Communitygithub.com

curiositech/windags-skills

使用 Whisper、Deepgram 和 AssemblyAI 建立音訊轉錄管道,包括說話者分離和即時串流。適用於:轉錄、語音轉文字、說話者分離、音訊處理、會議記錄。不適用於:文字轉語音合成(請見 voice-audio-engineer)、音樂生成(請見 ai-engineer)。

windags-skills 是什麼?

此技能提供一個全面的音訊轉錄管道,整合了 Whisper、Deepgram 和 AssemblyAI 等領先的語音轉文字引擎。它涵蓋了批次處理和即時串流轉錄,並支援說話者分離,非常適合處理會議、講座和訪談。該技能提供了清晰的決策樹,可根據延遲需求、預算、準確性和領域特定術語等因素來選擇最佳引擎。它包括故障排除指南,用於解決幻覺、說話者分離失敗和時間戳偏移等常見問題,並提供完整的逐步實作範例。此外,還定義了品質閘道,以確保字錯誤率 (WER) 低於 5%,以及明確的「不適用」邊界,以防止在文字轉語音或音樂生成等不相關任務上誤用。

相容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/curiositech/windags-skills/tree/HEAD/skills/audio-transcription-pipeline

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

說明文件

音訊轉錄管道

使用 Whisper、Deepgram 和 AssemblyAI 建立生產級的語音轉文字管道,支援批次和即時轉錄,並具備說話者分離功能。

決策點

引擎選擇決策樹

如果需求包括:
├─ 需要即時串流?
│  ├─ 是:使用 Deepgram Nova-3 WebSocket(最快)
│  └─ 否:前往準確性需求
├─ 需要最高準確性 + 有 GPU?
│  ├─ 是:使用 Whisper large-v3 搭配 faster-whisper
│  └─ 否:前往成本分析
├─ 預算 < $0.0059/分鐘 且有運算資源?
│  ├─ 是:使用本地 Whisper
│  └─ 否:使用 AssemblyAI Universal-2(最佳 API 說話者分離)

批次 vs 串流處理

如果音訊特性:
├─ 時長 > 30 分鐘?
│  ├─ 是:使用批次處理並搭配區塊切割(在靜音處分割)
│  └─ 否:前往延遲檢查
├─ 需要 < 10 秒內得到結果?
│  ├─ 是:使用串流(Deepgram/Whisper.cpp)
│  └─ 否:使用批次處理以獲得更好的準確性

VAD(語音活動偵測)使用

如果內容類型:
├─ 即時對話/會議?
│  ├─ 是:啟用 VAD(可節省 40-60% 的靜音運算量)
│  └─ 否:前往內容檢查
├─ 有停頓的講座/簡報?
│  ├─ 是:使用保守的 VAD(min_silence_duration_ms: 1000)
│  └─ 否:跳過 VAD(適用於密集語音,如有聲書等)

按領域選擇模型

如果語言/口音:
├─ 非英語或重口音?
│  ├─ 是:使用 Whisper large-v3(最佳多語言支援)
│  └─ 否:前往速度檢查
├─ 需要 < 1 秒延遲?
│  ├─ 是:使用 Deepgram Nova-3 串流
│  └─ 否:使用 AssemblyAI 處理商業/醫學術語

失敗模式

靜音時產生幻覺

偵測:轉錄稿在安靜時段顯示重複的句子,或出現幻想的音樂描述 診斷:VAD 已停用或閾值過低,模型從背景噪音中產生文字 修復:啟用 VAD,設定 min_silence_duration_ms: 500,在 Whisper 中使用 --no_speech_threshold 0.6

超過 10 位說話者時說話者分離失敗

偵测:10-15 分鐘後所有說話者都被標記為“說話者 1”,或句子中間出現隨機的說話者切換 診斷:說話者嵌入模型飽和,在吵雜音訊中發生重疊混淆 修復:按靜音預先分割,如果音軌是立體聲則使用 AssemblyAI 的 dual_channel,最多限制 8 個活躍說話者

影片時間戳偏移

偵測:字幕在對應影片影格之前/之後 2-5 秒出現 診斷:音訊前處理改變了時長,或 VAD 移除片段時未調整時間戳 修復:在前處理中使用 --preserve_timing,與原始音訊時間碼同步,根據已知語音事件進行驗證

語言自動偵測失敗

侦测:當說話者有口音時,英文單字被轉錄為亂碼,或忽略了語碼轉換 診斷:模型在前 30 秒鎖定了錯誤語言,或多語言內容混淆了分類器 修復:對於有口音的英語,強制設定語言 language="en";對於非英語轉英語,使用 task="translate"

長檔案記憶體溢出

偵測:處理超過 45 分鐘的檔案時發生 OOM 崩潰,或 30 分鐘後突然出現品質下降 診斷:模型保留了完整的上下文視窗,GPU VRAM 耗盡 修復:在 25 分鐘邊界處進行區塊切割,並有 30 秒重疊,使用 --without_timestamps 以提高 RAM 效率

實作範例

完整會議轉錄逐步解說

情境:90 分鐘的董事會會議,6 位說話者,需要準確的說話者識別和時間戳以產出會議記錄

輸入分析:

  • 90 分鐘 → 需要區塊切割
  • 6 位說話者 → 在說話者分離限制內
  • 商業情境 → 使用 AssemblyAI 處理術語

決策路徑:

  1. 時長 > 30 分鐘 → 需要批次處理
  2. 說話者數量 = 6 → 說話者分離可行
  3. 商業領域 → 選擇 AssemblyAI Universal-2
  4. 需要高準確性 → 啟用說話者標籤和智慧格式化

實作:

# 步驟 1:前處理(專家會注意到:標準化音訊音量)
ffmpeg -i meeting.mp4 -ar 16000 -ac 1 -filter:a "volume=0.8" meeting_clean.wav

# 步驟 2:使用重疊進行區塊切割(新手會直接處理整個檔案)
from pydub import AudioSegment
audio = AudioSegment.from_wav("meeting_clean.wav")
chunks = []
for i in range(0, len(audio), 25*60*1000):  # 25 分鐘區塊
    chunk = audio[i:i+27*60*1000]  # 27 分鐘,含 2 分鐘重疊
    chunks.append(chunk)

# 步驟 3:使用說話者分離進行轉錄
results = []
for chunk in chunks:
    response = assemblyai_client.transcribe(
        chunk, speaker_labels=True, auto_punctuation=True,
        dual_channel=False, speaker_labels_max=8
    )
    results.append(response.get_paragraphs())

# 步驟 4:合併重疊片段(專家步驟,新手會忽略)
merged = merge_overlapping_transcripts(results, overlap_seconds=120)

專家 vs 新手:

  • 新手:直接處理 90 分鐘的檔案 → OOM 崩潰或準確性差
  • 專家:使用重疊進行區塊切割,驗證區塊間說話者的一致性,首先標準化音訊

品質閘道

  • WER(字錯誤率)在已知標準答案的測試樣本上 < 5%
  • 說話者準確率 > 90%(在有標準答案的情況下,每個話語的說話者 ID 正確)
  • 即時延遲 < 2 秒(端到端,針對串流實作)
  • SRT/VTT 檔案通過驗證(正確的時間戳,無重疊片段)
  • 音訊前處理完成:確認格式為 16kHz 單聲道 WAV/FLAC
  • VAD 參數已調整:樣本中靜音偵測的誤報率 < 10%
  • 記憶體使用量 < 8GB(針對長達 2 小時的檔案,確認區塊切割正常運作)
  • API 錯誤處理已測試:處理超時、重試和配額超限
  • 說話者分離數與預期相符(±1 位說話者容差)
  • 輸出時間戳與原始音訊的對齊精度在 100ms 內

不適用邊界

此技能不應用於:

  • 文字轉語音合成 → 請改用 voice-audio-engineer
  • 音樂轉錄或歌詞提取 → 請改用 ai-engineer 處理音樂 AI 模型
  • 不經轉錄的音訊分類 → 請改用 ai-engineer 處理音訊分類
  • 即時翻譯(轉錄+翻譯) → 請與 language-translator 技能結合使用
  • 語音生物辨識或說話者識別 → 請改用 ai-engineer 處理說話者辨識模型
  • 音訊品質增強或降噪 → 請改用 voice-audio-engineer 處理音訊處理

以下情況請委派給其他技能:

  • 需要自訂喚醒詞偵測 → voice-audio-engineer
  • 需要音訊指紋辨識 → data-pipeline-engineer
  • 建構語音助理 → voice-audio-engineer + conversation-designer
  • 處理超過 10,000 小時的音訊 → data-pipeline-engineer 負責編排

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

curiositech/windags-skills

Expert in 2000s-era music visualization (Milkdrop, AVS, Geiss) and modern WebGL implementations. Specializes in Butterchurn integration, Web Audio API AnalyserNode FFT data, GLSL shaders for audio-reactive visuals, and psychedelic generative art. Activate on "Milkdrop", "music visualization", "WebGL visualizer", "Butterchurn", "audio reactive", "FFT visualization", "spectrum analyzer". NOT for simple bar charts/waveforms (use basic canvas), video editing, or non-audio visuals.

curiositech/windags-skills

Expert legal research agent for finding and scraping expungement data state by state. Knows authoritative sources, URL patterns, Firecrawl configuration, and 2026 legal landscape.

curiositech/windags-skills

Expert in 3D computer vision labeling tools, workflows, and AI-assisted annotation for LiDAR, point clouds, and sensor fusion. Covers SAM4D/Point-SAM, human-in-the-loop architectures, and vertical-specific training strategies. Activate on '3D labeling', 'point cloud annotation', 'LiDAR labeling', 'SAM 3D', 'SAM4D', 'sensor fusion annotation', '3D bounding box', 'semantic segmentation point cloud'. NOT for 2D image labeling (use clip-aware-embeddings), general ML training (use ml-engineer), video annotation without 3D (use computer-vision-pipeline), or VLM prompt engineering (use prompt-engineer).

curiositech/windags-skills

Implement WCAG 2.2 AA/AAA compliance with automated testing, keyboard navigation, screen reader support, and focus management. Activate on: accessibility audit, WCAG compliance, keyboard navigation, screen reader, aria attributes, axe-core, focus trap. NOT for: design-level accessibility review (use design-accessibility-auditor), color contrast only (use css-in-js-architect).

curiositech/windags-skills

Time-blind friendly planning, executive function support, and daily structure for ADHD brains. Specializes in realistic time estimation, dopamine-aware task design, and building systems that actually work for neurodivergent minds.

curiositech/windags-skills

Designs digital experiences for ADHD brains using neuroscience research and UX principles. Expert in reducing cognitive load, time blindness solutions, dopamine-driven engagement, and compassionate design patterns. Activate on 'ADHD design', 'cognitive load', 'accessibility', 'neurodivergent UX', 'time blindness', 'dopamine-driven', 'executive function'. NOT for general accessibility (WCAG only), neurotypical UX design, or simple UI styling without ADHD context.

curiositech/windags-skills

>- Apply crisis decision-making research to agent routing, uncertainty triage, and coordination failure analysis in time-pressured systems. Use when diagnosing handoff failures, analytical paralysis, or expert judgment under incomplete information. NOT for routine coding, simple CRUD design, or static single-agent tasks with complete information.

curiositech/windags-skills

Extend and modify the admin dashboard, developer portal, and operations console. Use when adding new admin tabs, metrics, monitoring features, or internal tools. Activates for dashboard development, analytics, user management, and internal tooling.

curiositech/windags-skills

Conversation patterns and interaction protocols for multi-agent systems. Covers request/response, pub/sub, blackboard, delegation chains, debate, critique, consensus, fan-out/fan-in, supervisor-worker, and peer negotiation. Deep analysis of AutoGen conversation patterns, CrewAI delegation, LangGraph state passing, and FIPA-ACL performatives. Teaches how to design what agents say to each other and in what order. Activate on: "agent conversation", "agent protocol", "multi-agent debate", "agent delegation", "supervisor worker pattern", "agent voting", "consensus protocol", "fan-out fan-in", "agent negotiation", "blackboard pattern", "agent dialogue", "conversation topology", "agent handoff". NOT for: wire format or serialization (use agent-interchange-formats), orchestration infrastructure (use agentic-infrastructure-2026), single agent behavior (use agentic-patterns).

curiositech/windags-skills

Meta-agent for creating new custom agents, skills, and MCP integrations. Expert in agent design, MCP development, skill architecture, and rapid prototyping. Activate on 'create agent', 'new skill', 'MCP server', 'custom tool', 'agent design'. NOT for using existing agents (invoke them directly), general coding (use language-specific skills), or infrastructure setup (use deployment-engineer).

curiositech/windags-skills

AI-powered calendar management and agent-based scheduling coordination. Covers calendar APIs (Google Calendar, CalDAV/iCal), AI scheduling assistants (Reclaim, Clockwise, Motion, Cal.com), building custom calendar agents with MCP, multi-calendar merging, timezone management, focus block protection, meeting fatigue detection, and agent-to-agent meeting negotiation protocols. Activate on: "calendar agent", "AI scheduling", "calendar coordination", "meeting scheduling", "calendar API", "focus time protection", "calendar optimization", "Google Calendar MCP", "Reclaim", "Clockwise", "Motion", "Cal.com", "smart scheduling", "calendar-aware agent", "timezone scheduling", "agent negotiation meetings". NOT for: manual calendar UI component design (use form-validation-architect), project management scheduling or Gantt charts (use project-management-guru-adhd), general time-tracking or pomodoro apps (use adhd-daily-planner for time-awareness), building the agent itself from scratch (use agent-creator).

curiositech/windags-skills

Build and adopt production AI agent infrastructure in 2026. Covers framework selection (LangGraph, CrewAI, AutoGen, MCP), orchestration patterns, evaluation, observability, memory systems, and tool use. Also covers the SOCIAL dimension: how to sell agent infrastructure internally, change management, measuring ROI, building trust in autonomous systems, and scaling adoption across teams. Activate on: "agent infrastructure", "agent framework comparison", "which agent framework", "sell AI tools internally", "agent adoption", "agent observability", "agent evaluation", "MCP architecture", "agentic mesh", "enterprise AI agents", "AI change management", "agent ROI". NOT for: building specific agents (use ai-engineer), designing agent behavior patterns (use agentic-patterns), prompt tuning (use prompt-engineer).

curiositech/windags-skills

Fundamental patterns for effective agentic behavior. Teaches decomposition, tool orchestration, error recovery, context management, quality self-assessment, and knowing when to stop. Model-agnostic principles that make any agent more effective regardless of domain. Activate on: "how should I structure this agent", "agentic workflow", "agent patterns", "multi-step task", "tool orchestration", "/agentic-patterns", "decompose this", "agent best practices", "chain of actions", "when should the agent stop", "agent loop design". NOT for: creating agent infrastructure (use agent-creator), building DAGs (use windags-architect), specific tool implementation.

curiositech/windags-skills

Automated discovery and matching of agent skills for dynamic task routing and capability assessment

curiositech/windags-skills

Cryptographic security for agentic systems — zero-trust agent networking, signed message envelopes (JWS/JWE), capability-based security (ocaps), Merkle tree audit trails, WASM sandboxing, and formal verification. Covers CLI dev tool security, mTLS between agents, permission boundaries (least privilege for AI agents), and supply chain security for skills/plugins. Activate on: "agent security", "zero trust agents", "secure agent communication", "capability-based security", "ocap", "signed messages between agents", "agent audit trail", "sandbox agent execution", "agent permissions", "mTLS agents", "cryptographic verification", "agent supply chain", "OWASP agentic", "prove agent did X", "tamper-proof agent logs". NOT for: application-level SAST scanning (use security-auditor), network firewall rules (use infrastructure), SOC2/HIPAA compliance (organizational), or prompt injection defense (use prompt-engineer).

curiositech/windags-skills

Data structures and serialization formats for agent-to-agent communication. Covers message envelopes, structured output schemas, capability declarations, task handoff payloads, error/retry signaling, and context windows as data structures. Deep comparison of A2A protocol, MCP, OpenAI function calling, and LangChain message types. Teaches when to use rigid schemas vs free-form with validation, typed vs untyped, streaming vs batch. Activate on: "agent message format", "agent communication schema", "agent-to-agent protocol", "A2A protocol", "MCP message format", "structured output for agents", "agent interop", "interchange format", "agent serialization", "task handoff format", "capability declaration". NOT for: what agents say to each other (use agent-conversation-protocols), orchestration topology (use multi-agent-coordination), building agent infrastructure (use agentic-infrastructure-2026).

curiositech/windags-skills

Logic-based agent programming language implementing BDI architecture for practical autonomous agent development

curiositech/windags-skills

>- Design AgentSpeak(L)-style BDI agents with context-guarded plans, selection functions, and intention stacks. Use for interruptible autonomy, agent policy, and multi-agent orchestration in dynamic environments. NOT for simple rule engines, static planners, or centralized workflows.

curiositech/windags-skills

Foundational concurrent computation model where actors communicate exclusively through asynchronous message passing

curiositech/windags-skills

license: Apache-2.0 NOT for unrelated tasks outside this domain.

相關技能