Realtime AI News
LibTV Launches AI Video Creation Agent With 100+ Director-Level Skills
LibTV has released a new AI Agent product for video creation, featuring 100+ professional director-level Skills and a canvas-based workflow. Users can generate a complete video from script to final cut with just a single sentence of input.
AI video creation platform LibTV has launched a new Agent product, LibTV Agent, that packs professional video production capabilities into over 100 one-click director-level Skills, aiming to turn the long-promised concept of AI-to-delivery into a practical reality. Users simply input a creative idea into the dialogue box, and the Agent handles the entire pipeline — scriptwriting, storyboarding, image and video generation, editing, subtitles, and soundtrack selection — to produce a finished film.
LibTV Agent's core innovation is the world's largest professional video Agent Skill Hub, containing over 100 AI director Skills. Each Skill encapsulates a specific creative methodology, with workflows for Western-style films, automotive commercials, short dramas, music videos, and self-media content. Users select a Skill and click 'use,' and the Agent executes the entire creative process according to that style's narrative techniques, lighting aesthetics, and editing rhythm, with no manual parameter adjustments or complex prompting required.
The product offers two canvas view modes: a Storyboard mode for managing shots, creativity, and overall pacing, and a Node Workflow mode that displays each processing step with corresponding parameters for fine-grained adjustments. Every operation in the right-side dialogue panel syncs in real-time to the left-side canvas, making the entire generation process visually traceable.
The built-in video editing capabilities include splitting, subtitle addition, region editing, and transitions. Users can modify unsatisfactory segments directly on the canvas without exporting to third-party editing software. The Agent integrates with mainstream AI image and video generation models to ensure visual quality.
Perhaps most notably, LibTV Agent allows users to create custom video creation Skills. Users can select a template, name the Skill, define tasks and outputs, and build a personalized AI production pipeline without writing code. Successful workflows can be saved as reusable custom Skills, ultimately giving each user their own AI Studio.
LibTV Agent is now available on the company's official website. For the AI video industry, this release matters not because it introduces a smarter chatbot, but because it puts director-grade creative capability into the hands of ordinary creators — no AI expertise or editing experience required, from a single sentence to a professional finished film.
Why it matters
LibTV Agent democratizes professional video production through an Agent-plus-Skill model, potentially reshaping the AI video creation landscape by dramatically empowering individual creators.
Nearby Updates
All07/14, 11:56
Honor and Alibaba Reportedly to Announce Partnership Focused on Agentic OS
Multiple Chinese media outlets report that smartphone maker Honor and tech giant Alibaba will officially announce a strategic partnership on July 18, centering on Agentic OS — a next-generation AI-agent-driven operating system. The move signals accelerating integration between handset makers and AI platform companies in the terminal ecosystem.
07/14, 12:02
Xobin Launches NURA, an AI Agent Built for Enterprise Hiring
HR technology company Xobin has unveiled NURA, an AI agent purpose-built for enterprise recruitment. The agent handles the full hiring pipeline from job posting and resume screening to candidate communication and initial assessment, aiming to reduce manual workload for HR teams.
07/14, 10:50
Hong Kong-Listed AI Model Stocks Slide; Zhipu Falls Over 10% Intraday
Shares of Zhipu, one of China's leading large language model companies, plunged more than 10% during Hong Kong trading on July 14. The decline dragged down other AI concept stocks as market sentiment toward big model valuations turned cautious.
07/14, 12:41
12 Chinese AI Models Beat 35 Million Human Fans in World Cup Prediction Contest With 66% Accuracy
Twelve Chinese AI models achieved 66% accuracy in win-draw-lose predictions for the 2026 FIFA World Cup, outperforming 35 million human fans who managed 59%. DeepSeek, Qwen, Hunyuan, and Kimi were among the models that correctly predicted 788 of 1,200 outcomes.