short-video-maker
short-video-maker is an open-source TypeScript tool that automates short-form video generation for TikTok, Instagram Reels, and YouTube Shorts by combining text-to-speech, automatic captions, background videos from Pexels, and music. It runs as both a REST API and Model Context Protocol (MCP) server, designed for faceless video creation without heavy GPU requirements.
Key facts
Objective fields from the source. Values we can't verify are shown as “Unknown” rather than guessed.
| Field | Value |
|---|---|
| Repository | gyoridavid/short-video-maker |
| Owner | gyoridavid |
| Primary language | TypeScript |
| License | MIT — OSI-approved |
| Stars | 1.2k |
| Forks | 392 |
| Open issues | 27 |
| Latest release | Unknown |
| Last updated | 2025-06-21 |
| Source | https://github.com/gyoridavid/short-video-maker |
What short-video-maker is
Built in TypeScript, the tool chains Kokoro TTS for speech synthesis, Whisper.cpp for caption generation, Pexels API for stock footage, and Remotion for video composition. It exposes REST endpoints and MCP server interfaces, with Docker deployment (tiny/normal/CUDA variants) for resource-constrained environments, requiring ≥3GB RAM, ≥2 vCPU, ≥5GB disk, and a free Pexels API key.
Get the short-video-maker source
Clone the repository and explore it locally.
git clone https://github.com/gyoridavid/short-video-maker.gitcd short-video-maker# follow the project's README for install & configurationNeed it deployed, integrated, or customized instead? DEV.co ships production installs.
Best use cases
Implementation considerations
- Require and validate a free Pexels API key before deployment; requests will fail without it. Rate limits and video availability depend on Pexels' current catalog and API quota.
- Memory and CPU tuning is critical: Docker tiny image uses q4 quantized models and CONCURRENCY=1 to avoid OOM; estimate render time 2–5 minutes per video depending on complexity and hardware.
- Platform support is Linux (Ubuntu ≥22.04) and macOS only; Windows is explicitly unsupported due to whisper.cpp build failures. Plan infrastructure accordingly.
- Choose appropriate Whisper model (tiny.en, base.en, medium.en with CUDA) based on accuracy needs and available RAM. Smaller models trade accuracy for speed and memory.
- FFmpeg, Node.js 22+, and system libraries (libsdl2-dev, libnss3, libdbus-1-3, etc.) are required for npm installation; Docker handles these transparently.
When to avoid it — and what to weigh
- Multi-Language Narration Required — Project only supports English voiceover; Kokoro-js lacks multi-language support. Not suitable if you need narration in Spanish, Mandarin, French, or other languages without external TTS integration.
- AI-Generated Video Synthesis from Prompts — Does not generate novel video content from image prompts or AI models. It composites existing Pexels stock footage—not a generative tool. If you need synthetic or AI-rendered visuals, this is not the solution.
- Production Environments with SLA Requirements — Project is young (created April 2025, last push June 2025), lacks formal release versioning, and has 27 open issues. Not recommended for mission-critical systems requiring stability guarantees or vendor support.
- Resource-Constrained Devices — Minimum 3GB RAM and 2 vCPU; Remotion rendering and Whisper inference are memory-intensive. Not suitable for embedded systems, serverless (Lambda) at scale, or devices with <2GB available RAM.
License & commercial use
MIT License (permissive open-source). Permits commercial use, modification, and redistribution with minimal restrictions (retain copyright and license notice). No viral copyleft obligations; can be used in proprietary products.
MIT License explicitly allows commercial use. However, verify that all dependencies (Kokoro TTS, Whisper.cpp, Remotion, Pexels API) comply with your commercial use case. Pexels API has its own terms; review video usage rights for your platform before monetizing content.
DEV.co evaluation signals
Editorial assessment — not user reviews. Directional, with an explicit confidence level.
| Signal | Assessment |
|---|---|
| Maintenance | Active |
| Documentation | Adequate |
| License clarity | Clear |
| Deployment complexity | Low |
| DEV.co fit | Good |
| Assessment confidence | Medium |
Pexels API key is passed via environment variables; ensure secrets management (vault, K8s secrets, env file restrictions) in production. REST API and MCP server are unauthenticated by default; apply network segmentation or reverse-proxy authentication in production. No mention of input validation against script injection in text prompts or search terms. Whisper.cpp and Kokoro TTS are local (no external data exfiltration), but review Remotion's rendering sandbox if handling untrusted input.
Alternatives to consider
Synthesia / Pictory / Descript
Commercial SaaS platforms with multi-language TTS, AI avatars, and production-grade support. Best if you need non-English narration, human avatars, or want to avoid self-hosting. Higher cost; vendor lock-in.
RunwayML / Pika / Haiper
AI video generation from prompts; creates synthetic visuals. Better if you need novel, AI-rendered content rather than stock footage composition. Requires GPU/cloud compute; not self-hosted.
FFmpeg + Open Source TTS (Coqui, gTTS, Bark)
DIY low-code approach using FFmpeg CLI and open-source TTS. More control, minimal dependencies, but requires scripting expertise and manual orchestration. No built-in captions, Pexels search, or MCP protocol.
Build on short-video-maker with DEV.co software developers
Evaluate short-video-maker for your content pipeline. Deploy with Docker in minutes. Pair with n8n or custom automation for enterprise-scale faceless video generation. Contact our team to plan your integration.
Talk to DEV.coRelated open-source tools
Surfaced by semantic similarity across the DEV.co open-source index.
Related on DEV.co
Explore the category and the services that help you build with it.
short-video-maker FAQ
Can I use this for commercial YouTube monetization?
How long does it take to generate one video?
Can I run this on AWS Lambda or serverless?
What if Pexels returns no relevant videos for my search term?
Software developers & web developers for hire
Adopting short-video-maker is usually one piece of a larger software development effort. As a software development agency, DEV.co provides software development services and web development expertise — pairing senior software developers and web developers with your team to design, build, and operate mcp servers software in production.
Ready to Automate Video Production?
Evaluate short-video-maker for your content pipeline. Deploy with Docker in minutes. Pair with n8n or custom automation for enterprise-scale faceless video generation. Contact our team to plan your integration.