# Memories.ai API Tools

## Docs

- [Overview](https://api-tools.memories.ai/agents/overview.md): Production-focused open-source agents for video searching and video editing workflows.
- [Video Editing Agent (VEA)](https://api-tools.memories.ai/agents/video-editing-agent.md): An automated pipeline for converting long-form videos into short-form edits.
- [Video Searching Agent](https://api-tools.memories.ai/agents/video-searching-agent.md): Official OpenClaw skill on ClawHub powered by the managed Memories.ai Video Searching API.
- [Video Searching API](https://api-tools.memories.ai/agents/video-searching-api.md): Due to limitation of Mintlify, SSE results are sent at the end of the stream when you click "Try it" on the page.
- [Delete Asset](https://api-tools.memories.ai/api-reference/base/delete.md): Delete an asset by its ID
- [Download Asset](https://api-tools.memories.ai/api-reference/base/download.md): Download an asset file as a binary stream and save to local storage
- [Extract Video Frames](https://api-tools.memories.ai/api-reference/base/extract-frames.md): Extract individual frames from a video asset
- [Get Asset Metadata](https://api-tools.memories.ai/api-reference/base/get-metadata.md): Retrieve metadata information for a specific asset
- [Upload File](https://api-tools.memories.ai/api-reference/base/upload.md): Upload a video, audio, or image file to the MAVI platform
- [Get Upload Signed URL](https://api-tools.memories.ai/api-reference/base/upload-by-signed-url/get-upload-signed-url.md): Generate a pre-signed URL for direct file upload
- [Upload File Using Signed URL](https://api-tools.memories.ai/api-reference/base/upload-by-signed-url/upload-file-using-signed-url.md): Upload file directly to storage using pre-signed URL
- [Scene Detection](https://api-tools.memories.ai/api-reference/base/video-clip.md): Detect scene boundaries in a video asset
- [Edit Video](https://api-tools.memories.ai/api-reference/base/video-edit.md): Edit and compose videos with AI-powered instructions
- [Split Video](https://api-tools.memories.ai/api-reference/base/video-split.md): Split a video into multiple segments
- [Generate Image Embedding](https://api-tools.memories.ai/api-reference/embeddings/image-embedding.md): Generate vector embeddings for images using multimodal models
- [Generate Text Embedding](https://api-tools.memories.ai/api-reference/embeddings/text-embedding.md): Generate vector embeddings for text using language models
- [Generate Video Embedding](https://api-tools.memories.ai/api-reference/embeddings/video-embedding.md): Generate vector embeddings for videos using multimodal models
- [Gemini Image](https://api-tools.memories.ai/api-reference/gemini/gemini-ilm.md): Generate chat completions using Gemini ILM model with image inputs.
- [Gemini Video](https://api-tools.memories.ai/api-reference/gemini/gemini-vlm.md): Generate chat completions using Gemini VLM model with text, video, and image inputs.
- [Create Your API Key](https://api-tools.memories.ai/api-reference/getting-started/create-your-key.md): Get started with Memories.ai API by creating your first API key
- [Response & Error Codes](https://api-tools.memories.ai/api-reference/getting-started/error-codes.md): Understand the standard API response structure and error codes
- [Overview](https://api-tools.memories.ai/api-reference/getting-started/overview.md): All-in-one API tools platform for video scraping, processing, and understanding
- [Rate Limit](https://api-tools.memories.ai/api-reference/getting-started/rate-limit.md): Understand the rate limits for Memories.ai API endpoints
- [Webhooks](https://api-tools.memories.ai/api-reference/getting-started/webhooks.md): Configure webhook endpoints to receive async task results
- [GPT Image](https://api-tools.memories.ai/api-reference/gpt/gpt-ilm.md): Generate chat completions using GPT ILM model with image inputs.
- [Image Model Selection](https://api-tools.memories.ai/api-reference/image-model-selection.md): Choose the right image understanding model for your workload
- [Nova Image](https://api-tools.memories.ai/api-reference/nova/nova-ilm.md): Generate chat completions using Nova ILM model with image and text inputs.
- [Nova Video](https://api-tools.memories.ai/api-reference/nova/nova-vlm.md): Generate chat completions using Nova VLM model with text, video, and image inputs.
- [Qwen Image](https://api-tools.memories.ai/api-reference/qwen/qwen-ilm.md): Generate chat completions using Qwen ILM model with image inputs.
- [Qwen Video](https://api-tools.memories.ai/api-reference/qwen/qwen-vlm.md): Generate chat completions using Qwen VLM model with text, video, and image inputs.
- [TikTok Video Comment](https://api-tools.memories.ai/api-reference/scraper/tiktok-video-comment.md): Get the comment list for TikTok videos.
- [TikTok Video Comment Reply](https://api-tools.memories.ai/api-reference/scraper/tiktok-video-comment-reply.md): Get the reply list for TikTok video comments.
- [TikTok Video Detail](https://api-tools.memories.ai/api-reference/scraper/tiktok-video-detail.md): Get detailed information for TikTok videos.
- [YouTube Video Comment](https://api-tools.memories.ai/api-reference/scraper/youtube-video-comment.md): Get the comment list for YouTube videos.
- [YouTube Video Comment Reply](https://api-tools.memories.ai/api-reference/scraper/youtube-video-comment-reply.md): Get the reply list for YouTube video comments.
- [YouTube Video Detail](https://api-tools.memories.ai/api-reference/scraper/youtube-video-detail.md): Get detailed information for YouTube videos.
- [Cancel Task](https://api-tools.memories.ai/api-reference/screenplay/cancel-task.md): Cancel a running screenplay extraction task
- [Download Task Result](https://api-tools.memories.ai/api-reference/screenplay/download-task-result.md): Download completed screenplay extraction results as a zip file
- [Get Task Status](https://api-tools.memories.ai/api-reference/screenplay/get-task-status.md): Query the current status and progress of a screenplay extraction task
- [Submit Screenplay Task](https://api-tools.memories.ai/api-reference/screenplay/submit-task.md): Submit an async screenplay extraction task for short drama videos
- [Social Media Scraping Overview](https://api-tools.memories.ai/api-reference/social-media-scraping-overview.md): How channel routing works across social media scraping endpoints, including Apify, RapidAPI, and managed routing by Memories.ai.
- [Start Audio Stream Transcription](https://api-tools.memories.ai/api-reference/stream/audio-stream-start.md): Start real-time audio stream transcription with ElevenLabs or AssemblyAI, controlled by a provider parameter.
- [Stop Audio Stream Transcription](https://api-tools.memories.ai/api-reference/stream/audio-stream-stop.md): Stop an active audio stream transcription task.
- [Real-time Audio Stream (WebSocket)](https://api-tools.memories.ai/api-reference/stream/audio-stream-websocket.md): Connect directly via WebSocket for real-time speech-to-text with ElevenLabs or AssemblyAI.
- [Start Video Stream Moderation](https://api-tools.memories.ai/api-reference/stream/video-stream-start.md): Start video stream content moderation and logo detection with real-time processing.
- [Stop Video Stream Moderation](https://api-tools.memories.ai/api-reference/stream/video-stream-stop.md): Stop an active video stream processing task.
- [AssemblyAI](https://api-tools.memories.ai/api-reference/transcript/assemblyai.md): Transcribe audio to text using AssemblyAI Universal-2 model.
- [Async Generate Audio Transcription](https://api-tools.memories.ai/api-reference/transcript/async-generate-audio.md): Generate audio transcription asynchronously.
- [Async Generate Speaker](https://api-tools.memories.ai/api-reference/transcript/async-generate-speaker.md): Generate speaker identification asynchronously.
- [Async Generate Video Description](https://api-tools.memories.ai/api-reference/transcript/async-generate-video.md): Generate visual descriptions of video content asynchronously.
- [Async Generate Summary](https://api-tools.memories.ai/api-reference/transcript/async-summary.md): Generate transcription summary asynchronously.
- [ElevenLabs](https://api-tools.memories.ai/api-reference/transcript/elevenlabs.md): Transcribe audio to text using ElevenLabs Scribe V2 model.
- [Speaker Recognition](https://api-tools.memories.ai/api-reference/transcript/speaker-recognition.md): Generate multi-speaker identification asynchronously.
- [Sync Generate Audio Transcription](https://api-tools.memories.ai/api-reference/transcript/sync-generate-audio.md): Generate audio transcription synchronously.
- [Sync Generate Speaker](https://api-tools.memories.ai/api-reference/transcript/sync-generate-speaker.md): Generate speaker identification synchronously.
- [Instagram Video Caption](https://api-tools.memories.ai/api-reference/video-metadata-transcript/instagram-video-caption.md): Get Instagram video caption.
- [Instagram Video Metadata](https://api-tools.memories.ai/api-reference/video-metadata-transcript/instagram-video-metadata.md): Get Instagram video metadata.
- [Instagram Video Transcript](https://api-tools.memories.ai/api-reference/video-metadata-transcript/instagram-video-transcript.md): Get Instagram video transcript.
- [TikTok Video Caption](https://api-tools.memories.ai/api-reference/video-metadata-transcript/tiktok-video-caption.md): Get TikTok video caption.
- [TikTok Video Metadata](https://api-tools.memories.ai/api-reference/video-metadata-transcript/tiktok-video-metadata.md): Get TikTok video metadata.
- [TikTok Video Transcript](https://api-tools.memories.ai/api-reference/video-metadata-transcript/tiktok-video-transcript.md): Get TikTok video transcript.
- [Twitter Video Caption](https://api-tools.memories.ai/api-reference/video-metadata-transcript/twitter-video-caption.md): Get Twitter video caption.
- [Twitter Video Metadata](https://api-tools.memories.ai/api-reference/video-metadata-transcript/twitter-video-metadata.md): Get Twitter video metadata.
- [Twitter Video Transcript](https://api-tools.memories.ai/api-reference/video-metadata-transcript/twitter-video-transcript.md): Get Twitter video transcript.
- [YouTube Video Caption](https://api-tools.memories.ai/api-reference/video-metadata-transcript/youtube-video-caption.md): Get YouTube video caption.
- [YouTube Video Metadata](https://api-tools.memories.ai/api-reference/video-metadata-transcript/youtube-video-metadata.md): Get YouTube video metadata.
- [YouTube Video Transcript](https://api-tools.memories.ai/api-reference/video-metadata-transcript/youtube-video-transcript.md): Get YouTube video transcript.
- [Video Model Selection](https://api-tools.memories.ai/api-reference/video-model-selection.md): Choose the right video understanding model for your workload
- [Welcome to Memories.ai](https://api-tools.memories.ai/home/overview.md): The complete platform for video understanding, long-term memory, and autonomous agents.
- [Add Memory](https://api-tools.memories.ai/platform/add-memory.md): Create new text memories with content, tags, location, and temporal metadata.
- [API Overview](https://api-tools.memories.ai/platform/api-overview.md): Overview and key concepts of the memories.ai API platform.
- [Get Audio Transcription](https://api-tools.memories.ai/platform/audio-transcription.md): Retrieve the transcription result of a video's audio track using its unique video number.
- [Create your key](https://api-tools.memories.ai/platform/create-your-key.md): Access memories.ai APIs securely using your API key.
- [Delete Videos](https://api-tools.memories.ai/platform/delete-video.md): Safely delete videos from the platform.
- [Download Video](https://api-tools.memories.ai/platform/download-video.md): Download a processed video file from your private library.
- [Error Codes](https://api-tools.memories.ai/platform/error-codes.md): Reference for API error codes and troubleshooting.
- [Get Video Metadata](https://api-tools.memories.ai/platform/get-metadata.md): Fetch the full set of metadata (capture time, camera model, GPS, tags) for a single uploaded video.
- [Get Task Status](https://api-tools.memories.ai/platform/get-task-status.md): Retrieve the processing status and associated video IDs of a submitted parsing task using its task ID.
- [Human Re-identification (ReID)](https://api-tools.memories.ai/platform/human-reid.md): Identify and track people across videos or images using reference images.
- [Image Caption](https://api-tools.memories.ai/platform/image-caption.md): Analyze images and generate captions or descriptions from a URL or uploaded file.
- [Introduction](https://api-tools.memories.ai/platform/introduction.md): Welcome to memories.ai — the next-generation video understanding platform.
- [List Memories](https://api-tools.memories.ai/platform/list-memories.md): Retrieve memories with advanced filtering by content, tags, location, time ranges, and more.
- [List Unique IDs](https://api-tools.memories.ai/platform/list-unique-ids.md): List all unique_id scopes (folders) created under the authenticated account.
- [List Videos](https://api-tools.memories.ai/platform/list-videos.md): Retrieve a paginated list of uploaded videos with optional filtering by name, ID, folder, status, or capture-time metadata (GPS, datetime, camera model, tags).
- [Chat with personal media entities](https://api-tools.memories.ai/platform/personal-media-chat.md): QA your personal media.
- [Quick Start](https://api-tools.memories.ai/platform/quick-start.md): Build your own personal video management and understanding assistant.
- [Rate Limits](https://api-tools.memories.ai/platform/rate-limits.md): API rate limits and usage guidelines.
- [Search clips by image](https://api-tools.memories.ai/platform/search-clips-by-image.md): Locate matching time ranges (clips) within a specific video by uploading a query image plus a natural-language prompt.
- [Search from audio](https://api-tools.memories.ai/platform/search-from-audio.md): Exact-match (LIKE) search over stored audio transcripts in your private library.
- [Search Memories](https://api-tools.memories.ai/platform/search-memories.md): Perform semantic search across memory content using natural language queries.
- [Search from private library](https://api-tools.memories.ai/platform/search-private-video.md): Retrieve relevant video clips, audio moments, or images from your private library using natural-language search.
- [Search from public video sources](https://api-tools.memories.ai/platform/search-public-video.md): Retrieve relevant videos and audio moments from public platforms (TikTok / YouTube / Instagram) using natural-language search.
- [Search for similar images](https://api-tools.memories.ai/platform/search-similar-images.md): Search with images.
- [Upload image from file](https://api-tools.memories.ai/platform/upload-image-from-file.md): Upload one or multiple images to the platform with optional metadata.
- [Upload video from platform creator URL](https://api-tools.memories.ai/platform/upload-video-from-creator.md): Seamlessly upload videos from a creator's main page.
- [Upload video from file](https://api-tools.memories.ai/platform/upload-video-from-file.md): Seamlessly upload videos to the platform for processing and analysis.
- [Upload video from hashtag](https://api-tools.memories.ai/platform/upload-video-from-hashtag.md): Bulk-import videos discovered by hashtag for processing and analysis.
- [Upload video from platform URL](https://api-tools.memories.ai/platform/upload-video-from-platform-url.md): Seamlessly upload videos from social platforms (e.g., TikTok, YouTube, Instagram) via post URLs.
- [Upload video from URL](https://api-tools.memories.ai/platform/upload-video-from-url.md): Seamlessly upload videos to the platform via a direct download link.
- [Video Caption](https://api-tools.memories.ai/platform/video-caption.md): Generate captions and analysis for uploaded or linked videos with optional human re-identification.
- [Video Chat](https://api-tools.memories.ai/platform/video-chat.md): QA your videos.
- [Video Marketer](https://api-tools.memories.ai/platform/video-marketer.md): QA your videos.
- [Get Video Transcription](https://api-tools.memories.ai/platform/video-transcription.md): Retrieve the transcription result of a video using its unique video number.

## OpenAPI Specs

- [openapi](https://api-tools.memories.ai/platform/openapi.json)

## Optional

- [Video Intelligence Console](https://api-platform.memories.ai/stripe)
- [Memories Playground](https://memories.ai/app/)