Getting Started

Welcome to the AI Gemini Video Editor — your intelligent editing assistant that understands your footage and turns your ideas into polished video content. Drop your video or describe your project and let's start editing!

Try saying:

• "I have a 12-minute product walkthrough video. Can you identify the 5 most important moments and suggest where to cut it down to under 3 minutes for social media?"
• "Generate accurate subtitles for this video and reformat the captions to fit a vertical 9:16 TikTok layout with bold on-screen text styling."
• "Analyze this talking-head interview and rewrite the spoken script into a tighter narrative — remove filler words, redundant sections, and suggest a stronger opening hook."

First-Time Connection

When a user first opens this skill, connect to the processing backend automatically. Briefly let them know (e.g. "Setting up...").

Authentication: Check if NEMO_TOKEN is set in the environment. If it is, skip to step 2.

1. Obtain a free token: Generate a random UUID as client identifier. POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id set to that UUID. The response data.token is your NEMO_TOKEN — 100 free credits, valid 7 days.
2. Create a session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Authorization: Bearer <token>, Content-Type: application/json, and body {"task_name":"project","language":"<detected>"}. Store the returned session_id for all subsequent requests.

Keep setup communication brief. Don't display raw API responses or token values to the user.

Edit Smarter, Not Harder With Gemini AI

The AI Gemini Video Editor brings the power of Google's Gemini multimodal model directly into your editing workflow. Instead of manually scrubbing through timelines, you describe what you want — and the skill interprets your footage, identifies key moments, and delivers actionable edits, structured scripts, and scene-level suggestions.

Whether you're cutting a 45-minute interview down to a punchy 3-minute highlight reel, adding context-aware subtitles to a product demo, or restructuring a tutorial for better audience retention, this skill understands the content of your video — not just its metadata. It reads scenes, spoken words, visual cues, and pacing to give you edits that actually make sense.

This is built for solo creators, small marketing teams, online educators, and social media managers who produce video regularly but don't have the time or budget for professional post-production. The AI Gemini Video Editor shortens the gap between raw footage and publish-ready content dramatically.

Gemini Routing Your Edit Requests

Every prompt you send — whether trimming a clip, generating captions, or applying a scene transition — gets parsed by Gemini's multimodal understanding layer and routed to the appropriate video processing pipeline automatically.