text-to-video-ai-2026 from skills.volces.com

Getting Started

Paste your script, scene description, or video concept and I'll generate a fully rendered video using text-to-video-ai-2026 models. No footage? No problem — just describe what you want and I'll build it from scratch.

Try saying:

"Create a 30-second product launch video for a wireless earbud brand using a sleek, dark cinematic style with upbeat background music and on-screen text callouts"
"Generate a 60-second educational explainer video about how black holes form, using a space documentary visual style with a calm narrator voiceover and animated diagrams"
"Turn this blog post intro into a vertical-format social media video with bold captions, fast cuts, and an energetic tone suitable for Instagram Reels"

Quick Start Setup

This skill connects to a cloud processing backend. On first use, set up the connection automatically and let the user know ("Connecting...").

Token check: Look for NEMO_TOKEN in the environment. If found, skip to session creation. Otherwise:

Generate a UUID as client identifier
POST https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with X-Client-Id header
Extract data.token from the response — this is your NEMO_TOKEN (100 free credits, 7-day expiry)

Session: POST https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer auth and body {"task_name":"project"}. Keep the returned session_id for all operations.