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

# Analyze Video

> Analyzes video content using AI

Analyzes video content using AI. Supports uploaded videos and YouTube URLs. Can transcribe audio, provide timestamps, and answer questions about video content.

|                      |                    |
| -------------------- | ------------------ |
| **App**              | AI                 |
| **Operation ID**     | `ai_analyze_video` |
| **Type**             | Action             |
| **Connection**       | None               |
| **Credits per run**  | 20                 |
| **Agent / MCP tool** | Yes                |

## Inputs

| Field          | Type                       | Required | Default | Description                                                                                                                                                                                                                                                                                                                                                                                                                                                       |
| -------------- | -------------------------- | -------- | ------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `prompt`       | string                     | Yes      | -       | Instructions for analyzing the video. This is a multi-line text area where you can: - Ask questions about video content - Request descriptions of specific scenes or actions - Ask for transcription of dialogue or audio - Request timestamps for specific events - Analyze visual elements, movements, or changes  Example: "Analyze this video and provide: 1. A summary of what happens 2. Timestamps of key moments 3. Transcription of any spoken dialogue" |
| `model`        | string or SelectableOption | Yes      | -       | The AI model to use for video analysis. Available Gemini models: 'gemini-2.5-flash' (RECOMMENDED) - Best for video analysis 'gemini-2.5-flash-lite' (FAST) - Fast and efficient 'gemini-2.5-pro' - Advanced capabilities for complex analysis                                                                                                                                                                                                                     |
| `video_source` | string or SelectableOption | Yes      | -       | Source of the video to analyze: 'upload' - Upload a video file (MP4, MOV, AVI, etc.) 'youtube' - Provide a YouTube URL                                                                                                                                                                                                                                                                                                                                            |
| `video`        | string                     | No       | -       | Video to analyze. Depending on the video\_source: - For 'upload': Video file URL from upload - For 'youtube': YouTube video URL (e.g., `https://www.youtube.com/watch?v=...`)  Supported formats for upload: MP4, MOV, AVI, WebM, FLV, MKV                                                                                                                                                                                                                        |
| `youtube_url`  | string                     | No       | -       | YouTube URL if video\_source is 'youtube'.  Must be a public video (not private or unlisted). Example: `https://www.youtube.com/watch?v=9hE5-98ZeCg`                                                                                                                                                                                                                                                                                                              |

### SelectableOption

| Field   | Type   | Required | Default | Description |
| ------- | ------ | -------- | ------- | ----------- |
| `value` | string | Yes      | -       |             |
| `label` | string | Yes      | -       |             |

## Output

**Type**: `str`

Returns AI analysis of the video as markdown text.