rfdiosuao/voxcpm-video-maker — explained in plain English
Analysis updated 2026-05-18
Automatically generate a daily AI news video from headlines with narration and animated scenes.
Produce a locally voiced video without relying on any external text to speech API.
Rotate between five distinct visual styles so a daily video series does not look repetitive.
Validate audio and video sync and check for black frames before publishing a rendered clip.
| rfdiosuao/voxcpm-video-maker | 0xhassaan/nn-from-scratch | 3ks/embedoc | |
|---|---|---|---|
| Stars | 0 | 0 | — |
| Language | Python | Python | Python |
| Last pushed | — | — | 2023-06-08 |
| Maintenance | — | — | Dormant |
| Setup difficulty | hard | moderate | hard |
| Complexity | 4/5 | 4/5 | 1/5 |
| Audience | developer | developer | developer |
Figures from each repo's GitHub metadata at analysis time.
Requires Node.js, Python, FFmpeg, HyperFrames, and a locally downloaded VoxCPM voice model.
VoxCPM Video Maker is an automation tool that produces short AI news videos from start to finish with a single command. It is designed as a skill, a reusable workflow, for the Trae SOLO AI assistant. Given a date, the tool fetches the day's AI industry headlines from an online source called AI HOT, writes a narration script, generates spoken audio using a local text to speech model called VoxCPM, builds animated video scenes from HTML templates, and renders everything into a finished 1920x1080 video file with audio synchronized to the visuals. The rendering pipeline converts each video scene, expressed as an HTML file with animations, into video frames using a tool called HyperFrames. Scene durations adjust dynamically to match the actual length of the recorded narration, keeping spoken words and visuals aligned to within 0.2 seconds. A quality check step then scans the output for black frames using FFmpeg. Five visual style presets are available and rotate daily so consecutive videos do not look identical. The styles include Signal Radar, a radar scan look for breaking news, Deep Space Briefing, a space theme for model releases, Command Center, a terminal and dashboard aesthetic for tool updates, Magazine Motion, an editorial layout for daily roundups, and Neon Dataflow, flowing lines and particles for technical stories. The stack is Python and PowerShell for orchestration, Node.js for running HyperFrames, FFmpeg for audio and video processing, VoxCPM 2.0 or higher for local voice generation, GSAP and Anime.js for in-scene animation, and AI HOT as the news data source. Python 3.10 or higher and Node.js 18 or higher are required.
An automation tool that turns daily AI news headlines into a fully rendered, narrated video with animated scenes, using a local text to speech model and one command.
Mainly Python. The stack also includes Python, Node.js, PowerShell.
MIT license: free to use, modify, and distribute, including commercially, as long as the copyright notice is kept.
Setup difficulty is rated hard, with roughly 1h+ to a first successful run.
Mainly developer.
This repo across BitVibe Labs
Verify against the repo before relying on details.