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

# Memories.ai Documentation

> Pick the right product: Visual Intelligence for stateless inference, Visual Search for an indexed video + image library, Visual Agents for ready-made workflows.

Memories.ai ships three independent products on top of one shared video understanding stack — plus a CLI that drives all of them from the terminal. Pick the product that matches what you're building.

## Get Started

<CardGroup cols={2}>
  <Card title="Create Your API Key" icon="key" href="/visual-intelligence/getting-started/create-your-key">
    Generate one `sk-mavi-...` key that works across Visual Intelligence, Visual Search, and Visual Agents. Under 2 minutes.
  </Card>

  <Card title="Upload Your First Video" icon="upload" href="/visual-search/upload-overview">
    The Visual Search indexing pipeline at a glance — pick the right upload method and learn how to wait for the parse to finish.
  </Card>
</CardGroup>

## Products

<CardGroup cols={3}>
  <Card title="Visual Intelligence" icon="bolt" href="/visual-intelligence/getting-started/introduction">
    **Stateless inference APIs.** Direct REST calls for transcription, captioning, model inference, embeddings, live-stream moderation, and Human ReID. No persistence — you bring the data, we return the result.
  </Card>

  <Card title="Visual Search" icon="database" href="/visual-search/introduction">
    **Indexed video + image library.** Upload videos and images once, the platform auto-indexes them, and you query by natural language, image similarity, or transcript phrase. State lives on the server.
  </Card>

  <Card title="Visual Agents" icon="robot" href="/visual-agents/overview">
    **Pre-built agents + workflow APIs.** Open-source video-searching and video-editing agents, plus managed services for queries, clip/edit/split, and screenplay extraction. Fork the agents, or call the managed endpoints directly.
  </Card>
</CardGroup>

## Which One Do I Use?

| If you want to…                                                          | Use                                                                                                                                                                 |
| ------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Run AI analysis on a one-off video file you have                         | **Visual Intelligence** — [Video Model APIs](/visual-intelligence/video-model-selection) or [Video Task APIs](/visual-intelligence/caption/video-frame-description) |
| Transcribe an audio or video file to text                                | **Visual Intelligence** — [Audio File Transcription](/visual-intelligence/transcript/whisper-audio-transcription)                                                   |
| Pull a transcript / caption from a YouTube / TikTok / Instagram / X link | **Visual Intelligence** — [Social Media Scraping](/visual-intelligence/social-media-scraping-overview)                                                              |
| Moderate a live RTMP stream in real time                                 | **Visual Intelligence** — [Live Video Content Moderation](/visual-intelligence/stream/video-stream-start)                                                           |
| Transcribe a live audio broadcast in real time                           | **Visual Intelligence** — [Live Audio Transcription](/visual-intelligence/stream/audio-stream-start)                                                                |
| Identify specific named people in a video                                | **Visual Intelligence** — [Human ReID & Caption](/visual-intelligence/caption/video-caption)                                                                        |
| Build a searchable video library you can query later                     | **Visual Search** — [upload once, auto-indexed, query later](/visual-search/introduction)                                                                           |
| Find moments across all your uploaded videos by natural language         | **Visual Search** — [Search by Text](/visual-search/search-by-text)                                                                                                 |
| Build a video discovery / editing bot                                    | **Visual Agents** — [Video Searching Agent](/visual-agents/video-searching-agent) or [Video Editing Agent](/visual-agents/video-editing-agent)                      |
| Extract storyboard / screenplay data from short drama episodes           | **Visual Agents** — [Screenplay Extraction](/visual-agents/screenplay/submit-task)                                                                                  |
| Drive the platform from the terminal                                     | **Memories CLI** — see [Tools](#tools) below                                                                                                                        |

## What's Inside Each Product

### Visual Intelligence

Stateless REST APIs on `https://mavi-backend.memories.ai/serve/api/v2` (plus two specialty hosts — see [Base URLs](/visual-intelligence/getting-started/overview#base-urls)).

| Group                                                                                    | What it does                                                                         |
| ---------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------ |
| [Asset Management](/visual-intelligence/base/upload)                                     | Upload / download / delete video and image assets used by other VI APIs              |
| [Social Media Scraping](/visual-intelligence/social-media-scraping-overview)             | Metadata, transcripts, captions, comments from YouTube, Instagram, TikTok, Twitter/X |
| [Audio File Transcription](/visual-intelligence/transcript/whisper-audio-transcription)  | Whisper, ElevenLabs, AssemblyAI providers + speaker diarization / recognition        |
| [Live Audio Transcription](/visual-intelligence/stream/audio-stream-start)               | Real-time STT on live audio — server-pull (callback) or WebSocket (client-push)      |
| [Video Model APIs](/visual-intelligence/video-model-selection)                           | Direct VLM calls with your own prompt — Gemini, Nova, Qwen                           |
| [Video Task APIs](/visual-intelligence/caption/video-frame-description)                  | Pre-packaged tasks on top of VLMs — Video Frame Description, Video Summary           |
| [Live Video Content Moderation](/visual-intelligence/stream/video-stream-start)          | NSFW / violence / logo detection on RTMP/RTSP streams                                |
| [Live Video Understanding](/visual-intelligence/stream/video-stream-understanding-start) | Custom AI prompt continuously applied to a live RTMP stream                          |
| [Image Model APIs](/visual-intelligence/image-model-selection)                           | Direct ILM calls — Gemini, GPT, Nova, Qwen                                           |
| [Embeddings](/visual-intelligence/embeddings/image-embedding)                            | Image / video / text embeddings for semantic search and retrieval                    |
| [Human ReID & Caption](/visual-intelligence/caption/video-caption)                       | Identity-aware vision — caption a video with named people. Requires a dedicated key  |

**Example — transcribe an audio URL:**

```bash theme={null}
curl -X POST "https://mavi-backend.memories.ai/serve/api/v2/transcriptions/speech-to-text" \
  -H "Authorization: sk-mavi-..." \
  -H "Content-Type: application/json" \
  -d '{
    "provider": "elevenlabs",
    "url": "https://example.com/recording.mp3",
    "language_code": "en"
  }'
```

### Visual Search

Indexed video + image library on `https://api.memories.ai/serve/api/v1`. Upload once, query forever.

| Group                                                 | What it does                                                                                                                |
| ----------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------- |
| [Index Upload](/visual-search/upload-video-from-file) | Upload videos (from file, URL, or social-media creator handle) and images for indexing                                      |
| [Search](/visual-search/search-overview)              | Semantic and keyword search across your private library and the public video library — by text, image, or transcript phrase |
| [Library Management](/visual-search/list-videos)      | List / get metadata / download / delete videos in your library                                                              |

**Example — upload a video for indexing:**

```python theme={null}
import requests

with open("meeting.mp4", "rb") as f:
    response = requests.post(
        "https://api.memories.ai/serve/api/v1/upload",
        headers={"Authorization": "sk-mavi-..."},
        files={"file": ("meeting.mp4", f, "video/mp4")},
        data={"unique_id": "my-project", "callback": "https://your.app/callback"},
    )
print(response.json())  # returns videoNo for later search
```

### Visual Agents

Reference implementations and managed workflow APIs on `https://mavi-backend.memories.ai/serve/api/v2`.

| Agent / Service                                                 | Open-source repo                                                                   | Managed API                                                                                                                               |
| --------------------------------------------------------------- | ---------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------- |
| [Video Searching Agent](/visual-agents/video-searching-agent)   | [video-searching-agent](https://github.com/Memories-ai-labs/video-searching-agent) | [`POST /queries/stream`](/visual-agents/video-searching-api)                                                                              |
| [Video Editing Agent (VEA)](/visual-agents/video-editing-agent) | [vea-open-source](https://github.com/Memories-ai-labs/vea-open-source)             | [`POST /video/edit`](/visual-agents/video-edit), [`/video/clip`](/visual-agents/video-clip), [`/video/split`](/visual-agents/video-split) |
| [Screenplay Extraction](/visual-agents/screenplay/submit-task)  | — (managed only)                                                                   | `POST /screenplay/tasks` (async)                                                                                                          |

**Example — stream a Video Searching Agent query:**

```bash theme={null}
curl -N -X POST "https://mavi-backend.memories.ai/serve/api/v2/queries/stream" \
  -H "Authorization: sk-mavi-..." \
  -H "Content-Type: application/json" \
  -d '{
    "query": "Trending AI coding tool videos on TikTok this week",
    "platforms": ["tiktok"],
    "max_results": 5,
    "time_frame": "past_week"
  }'
```

## Tools

### Memories CLI

Command-line tool for the entire ecosystem — uploads, searches, agent calls, asset management from your terminal or shell scripts. Same `sk-mavi-...` key as the rest of the platform.

<CardGroup cols={2}>
  <Card title="Memories CLI on GitHub" icon="github" href="https://github.com/Memories-ai-labs/memories-cli">
    Install instructions, command reference, and source.
  </Card>

  <Card title="Memories.ai Console" icon="terminal" href="https://api-platform.memories.ai/stripe">
    Manage API keys, view usage and credits, configure webhooks.
  </Card>
</CardGroup>

## Billing

All three products share a unified billing system. Pricing varies per endpoint — see the pricing note at the top of each endpoint page, or the [Memories.ai Console](https://api-platform.memories.ai/stripe) for your current usage and credits.

## Compliance

<Note icon="lock">
  Memories.ai meets the highest standards of data security and privacy with HIPAA, SOC 2 Type 2, and GDPR compliance. For more information, see the [Trust Center](https://trust.memories.ai).
</Note>