Tagged video

Animate editorial line, bar and range charts with newsroom typography in video

Generate game art images and image-to-video clips through configured media APIs

Turn one character still into a full animated sprite set of image-to-video clips

Build branded YouTube thumbnail image prompts from a video title for Gemini

Write Gemini API code for text, chat, images, video, speech and tools

Build real-time audio and video streaming apps with the Gemini Live API

Turn academic papers into project websites, talk videos and conference posters

Calibrate cameras from recorded MP4 datasets with the AutoMagicCalib API

Author and validate Cosmos Data Factory augmentation configs for video and images

Curate video and image datasets by splitting, deduplicating and captioning them

Generate anomaly event videos from images through the CDF orchestration DAG

Create Cosmos video variants and auto-label source and generated videos

Build video analytics pipelines with DeepStream, TensorRT and Kafka in Python

Build DeepStream inference pipelines for detection, tracking and streaming

Serve a converted LeRobot dataset in the browser to inspect videos and timelines

Run video data augmentation and auto-labeling workflows on OSMO end to end

Fine-tune Cosmos-Embed1 for text-to-video search and semantic deduplication

Fine-tune InternVideo2-CLIP for video-text retrieval and export it to TensorRT

Turn raw videos into chain-of-thought training data, captions and QA pairs

Train, evaluate and export TAO action recognition models on video clips

Find Atlas Cloud image and video models and submit generation requests

Upload and publish TikTok videos, post photos and view profile stats through Composio

Turn a proven UGC video ad into a shot-by-shot script for your own product

Publish and schedule videos and photos to 15 social platforms in one API call

Transcribe speech from local video files and read Douyin share link metadata

Generate images and videos with Wan27 and track generation tasks and credit costs

Pull YouTube transcripts, channel data and video summaries for research

Analyze video comment sections to gauge content quality and find recommendations

Turn your editing style into a reusable skill file for future video edits

Publish image and video posts to Xiaohongshu with login checks and comment actions

Generate images, speech, video and transcripts with TanStack AI media adapters

Transcribe local audio, video and Voice Memos quickly with cached MLX Whisper

Analyze images, video and audio with hosted vision and speech models via MCP

Create an Agent Skill from a teaching video or screen recording

Research a video's claims with sources and deliver an illustrated, cited report

Estimate distance, size, orientation and object counts in images and video

Extract multimodal content from documents, images, audio and video in Python

Turn a video, podcast or newsletter into a week of Instagram reels and carousels

Search the web, images, news and videos with the ddgs Python library and CLI

Boost influencer posts with whitelisting, Spark Ads and repurposed video ads

Write timed TikTok, Reels and Shorts scripts with a hook that holds the first seconds

Build interactive p5.js sketches, generative art and motion graphics as HTML or video

Turn a video, newsletter or transcript into a week of LinkedIn posts

Send Markdown, image, file, voice and video messages to WeCom contacts and groups

Fetch YouTube video transcripts to summarize and analyze talks and tutorials

Generate instrumentals, songs and video scores through Mureka, MiniMax and others

Analyze BPM, beats and song structure to plan beat-synced video cuts

Turn a product into ad angles, hooks, scene outlines and a call to action

Create platform-ready thumbnails and covers from real frames of a video