signed-URL upload, frame extraction, download, delete — manage assets used by other VI APIs.
  </Card>

  <Card title="Video & Image Understanding" icon="brain">
    Call Gemini / Nova / Qwen / GPT VLMs and ILMs directly. Pre-packaged tasks for frame description and summary.
  </Card>

  <Card title="Audio Transcription" icon="mic">
    Whisper, ElevenLabs, AssemblyAI providers + speaker diarization / recognition for files and live streams.
  </Card>

  <Card title="Live Stream Processing" icon="radio-tower">
    Real-time content moderation and prompt-driven understanding on RTMP / RTSP streams.
  </Card>

  <Card title="Embeddings" icon="vector-square">
    Image / video / text embeddings for semantic search and retrieval pipelines.
  </Card>
</CardGroup>

## Hosts

Most endpoints live on `https://mavi-backend.memories.ai/serve/api/v2`. Two specialty hosts are used for specific groups:

| Group                              | Host                                            |
| ---------------------------------- | ----------------------------------------------- |
| Most Visual Intelligence endpoints | `https://mavi-backend.memories.ai/serve/api/v2` |
| Live Video Understanding           | `https://stream.memories.ai`                    |
| Human ReID & Caption (Security)    | `https://security.memories.ai`                  |

Each endpoint page includes a banner with its exact host and the authentication header to use.

## Next Steps

<CardGroup cols={2}>
  <Card title="API Overview" icon="map" href="/visual-intelligence/getting-started/overview">
    Browse every endpoint group with one-line descriptions — pick the right one for your use case.
  </Card>

  <Card title="Create Your API Key" icon="key" href="/visual-intelligence/getting-started/create-your-key">
    Generate a key in under 2 minutes and start calling endpoints.
  </Card>
</CardGroup>