Communitygithub.com

curiositech/windags-skills

使用 Whisper、Deepgram 和 AssemblyAI 构建音频转录管道,支持说话人区分和实时流式传输,适用于转录、语音转文本、音频处理等场景。

windags-skills 是什么?

该技能提供了一个全面的音频转录管道构建方案,支持 Whisper、Deepgram 和 AssemblyAI 等主流引擎。它涵盖了引擎选择、批处理与流处理对比、语音活动检测(VAD)以及按领域选择模型等决策点,帮助开发者根据具体需求(如实时性、准确性、成本)做出最佳技术选型。此外,技能详细描述了常见故障模式(如静音时幻觉、多人说话人区分崩溃、时间戳漂移等)及其诊断与修复方法,并通过完整的会议转录工作示例展示了从预处理到输出的专家级实施流程。该技能适用于需要高质量语音转文本和说话人区分的开发者和 AI 代理,支持 Python 等主流编程语言,并提供了清晰的质量门控标准以确保输出结果的可信度。

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

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

音频转录管道

使用 Whisper、Deepgram 和 AssemblyAI 构建生产级语音转文本管道,支持批处理和实时转录,并具备说话人区分功能。

决策点

引擎选择决策树

如果需求包括:
├─ 需要实时流式传输?
│  ├─ 是:使用 Deepgram Nova-3 WebSocket(最快)
│  └─ 否:继续检查准确性需求
├─ 需要最高准确性 + 有 GPU?
│  ├─ 是:使用 Whisper large-v3 配合 faster-whisper
│  └─ 否:继续成本分析
├─ 预算 < $0.0059/分钟 且有计算资源?
│  ├─ 是:使用本地 Whisper
│  └─ 否:使用 AssemblyAI Universal-2(最佳 API 说话人区分)

批处理与流处理对比

如果音频特征:
├─ 时长 > 30 分钟?
│  ├─ 是:使用带分块的批处理(在静音处拆分)
│  └─ 否:继续延迟检查
├─ 需要在 < 10 秒内获得结果?
│  ├─ 是:使用流式处理(Deepgram/Whisper.cpp)
│  └─ 否:使用批处理以获得更好的准确性

VAD(语音活动检测)使用

如果内容类型:
├─ 实时对话/会议?
│  ├─ 是:启用 VAD(可节省 40-60% 的静音计算资源)
│  └─ 否:继续内容检查
├─ 有停顿的讲座/演示?
│  ├─ 是:使用保守 VAD(min_silence_duration_ms: 1000)
│  └─ 否:跳过 VAD 用于密集语音(如有声书等)

按领域选择模型

如果语言/口音:
├─ 非英语或口音较重?
│  ├─ 是:使用 Whisper large-v3(最佳多语言支持)
│  └─ 否:继续速度检查
├─ 需要 < 1 秒延迟?
│  ├─ 是:使用 Deepgram Nova-3 流式处理
│  └─ 否:使用 AssemblyAI 处理商业/医学术语

故障模式

静音时幻觉

检测:转录文本在安静段落中显示重复短语,或出现虚假的音乐描述 诊断:VAD 被禁用或阈值过低,模型根据背景噪声生成文本 修复:启用 VAD 并设置 min_silence_duration_ms: 500,在 Whisper 中使用 --no_speech_threshold 0.6

超过 10 个说话人时的说话人区分崩溃

检测:10-15 分钟后所有说话人都被标记为“说话人 1”,或在句子中间出现随机说话人切换 诊断:说话人嵌入模型饱和,拥挤音频中的重叠混淆 修复:按静音预先分段,如果是立体声则使用 AssemblyAI dual_channel,限制最多 8 个活跃说话人

视频时间戳同步漂移

检测:字幕与对应视频帧出现 2-5 秒的偏差 诊断:音频预处理改变了时长,或 VAD 移除了片段但未调整时间戳 修复:在预处理中使用 --preserve_timing,与原始音频时间码同步,对照已知语音事件进行验证

语言自动检测失败

检测:当说话人有口音时,英语单词被转录为乱码,或代码切换被忽略 诊断:模型在前 30 秒内锁定到错误语言,或多语言内容混淆了分类器 修复:对于有口音的英语,强制设置语言为 language="en";对于非英语到英语的转化,使用 task="translate"

长文件内存溢出

检测:文件超过 45 分钟时出现 OOM 崩溃,或 30 分钟后质量突然下降 诊断:模型保留了完整上下文窗口,GPU VRAM 耗尽 修复:在 25 分钟边界处进行分块,并带有 30 秒重叠;使用 --without_timestamps 以提高 RAM 效率

工作示例

完整会议转录演练

场景:90 分钟董事会会议,6 位说话人,需要准确的说话人识别和时间戳以生成会议纪要

输入分析:

  • 90 分钟 → 需要分块
  • 6 位说话人 → 在说话人区分限制内
  • 商业语境 → 使用 AssemblyAI 处理术语

决策路径:

  1. 时长 > 30 分钟 → 需要批处理
  2. 说话人数 = 6 → 可进行说话人区分
  3. 商业领域 → 选择 AssemblyAI Universal-2
  4. 需要高准确性 → 启用说话人标签和智能格式化

实现:

# 步骤 1:预处理(专家注意:标准化音频电平)
ffmpeg -i meeting.mp4 -ar 16000 -ac 1 -filter:a "volume=0.8" meeting_clean.wav

# 步骤 2:带重叠的分块(新手会直接处理整个文件)
from pydub import AudioSegment
audio = AudioSegment.from_wav("meeting_clean.wav")
chunks = []
for i in range(0, len(audio), 25*60*1000):  # 25 分钟分块
    chunk = audio[i:i+27*60*1000]  # 27 分钟,带有 2 分钟重叠
    chunks.append(chunk)

# 步骤 3:带说话人区分的转录
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())

# 步骤 4:合并重叠段落(新手遗漏的专家步骤)
merged = merge_overlapping_transcripts(results, overlap_seconds=120)

专家 vs 新手:

  • 新手:直接处理 90 分钟文件 → OOM 崩溃或准确性差
  • 专家:带重叠分块,验证跨分块的说话人一致性,首先标准化音频

质量门控

  • WER(词错误率)在已知真实数据的测试样本上 < 5%
  • 说话人准确性 > 90%(在有真实数据可用时,每个语句的说话人 ID 正确)
  • 实时流式实现端到端延迟 < 2 秒
  • SRT/VTT 文件通过验证(时间戳正确,无重叠段)
  • 音频预处理完成:确认为 16kHz 单声道 WAV/FLAC 格式
  • VAD 参数已调优:样本上静音检测假阳性率 < 10%
  • 内存使用量 < 8GB,适用于长达 2 小时的文件(分块正常工作)
  • API 错误处理已测试:处理超时、重试和配额超限
  • 说话人区分数量与预期匹配(±1 说话人容差)
  • 输出时间戳与原始音频对齐精度在 100ms 以内

非适用范围边界

此技能不应用于:

  • 文本转语音合成 → 请使用 voice-audio-engineer 技能
  • 音乐转录或歌词提取 → 请使用 ai-engineer 技能处理音乐 AI 模型
  • 无转录的音频分类 → 请使用 ai-engineer 技能进行音频分类
  • 实时翻译(转录 + 翻译) → 请结合 language-translator 技能
  • 语音生物识别或说话人识别 → 请使用 ai-engineer 技能处理语音识别模型
  • 音频质量增强或降噪 → 请使用 voice-audio-engineer 技能处理音频

在以下情况下请委托给其他技能:

  • 需要自定义唤醒词检测 → voice-audio-engineer
  • 需要音频指纹识别 → data-pipeline-engineer
  • 构建语音助手 → voice-audio-engineer + conversation-designer
  • 处理超过 10,000 小时的数据 → data-pipeline-engineer 进行编排

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.

相关技能