DEV.co
AI Frameworks · zhouxiaoka

autoclip

AutoClip is a Python-based AI video processing system that automatically downloads videos from YouTube or Bilibili, analyzes them using LLMs to identify highlights, and generates cut clips and compilations. It provides a React web UI for managing projects and processing tasks via a FastAPI backend with Celery job queues.

Source: GitHub — github.com/zhouxiaoka/autoclip
6k
GitHub stars
1.2k
Forks
Python
Primary language
MIT
License (OSI-approved)

Key facts

Objective fields from the source. Values we can't verify are shown as “Unknown” rather than guessed.

FieldValue
Repositoryzhouxiaoka/autoclip
Ownerzhouxiaoka
Primary languagePython
LicenseMIT — OSI-approved
Stars6k
Forks1.2k
Open issues53
Latest releasev1.2.0 (2026-06-03)
Last updated2026-06-03
Sourcehttps://github.com/zhouxiaoka/autoclip

What autoclip is

Full-stack video automation platform: FastAPI backend with Celery/Redis async task queue, SQLite/PostgreSQL database, and React 18 + TypeScript frontend. Uses yt-dlp for download, integrates Alibaba DashScope LLM (Qwen model) for content analysis, FFmpeg for video processing, and WebSocket for real-time progress feedback.

Quickstart

Get the autoclip source

Clone the repository and explore it locally.

terminalbash
git clone https://github.com/zhouxiaoka/autoclip.gitcd autoclip# follow the project's README for install & configuration

Need it deployed, integrated, or customized instead? DEV.co ships production installs.

Best use cases

Content Creator Workflow Automation

Streamline repurposing long-form videos (streams, podcasts, tutorials) into short-form clips for TikTok, YouTube Shorts, or social media by automating highlight detection and clip generation.

Multi-Platform Video Distribution

Automatically download videos from YouTube/Bilibili, intelligently cut highlights, and enable one-click reupload to Bilibili with metadata and account management (feature in development).

Research & Knowledge Extraction

Extract key moments from educational videos, interviews, or webinars; generate timestamped summaries and topic-based compilations for archiving or knowledge management.

Implementation considerations

  • API key provisioning: must obtain and configure Alibaba DashScope (Qwen) API credentials in .env; cost depends on token usage and model selection.
  • Database migration path: shipping SQLite by default suitable for small projects; plan PostgreSQL migration strategy for multi-user or high-concurrency deployments.
  • FFmpeg availability: must be installed and in PATH on host or Docker image; ensure GPU acceleration config if processing 4K or high-volume workloads.
  • WebSocket stability: real-time progress updates rely on Redis + WebSocket; network partition or Redis downtime will break live feedback; plan monitoring and reconnection strategy.
  • Storage footprint: video files, temp transcodes, and project data can consume 10+ GB quickly; implement retention policies and external storage (S3, NAS) if scaling.

When to avoid it — and what to weigh

  • Strict Commercial SLA Requirements — Project is active but not production-hardened; several features (B station upload, subtitle editing, mobile) are marked 'in development' and may not be stable for mission-critical workflows.
  • Windows-Only or Lightweight Deployment — Requires Docker, Redis, FFmpeg, Node.js 16+, Python 3.8+, and 4–8 GB RAM; no native Windows GUI—WSL recommended. Not suitable for single-server, low-resource environments.
  • No LLM Service Access — Core intelligence depends on Alibaba DashScope API (qwen-plus/qwen-turbo models); requires valid API key. Offline or airgapped deployments are not supported.
  • Copyright-Sensitive Use Cases — Tool can download and process videos from any accessible URL; users are responsible for respecting platform ToS and copyright. No built-in digital rights checks.

License & commercial use

MIT License (OSI-approved): permissive, allows commercial and private use, modification, and distribution with attribution and without warranty. No copyleft obligations; can be used in proprietary projects.

MIT license permits commercial use without restrictions. However, commercial viability depends on your own DashScope API costs, infrastructure, and IP concerns regarding video processing (especially if processing user-uploaded or third-party videos). Carefully review platform ToS for YouTube and Bilibili regarding automated download and reupload, especially at scale. Liability or content moderation responsibilities are yours; the tool itself is provided as-is.

DEV.co evaluation signals

Editorial assessment — not user reviews. Directional, with an explicit confidence level.

SignalAssessment
MaintenanceActive
DocumentationStrong
License clarityClear
Deployment complexityModerate
DEV.co fitGood
Assessment confidenceHigh
Security considerations

No explicit security audit or penetration test data provided. Risks include: (1) API key stored in .env file—must use secure vaults in production; (2) SQLite default—no row-level security, plan DB encryption; (3) WebSocket over HTTP (dev) can expose session tokens; (4) Celery task queue unencrypted over Redis by default; (5) no rate limiting or API auth on exposed FastAPI endpoints (beyond B station account selection); (6) file upload endpoint could be vulnerable to path traversal if not carefully validated. Use TLS, strong secrets management, and network isolation for production.

Alternatives to consider

Synthesia / Loom Auto-Clip

Cloud-based, hosted solutions with commercial support and built-in compliance; no self-hosting, lower operational burden, but higher recurring cost and less customization.

Runway ML / Descript

AI-powered video editing with auto-captions and scene detection; more polished UI and multi-media support (audio, images), but broader scope beyond clip extraction and less specialized for highlight detection.

yt-dlp + MoviePy + Custom LLM Script

Lightweight, fully DIY alternative: assemble your own pipeline using yt-dlp for download, MoviePy for cutting, and direct LLM API calls (OpenAI, Anthropic) for analysis. Lower resource footprint but requires engineering time and no pre-built UI.

Software development agency

Build on autoclip with DEV.co software developers

Explore AutoClip's capabilities by deploying it locally or in the cloud. Combine it with Devco's AI application and cloud services for enterprise-grade automation at scale.

Talk to DEV.co

Related open-source tools

Surfaced by semantic similarity across the DEV.co open-source index.

autoclip FAQ

Can I use AutoClip offline or without internet?
No. Core functionality requires Alibaba DashScope API access (Qwen LLM) for content analysis and video platform APIs (YouTube, Bilibili) for download and upload. Airgapped or offline deployments are not supported.
How much does it cost to run AutoClip?
No subscription fee for the software (MIT license). Costs are: (1) DashScope API tokens (~0.01–0.1 USD per video depending on length and model); (2) cloud hosting/compute (Docker, 4–8 GB RAM, 10+ GB storage); (3) optional managed services (PostgreSQL, Redis cloud). Budget $50–500/month for moderate usage.
What LLM models does AutoClip support?
Currently integrated with Alibaba DashScope (Qwen family: qwen-plus, qwen-turbo). Switching or adding other providers (OpenAI, Claude, Llama) requires modifying the LLM manager module; not currently supported out-of-the-box.
Can I upload clips back to YouTube or other platforms?
YouTube: no built-in support—clips are saved locally; you must manually upload or use a third-party tool. Bilibili: planned feature (in development) with automatic account management and one-click upload. Timeline uncertain.

Custom software development services

From first prototype to production, DEV.co delivers software development services around tools like autoclip. Our software development agency staffs experienced software developers and web developers for custom software development, web development, integrations, and ongoing support across ai frameworks and beyond.

Ready to Automate Your Video Editing Workflow?

Explore AutoClip's capabilities by deploying it locally or in the cloud. Combine it with Devco's AI application and cloud services for enterprise-grade automation at scale.