douyin▌

本技能基于 F2 框架实现抖音视频批量下载，提供高效、稳定的批量下载能力。

这个技能用于自动化发布视频到抖音创作者中心。

Extract, transcribe, and summarize Douyin videos with local whisper.cpp processing. \n \n Handles both short ( v.douyin.com ) and direct Douyin URLs by parsing video IDs and intercepting audio via browser JavaScript \n Uses ffmpeg to convert audio to WAV and whisper.cpp for local Chinese transcription, with automatic Metal GPU acceleration on Apple Silicon \n Generates structured summaries with core points, details, and one-line takeaways in markdown format \n Optional Feishu (Lark) document syn

Automated viral copywriting generator for Douyin with self-optimizing quality control and performance prediction. \n \n Fully automated workflow: reads historical post data, applies nine viral factors, scores across three dimensions, iterates until reaching five-star quality, and predicts view counts without user intervention \n Learns from account history by analyzing past performance metrics, identifying high-performing elements, and recalibrating prediction models based on actual results \n G

Douyin watermark-free video downloader with automatic speech-to-text transcription and file export. \n \n Parses Douyin share links to extract direct download URLs for watermark-free videos without requiring API keys \n Downloads videos locally and extracts speech content via SiliconFlow's SenseVoice API, automatically saving transcripts as Markdown files organized by video ID \n Supports three action modes: info retrieval, video download, and text extraction with optional concurrent video savin

Download Douyin videos and extract metadata using browser automation. \n \n Supports both short links (v.douyin.com) and full Douyin URLs for video retrieval \n Extracts video metadata including title, author, and engagement statistics \n Offers flexible output modes: full video download or metadata-only extraction with custom output directories \n Requires one-time interactive login setup to establish authenticated browser session \n