AI-powered video editor that turns raw footage and a creative brief into a polished ad using an ensemble of AI agents (Google Gemini + FFmpeg)
A command-line AI video editor that turns raw footage and a creative brief into a polished ad. Point ave at a folder of clips, describe what you want, and an ensemble of AI agents handles the rest -- scene detection, shot selection, assembly, and quality review.
Built with Google Gemini for intelligence and FFmpeg for rendering.
Status: The CLI is the primary, supported interface. A web UI (AVE Studio) is included but is a work in progress -- see Web UI below.
Raw Footage + Creative Brief
|
[ Preprocess ] -- scene detection, transcription, shot indexing
|
[ Director ] -- AI agent picks shots, orders them, writes an EditPlan
|
[ Trim Refiner ] -- refines shot boundaries for tight cuts
|
[ Editor ] -- renders the EditPlan to video via FFmpeg
|
[ Reviewer ] -- scores the output (adherence, pacing, visual quality, watchability)
| if score < threshold, feeds back to Director and retries
v
Final Video + Review Scores
| Agent | Role | Powered By |
|---|---|---|
| Director | Searches the footage index, selects shots, and produces an EditPlan with trimming, ordering, and text overlays | Google Gemini via ADK |
| Trim Refiner | Adjusts start/end trim points for tighter cuts | Gemini |
| Editor | Renders the EditPlan to an MP4 using FFmpeg/MoviePy | FFmpeg |
| Reviewer | Watches the rendered video and scores it on 5 dimensions (0-1 scale) | Gemini |
Pipelines are defined as YAML manifests in pipelines/. Each step names an agent and optionally a gate or retry condition:
# pipelines/ugc-ad.yaml
steps:
- agent: director
- agent: trim_refiner
- agent: editor
- agent: reviewer
retry_if:
metric: overall
threshold: 0.65 # retry if overall score < 0.65
max_retries: 2 #
Google's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.
Workflows from the Neura Market marketplace related to this Gemini resource