lcy362/agnes-video-generator

What it solves

It removes the high financial and hardware barriers to AI video creation. Unlike commercial tools that require expensive monthly subscriptions or high-end GPUs for local execution, this project provides a free, open-source way to generate multi-scene videos with narration and subtitles using cloud-based AI compute.

How it works

The tool connects to Agnes AI's free cloud models via API keys. Because the compute happens in the cloud, users can run the software on a standard laptop. It automates the pipeline of turning a text idea or a long manuscript into a series of video clips, then adds AI-generated text-to-speech (TTS) narration and word-level subtitles to create a finished production.

Who it’s for

Content creators and hobbyists who want to create AI-generated videos without paying for subscriptions or owning professional-grade hardware.

Highlights

• Multiple Generation Modes: Supports text-to-video, image-to-video, manuscript-to-video (which splits long scripts into segments), and digital anchor videos.
• Advanced Controls: Includes keyframe animation and the ability to resume generation from checkpoints.
• Integrated Production: Built-in TTS narration and automatic subtitle generation.
• Flexible Deployment: Can be run locally via Python, Docker, or npm, or used through a browser-based studio.
• Zero Cost: No subscriptions, no usage limits (beyond a rate limit of 16 requests per minute), and no watermarks.