[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6H64E2WCCYAYAFRGMAP2RVW":3,"skill-same:01M6H64E2WCCYAYAFRGMAP2RVW":80},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":53,"commitSha":54,"skillDirectory":55,"forksCount":56,"repositoryHtmlUrl":57,"repositoryHomepageUrl":6,"ownerHtmlUrl":58,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":59,"install":60,"resources":73},"01M6H64E2WCCYAYAFRGMAP2RVW","deepgram-performance-tuning",null,"Optimize Deepgram API performance for faster transcription and lower latency.\nUse when improving transcription speed, reducing latency,\nor optimizing audio processing pipelines.\nTrigger with phrases like \"deepgram performance\", \"speed up deepgram\",\n\"optimize transcription\", \"deepgram latency\", \"deepgram faster\".","micsapp\u002Fmicstec-skills","micsapp","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F82411001?v=4","01M6GWCFQ6D3PV8EHNY62NN5VW","01M6GWCFVE1PA5HG0DKC7AMFJ3",4,"MIT","https:\u002F\u002Fgithub.com\u002Fmicsapp\u002Fmicstec-skills\u002Fblob\u002Fmaster\u002Fclaude-code\u002Fplugins-plus-skills\u002Fplugins\u002Fsaas-packs\u002Fdeepgram-pack\u002Fskills\u002Fdeepgram-performance-tuning\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"performance","tuning","deepgram performance tuning","performance tuning","deepgram","for","openclaw","Audio Processing","processing","io","latency","optimize","up","edit","write","read","Bash","Audio","api","code","2026-11-10 10:12:30",false,"---\nname: deepgram-performance-tuning\ndescription: |\n  Optimize Deepgram API performance for faster transcription and lower latency.\n  Use when improving transcription speed, reducing latency,\n  or optimizing audio processing pipelines.\n  Trigger with phrases like \"deepgram performance\", \"speed up deepgram\",\n  \"optimize transcription\", \"deepgram latency\", \"deepgram faster\".\nallowed-tools: Read, Write, Edit, Bash(gh:*), Bash(curl:*)\nversion: 1.0.0\nlicense: MIT\nauthor: Jeremy Longshore \u003Cjeremy@intentsolutions.io>\ncompatible-with: claude-code, codex, openclaw\n---\n# Deepgram Performance Tuning\n\n## Contents\n- [Overview](#overview)\n- [Prerequisites](#prerequisites)\n- [Instructions](#instructions)\n- [Output](#output)\n- [Error Handling](#error-handling)\n- [Examples](#examples)\n- [Resources](#resources)\n\n## Overview\nOptimize Deepgram integration performance through audio preprocessing (16kHz mono PCM), connection pooling, model selection, streaming for large files, parallel processing, and result caching.\n\n## Prerequisites\n- Working Deepgram integration\n- Performance monitoring in place\n- Audio processing capabilities (ffmpeg)\n- Baseline metrics established\n\n## Instructions\n\n### Step 1: Optimize Audio Format\nPreprocess audio to 16-bit PCM, mono channel, 16kHz sample rate WAV format using ffmpeg. This is optimal for Deepgram's speech models.\n\n### Step 2: Configure Connection Pooling\nCreate a pool of Deepgram clients (min 2, max 10) with acquire timeout and idle timeout. Use `execute()` pattern to auto-acquire and release connections.\n\n### Step 3: Select Optimal Model\nChoose Nova-2 for best accuracy\u002Fspeed balance. Use Base model for cost-sensitive batch jobs. Match model to priority: accuracy, speed, or cost.\n\n### Step 4: Implement Streaming for Large Files\nUse live transcription WebSocket for files over 60 seconds. Stream file data in chunks (1MB) and collect final transcripts.\n\n### Step 5: Enable Parallel Processing\nUse p-limit to process multiple audio files concurrently (default 5). Track per-file timing and total throughput.\n\n### Step 6: Cache Transcription Results\nHash audio URL + options as cache key. Store in Redis with configurable TTL. Return cached results for repeated requests.\n\nSee [detailed implementation](${CLAUDE_SKILL_DIR}\u002Freferences\u002Fimplementation.md) for advanced patterns.\n\n## Output\n- Audio preprocessing pipeline\n- Connection pool with auto-management\n- Model selection engine\n- Streaming transcription for large files\n- Parallel processing with concurrency control\n- Redis-backed result caching\n\n## Error Handling\n| Issue | Cause | Solution |\n|-------|-------|----------|\n| Slow transcription | Wrong audio format | Preprocess to 16kHz mono WAV |\n| Connection exhaustion | No pooling | Use connection pool |\n| High latency | Large files | Switch to streaming |\n| Redundant API calls | No caching | Enable transcription cache |\n\n## Examples\n\n### Performance Factors\n| Factor | Impact | Optimization |\n|--------|--------|--------------|\n| Audio Format | High | 16-bit PCM, mono, 16kHz |\n| File Size | High | Stream large files |\n| Model Choice | High | Balance accuracy vs speed |\n| Concurrency | Medium | Pool connections |\n| Network Latency | Medium | Use closest region |\n\n## Resources\n- [Deepgram Performance Guide](https:\u002F\u002Fdevelopers.deepgram.com\u002Fdocs\u002Fperformance-guide)\n- [Audio Format Best Practices](https:\u002F\u002Fdevelopers.deepgram.com\u002Fdocs\u002Faudio-best-practices)\n- [FFmpeg Documentation](https:\u002F\u002Fffmpeg.org\u002Fdocumentation.html)","# Deepgram Performance Tuning\n\n## Contents\n- [Overview](#overview)\n- [Prerequisites](#prerequisites)\n- [Instructions](#instructions)\n- [Output](#output)\n- [Error Handling](#error-handling)\n- [Examples](#examples)\n- [Resources](#resources)\n\n## Overview\nOptimize Deepgram integration performance through audio preprocessing (16kHz mono PCM), connection pooling, model selection, streaming for large files, parallel processing, and result caching.\n\n## Prerequisites\n- Working Deepgram integration\n- Performance monitoring in place\n- Audio processing capabilities (ffmpeg)\n- Baseline metrics established\n\n## Instructions\n\n### Step 1: Optimize Audio Format\nPreprocess audio to 16-bit PCM, mono channel, 16kHz sample rate WAV format using ffmpeg. This is optimal for Deepgram's speech models.\n\n### Step 2: Configure Connection Pooling\nCreate a pool of Deepgram clients (min 2, max 10) with acquire timeout and idle timeout. Use `execute()` pattern to auto-acquire and release connections.\n\n### Step 3: Select Optimal Model\nChoose Nova-2 for best accuracy\u002Fspeed balance. Use Base model for cost-sensitive batch jobs. Match model to priority: accuracy, speed, or cost.\n\n### Step 4: Implement Streaming for Large Files\nUse live transcription WebSocket for files over 60 seconds. Stream file data in chunks (1MB) and collect final transcripts.\n\n### Step 5: Enable Parallel Processing\nUse p-limit to process multiple audio files concurrently (default 5). Track per-file timing and total throughput.\n\n### Step 6: Cache Transcription Results\nHash audio URL + options as cache key. Store in Redis with configurable TTL. Return cached results for repeated requests.\n\nSee [detailed implementation](${CLAUDE_SKILL_DIR}\u002Freferences\u002Fimplementation.md) for advanced patterns.\n\n## Output\n- Audio preprocessing pipeline\n- Connection pool with auto-management\n- Model selection engine\n- Streaming transcription for large files\n- Parallel processing with concurrency control\n- Redis-backed result caching\n\n## Error Handling\n| Issue | Cause | Solution |\n|-------|-------|----------|\n| Slow transcription | Wrong audio format | Preprocess to 16kHz mono WAV |\n| Connection exhaustion | No pooling | Use connection pool |\n| High latency | Large files | Switch to streaming |\n| Redundant API calls | No caching | Enable transcription cache |\n\n## Examples\n\n### Performance Factors\n| Factor | Impact | Optimization |\n|--------|--------|--------------|\n| Audio Format | High | 16-bit PCM, mono, 16kHz |\n| File Size | High | Stream large files |\n| Model Choice | High | Balance accuracy vs speed |\n| Concurrency | Medium | Pool connections |\n| Network Latency | Medium | Use closest region |\n\n## Resources\n- [Deepgram Performance Guide](https:\u002F\u002Fdevelopers.deepgram.com\u002Fdocs\u002Fperformance-guide)\n- [Audio Format Best Practices](https:\u002F\u002Fdevelopers.deepgram.com\u002Fdocs\u002Faudio-best-practices)\n- [FFmpeg Documentation](https:\u002F\u002Fffmpeg.org\u002Fdocumentation.html)",{"name":5,"author":48,"license":14,"version":49,"description":50,"allowed-tools":51,"compatible-with":52},"Jeremy Longshore \u003Cjeremy@intentsolutions.io>","1.0.0","Optimize Deepgram API performance for faster transcription and lower latency.\nUse when improving transcription speed, reducing latency,\nor optimizing audio processing pipelines.\nTrigger with phrases like \"deepgram performance\", \"speed up deepgram\",\n\"optimize transcription\", \"deepgram latency\", \"deepgram faster\".\n","Read, Write, Edit, Bash(gh:*), Bash(curl:*)","claude-code, codex, openclaw","master","3f5d983eb4ef375b749adcd6b07ec03bd82ae8a8","claude-code\u002Fplugins-plus-skills\u002Fplugins\u002Fsaas-packs\u002Fdeepgram-pack\u002Fskills\u002Fdeepgram-performance-tuning",0,"https:\u002F\u002Fgithub.com\u002Fmicsapp\u002Fmicstec-skills","https:\u002F\u002Fgithub.com\u002Fmicsapp","2026-03-20 11:24:18",{"source":8,"skillName":5,"commands":61,"prompt":71,"zipAvailable":72},[62,65,68],{"tool":63,"command":64},"npx","npx skills add micsapp\u002Fmicstec-skills --skill deepgram-performance-tuning",{"tool":66,"command":67},"bunx","bunx skills add micsapp\u002Fmicstec-skills --skill deepgram-performance-tuning",{"tool":69,"command":70},"pnpm","pnpm dlx skills add micsapp\u002Fmicstec-skills --skill deepgram-performance-tuning","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicsapp\u002Fmicstec-skills\u002Fblob\u002Fmaster\u002Fclaude-code\u002Fplugins-plus-skills\u002Fplugins\u002Fsaas-packs\u002Fdeepgram-pack\u002Fskills\u002Fdeepgram-performance-tuning\u002FSKILL.md",true,[74],{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fimplementation.md","REFERENCE","参考文档",7938,"https:\u002F\u002Fgithub.com\u002Fmicsapp\u002Fmicstec-skills\u002Fblob\u002Fmaster\u002Fclaude-code\u002Fplugins-plus-skills\u002Fplugins\u002Fsaas-packs\u002Fdeepgram-pack\u002Fskills\u002Fdeepgram-performance-tuning\u002Freferences\u002Fimplementation.md",[81,114,143,163,183,207],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":95,"publishedAt":43},"01M6HBTJ02FXBFG9NYEHHYAP52","azure-apim-architecture","Analyzes and explains Azure API Management architecture decisions for enterprise API marketplace implementations using VNet Internal mode, Front Door, hybrid authentication, and multi-environment strategies. Use when discussing APIM component selection, network topology, cost optimization, or comparing alternatives like workspaces vs instances, VNet Internal vs External mode, or Front Door vs Application Gateway.","https:\u002F\u002Fgithub.com\u002Fmicsapp\u002Fmicstec-skills\u002Fblob\u002Fmaster\u002Fcopilot-cli\u002Fcopilot-agent-skills\u002F.github\u002Fskills\u002Fazure-apim-architecture\u002FSKILL.md",[87,90],{"categoryNo":88,"categoryName":89,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":91,"categoryName":92,"taxonomyType":93,"taxonomyTypeDesc":94},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[96,97,98,99,100,101,102,103,104,41,105,106,107,108,109,110,111,112,113,28],"architecture","azure","azure apim architecture","component","authentication","gateway","topology","Optimization","network","team","environment","multi-environment","workspaces","instances","selection","strategies","azure api management","mode",{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":128,"publishedAt":43},"01M6HBT7J4H082JEEA670B3EQ9","apiops-deployment","Guides deployment of Azure API Management infrastructure using Infrastructure as Code (Bicep\u002FTerraform), CI\u002FCD pipelines (GitHub Actions\u002FAzure DevOps), and APIOps workflows. Use when deploying APIM, creating pipelines, or implementing dev→test→prod promotion strategies.","https:\u002F\u002Fgithub.com\u002Fmicsapp\u002Fmicstec-skills\u002Fblob\u002Fmaster\u002Fcopilot-cli\u002Fcopilot-agent-skills\u002F.github\u002Fskills\u002Fapiops-deployment\u002FSKILL.md",[120,121,124,127],{"categoryNo":88,"categoryName":89,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":122,"categoryName":123,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":125,"categoryName":126,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":91,"categoryName":92,"taxonomyType":93,"taxonomyTypeDesc":94},[129,130,131,132,97,133,42,134,135,136,137,138,41,105,111,139,140,112,141,142],"deployment","apiops deployment","workflows","azure devops","infrastructure","infrastructure as code","actions","ci","github actions","github-actions","as","guides","CI\u002FCD","implementing",{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":147,"categories":148,"keywords":150,"publishedAt":43},"01M6HBT2HEA23THNE9E00GYQBE","apim-policy-authoring","Creates production-ready Azure API Management policy XML for authentication (OAuth 2.0, JWT validation, subscription keys), rate limiting, CORS configuration, error handling, and API transformations. Use when implementing API security, access control, or request\u002Fresponse processing logic.","https:\u002F\u002Fgithub.com\u002Fmicsapp\u002Fmicstec-skills\u002Fblob\u002Fmaster\u002Fcopilot-cli\u002Fcopilot-agent-skills\u002F.github\u002Fskills\u002Fapim-policy-authoring\u002FSKILL.md",[149],{"categoryNo":88,"categoryName":89,"taxonomyType":20,"taxonomyTypeDesc":21},[151,152,153,154,97,100,41,105,155,156,157,158,159,160,31,112,161,162,142,28],"policy","authoring","apim policy authoring","security","access","use","ready","api security","Access Control","error","cors configuration","production-ready",{"skillNo":164,"name":165,"nameZh":6,"description":166,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":167,"categories":168,"keywords":171,"publishedAt":43},"01M6HBSY65SB29J9WE9KYD0K6T","api-security-review","Reviews Azure API Management configurations for security vulnerabilities, OWASP API Security Top 10 compliance, VNet Internal mode validation, Private Link verification, and Azure Security Benchmark alignment. Use when performing security audits, pre-deployment validation, or compliance reviews.","https:\u002F\u002Fgithub.com\u002Fmicsapp\u002Fmicstec-skills\u002Fblob\u002Fmaster\u002Fcopilot-cli\u002Fcopilot-agent-skills\u002F.github\u002Fskills\u002Fapi-security-review\u002FSKILL.md",[169,170],{"categoryNo":88,"categoryName":89,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":91,"categoryName":92,"taxonomyType":93,"taxonomyTypeDesc":94},[172,154,173,41,158,174,97,129,175,176,177,178,105,179,112,180,181,182,113,28],"review","security review","api security review","benchmark","verification","owasp","owasp-api","alignment","azure security","reviews","top",{"skillNo":184,"name":185,"nameZh":6,"description":186,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":187,"categories":188,"keywords":189,"publishedAt":43},"01M6HBSRW4PDFE6K4F8JYPZQ05","jira-cli","Interact with Jira from the command line to create, list, view, edit, and transition issues, manage sprints and epics, and perform common Jira workflows. Use when the user asks about Jira tasks, tickets, issues, sprints, or needs to manage project work items.","https:\u002F\u002Fgithub.com\u002Fmicsapp\u002Fmicstec-skills\u002Fblob\u002Fmaster\u002Fcopilot-cli\u002Fawesome-copilot-agents\u002Fskills\u002Fjira-cli\u002FSKILL.md",[],[190,191,192,131,193,194,195,196,41,197,198,199,36,200,201,202,203,204,205,206],"cli","jira","jira cli","init","tasks","create","issues","common","work","command","list","view","project","project work","token","line","sprints",{"skillNo":208,"name":209,"nameZh":6,"description":210,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":211,"categories":212,"keywords":213,"publishedAt":43},"01M6HBSNS3JHMW603G47TWE31H","calculator","Performs arbitrary-precision arithmetic calculations including addition, subtraction, multiplication, division, and exponents. Use when the user asks to calculate, compute, or evaluate math expressions, or when precise decimal arithmetic is needed to avoid floating-point errors.","https:\u002F\u002Fgithub.com\u002Fmicsapp\u002Fmicstec-skills\u002Fblob\u002Fmaster\u002Fcopilot-cli\u002Fawesome-copilot-agents\u002Fskills\u002Fcalculator\u002FSKILL.md",[],[209,214,215,216,217,218,219,156,220,221],"npm","js","calculate","node","math","user","compute","errors"]