中文
FreeOffice5 nodes
Score 69

Meeting Minutes Automation

Drop a meeting recording — faster-whisper transcribes it, LLMs structure the minutes, and a polished DOCX with 5-layer detail lands in your downloads.

What does this workflow do?

音频流预处理(降噪/增益/VAD 活性检测)→ Faster-Whisper 高精度转写(带词级时间戳)→ 说话人嵌入向量聚类与分离 → 会议语篇结构分析(开场/议题/讨论/决策/结尾)→ AI 议题抽取与结论提炼 → 待办事项自动分配(负责人+DDL)→ 专业 Word 模板渲染

System flow

音频流预处理(降噪/增益/VAD 活性检测)→ Faster-Whisper 高精度转写(带词级时间戳)→ 说话人嵌入向量聚类与分离 → 会议语篇结构分析(开场/议题/讨论/决策/结尾)→ AI 议题抽取与结论提炼 → 待办事项自动分配(负责人+DDL)→ 专业 Word 模板渲染

Pipeline breakdown

Pillow audio Faster-Whisper audio LLM Reasoning json LLM Reasoning json Python-DOCX json
  1. Pillow pillow — Image pre-processing — deskew, denoise, crop and normalise before analysis audio → audio
  2. Faster-Whisper faster-whisper — Local speech-to-text transcription with timestamps and speaker turns audio → json
  3. LLM Reasoning llm — Large-language-model step that extracts, classifies, validates or writes structured output json → json
  4. LLM Reasoning llm — Large-language-model step that extracts, classifies, validates or writes structured output json → json
  5. Python-DOCX python-docx — Renders the final Word document with headings, tables and styling json → docx

Workflow Reputation Score

Based on executions, success rate, update frequency, component quality, and user rating.

69Overall
★★★★ 4.2
Executions
25
Success rate
96
Update frequency
65
Component quality
88
User rating
84

Based on executions, success rate, update frequency, component quality, and user rating.

Components used

Pillowpillow

Image pre-processing — deskew, denoise, crop and normalise before analysis

python-pillow/Pillow ↗
Faster-Whisperfaster-whisper

Local speech-to-text transcription with timestamps and speaker turns

SYSTRAN/faster-whisper ↗
LLM Reasoningllm

Large-language-model step that extracts, classifies, validates or writes structured output

FlowSync proprietary
Python-DOCXpython-docx

Renders the final Word document with headings, tables and styling

python-openxml/python-docx ↗

How is this different from n8n or Zapier?

Unlike generic workflow builders, FlowSync workflows ship pre-configured with AI skills baked into every node — OCR, LLM reasoning, transcription, super-resolution — not just webhook triggers. Each node is white-box auditable: you see input, output, and config. Deployment is instant — no self-hosting, no API-key per node.

Use cases

  • 日常团队站会/周会
  • 客户访谈录音归档
  • 产品评审会决策追踪
  • 跨部门协调会议同步

Author & Source

This workflow is maintained by the FlowSync team. All components are open-source or commercially licensed. Source code for each component is linked in the Components section above.

Pricing: Free tier available · FREE tier · Official

Field notes

每天 4-6 个会,Otter 每月 $17 还要付费。这个免费版效果一样,还带说话人识别。

— 产品总监 Alex, SaaS 产品总监

客户访谈录音转结构化纪要,一键出 Word。比人工整理节省 90% 时间。

— 咨询经理 Sarah, 战略咨询

技术评审会的决议和待办自动生成,追踪起来特别清晰。

— CTO 老王, 技术公司 CTO

Data handling

音频文件仅在处理过程中临时使用,原始音频完成后即刻清除。转录文本和纪要仅存储于您的账户。不会用于任何 AI 模型训练。敏感会议建议使用私有化部署。

FlowSync Workflow Marketplace · 69 reputation score · 25% execution · 96% success · 5-node white-box pipeline · maintained by FlowSync Official

Ready to run?

Drop a meeting recording — faster-whisper transcribes it, LLMs structure the minutes, and a polished DOCX with 5-layer detail lands in your downloads.