This repository is deprecated. All of its content and history has been moved to googleapis/google-cloud-node.
-
Updated
Jul 13, 2023
#
video-intelligence
Here are 19 public repositories matching this topic...
Language: All
Filter by language
Sort: Most stars
Sort options
Use the Moondream 2 model to detect faces and their gaze directions in videos.
-
Updated
Jan 13, 2025 - Python
Context based video seek and search
nodejs google video hackathon seekbar google-cloud-storage google-cloud context video-processing node-js google-cloud-platform google-cloud-vision mlh google-cloud-speech video-search hackathon-project video-search-engine video-intelligence video-intelligence-api google-cloud-text-to-speech
-
Updated
Jul 12, 2023 - JavaScript
A powerful video summarization tool that utilizes Moondream alongside multiple AI models to provide comprehensive video understanding through audio transcription, intelligent frame selection, visual description, and content summarization.
-
Updated
Jan 28, 2025 - Python
Uses Video Intelligence to analyse and edit a video based on a given sentence.
-
Updated
Apr 2, 2022 - Python
Foundational framework for mission-critical surveillance, autonomous video intelligence, and situational awareness.
computer-vision sentinel situational-awareness video-intelligence national-security yolov8 ai-surveillance
-
Updated
Feb 17, 2026 - Python
This tool uses Moondream 2B, a powerful yet lightweight vision-language model, to detect and redact objects from videos. Moondream can recognize a wide variety of objects, people, text, and more with high accuracy while being much smaller than most vision models.
-
Updated
Feb 19, 2025 - Python
Real-time AI agent for querying live courtroom video with sub-500ms latency. Multimodal search combining video intelligence, speech-to-text, and hybrid search. Built with Stream, Twelve Labs, Deepgram, and Gemini Live API.
mcp webrtc video-intelligence gemini-api deepgram hybrid-search vision-agents turbopuffer twelve-labs videodb
-
Updated
Mar 7, 2026 - Python
Local-first video intelligence orchestrator using Intel OpenVINO, Tauri, gRPC, SQLite, and agentic AI routing.
-
Updated
Apr 12, 2026 - Python
UnReel is an AI-powered Video Intelligence engine built to decode the context of any short-form content. It is designed for users who encounter language barriers, missed situational context, or struggle to find resources mentioned in a video via a dedicated video analysis pipeline.
ffmpeg nextjs video-intelligence multimodal rag fastapi yt-dlp analytic-hub openai-whisper generative-ai
-
Updated
Apr 2, 2026 - Python
BRI — empathetic video intelligence with production Streamlit, FastAPI MCP, SQLite durability, and multimodal ML tooling
python ai computer-vision sqlite mcp clean-architecture yolo production-ready enterprise-ready whisper video-analysis video-intelligence multimodal fastapi groq streamlit ai-agent ai-video-analysis repository-hygiene
-
Updated
May 18, 2026 - Python
Multimodal video-to-music recommender. Google Video Intelligence labels + real Spotify audio features (with librosa fallback) + Keras emotion classifier.
python spotify machine-learning tensorflow audio-features keras google-cloud music-recommendation librosa video-intelligence emotion-classification multimodal
-
Updated
May 2, 2026 - Python
Universal video intelligence: turn any video + a prompt into a timestamped timeline, evidence-grounded findings, and structured reports — ready for AI agents.
python ocr ffmpeg mcp openai transcription ai-agents claude video-analysis video-intelligence streamlit yt-dlp
-
Updated
Jun 12, 2026 - Python
This Multimodal AI Agent is a Streamlit application that uses Gemini 2.0 Flash to analyze video content alongside real-time web research. It enables users to upload videos and receive comprehensive, data-driven answers by synthesizing visual insights with live information from the internet.
computer-vision deeplearning ai-agents video-intelligence streamlit multimodal-artifical-intelligence real-time-web-research
-
Updated
Feb 23, 2026 - Python
The missing middle between raw video and reasoning models. Turn video into structured intelligence. Citable, queryable, AI-ready. CLI + MCP server. No Docker. No GPU.
nodejs typescript ocr mcp transcription clip whisper video-understanding ai-agents claude video-intelligence anthropic qwen-vl sam2 model-context-protocol temporal-scene-graph
-
Updated
Jun 5, 2026 - TypeScript
Multimodal video dossiers for agents: transcripts, frames, OCR, evidence, and RAG-ready knowledge.
-
Updated
Jun 19, 2026 - Python
Multimodal video intelligence platform that converts recorded conversations into transcripts, emotion insights, delivery analysis, reaction metadata, and conversation summaries using SpeechBrain, Wav2Vec2, PyTorch, and Streamlit.
nlp machine-learning python3 pytorch speech-recognition audio-processing video-intelligence streamlit wav2vec2 llm multimodal-ai
-
Updated
Jun 2, 2026 - Python
Local-first AI-powered Video Intelligence Workbench for transcript generation, semantic search, evidence-grounded Q&A, multi-video comparison, FAISS retrieval, and research workflows.
python machine-learning ai desktop-application research-tool semantic-search whisper video-analysis video-intelligence faiss machinelearning-python rag knwoledege pyside6 llm local-llm local-ai knowledge-retrieval
-
Updated
Jun 5, 2026 - Python
Google Cloud Video Intelligence API makes videos searchable and discoverable by extracting metadata with an easy-to-use REST API. It enables annotation of videos stored in Google Cloud Storage with video-level, shot-level, and frame-level labels, object tracking, text detection, and explicit content detection.
machine-learning google-cloud object-detection video-analysis video-intelligence content-moderation apis-json naftiko
-
Updated
Jun 20, 2026
Improve this page
Add a description, image, and links to the video-intelligence topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the video-intelligence topic, visit your repo's landing page and select "manage topics."