Podcast Episode Pipeline
Drop a podcast audio file — faster-whisper transcribes with speaker diarisation, LLM generates show notes, chapter markers, pull-quotes, and social-ready highlights, exports as structured DOCX.
这个工作流做什么？
系统流程
Audio ingestion → Faster-Whisper transcription with speaker diarisation → LLM chapter detection & highlight extraction → LLM show notes drafting → Python-DOCX formatted export
管线分解
- Faster-Whisper
faster-whisper— Local speech-to-text transcription with timestamps and speaker turns audio → json - LLM Reasoning
llm— Large-language-model step that extracts, classifies, validates or writes structured output json → json - LLM Reasoning
llm— Large-language-model step that extracts, classifies, validates or writes structured output json → markdown - Python-DOCX
python-docx— Renders the final Word document with headings, tables and styling markdown → docx
工作流信誉评分
基于执行次数、成功率、更新频率、组件质量和用户评分。
基于执行次数、成功率、更新频率、组件质量和用户评分。
使用组件
Local speech-to-text transcription with timestamps and speaker turns
SYSTRAN/faster-whisper ↗Large-language-model step that extracts, classifies, validates or writes structured output
FlowSync proprietaryRenders the final Word document with headings, tables and styling
python-openxml/python-docx ↗与 n8n / Zapier 有什么不同？
与通用工作流构建器不同，FlowSync 工作流在每个节点中预置了 AI 能力——OCR、LLM 推理、转录、超分辨率——不仅仅是 webhook 触发器。每个节点都白盒可审计：你能看到输入、输出和配置。部署即时——无需自托管，无需逐节点配置 API 密钥。
使用场景
- Weekly podcast production
- Interview transcription
- Show notes generation
- Social media clip extraction
作者与来源
用户评价
每期 40 分钟节目，以前手动写 shownotes 要 2 小时。现在跑完 pipeline 只需要核对一下人名拼写，省下大量时间做内容。
数据处理
FlowSync 工作流市场 · 72 分信誉评分 · 30% 执行率 · 99% 成功率 · 4 节点白盒管线 · FlowSync Official 维护
准备好运行了吗？
Drop a podcast audio file — faster-whisper transcribes with speaker diarisation, LLM generates show notes, chapter markers, pull-quotes, and social-ready highlights, exports as structured DOCX.