[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CHPKC25FPYBWTKV8FV3STR":3,"skill-same:01M7CHPKC25FPYBWTKV8FV3STR":51},{"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":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":30,"commitSha":31,"skillDirectory":32,"forksCount":13,"repositoryHtmlUrl":33,"repositoryHomepageUrl":34,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":36,"install":37,"resources":50},"01M7CHPKC25FPYBWTKV8FV3STR","azure-speech-to-text",null,"Transcribe audio to text using Azure AI Speech (Fast Transcription REST API). Use when converting audio\u002Fvideo to text, generating subtitles, or processing spoken content in OpenMontage. Optional cloud STT provider — preferred when AZURE_SPEECH_KEY is configured; the local faster-whisper `transcriber` is the default offline path.","makemoney2023\u002Fabracadabra","makemoney2023","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F124006256?v=4","01M79SG90P20MHWQ1HA5ZD90F0","01M7CF7A8BKNCV8QDVPQTM37GD",0,"MIT","https:\u002F\u002Fgithub.com\u002Fmakemoney2023\u002Fabracadabra\u002Fblob\u002Fmain\u002F.cursor\u002Fskills\u002Fcommunity\u002Fopenmontage\u002F.claude\u002Fskills\u002Fazure-speech-to-text\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: azure-speech-to-text\ndescription: Transcribe audio to text using Azure AI Speech (Fast Transcription REST API). Use when converting audio\u002Fvideo to text, generating subtitles, or processing spoken content in OpenMontage. Optional cloud STT provider — preferred when AZURE_SPEECH_KEY is configured; the local faster-whisper `transcriber` is the default offline path.\nlicense: MIT\ncompatibility: Requires internet access and an Azure AI Speech resource (AZURE_SPEECH_KEY + AZURE_SPEECH_REGION).\nmetadata: {\"openclaw\": {\"requires\": {\"env\": [\"AZURE_SPEECH_KEY\", \"AZURE_SPEECH_REGION\"]}, \"primaryEnv\": \"AZURE_SPEECH_KEY\"}}\n---\n\n# Azure AI Speech — Speech-to-Text\n\nTranscribe audio to text with **Azure Fast Transcription** — synchronous,\nword-level timestamps, speaker diarization, and multi-language identification.\nIn OpenMontage this is exposed through the `azure_stt` tool (`capability=analysis`,\n`provider=azure`). It is an **optional cloud STT provider** — when\n`AZURE_SPEECH_KEY` is configured, prefer it for cloud transcription. The local\n`transcriber` tool (faster-whisper) remains the **default offline path** and the\nfallback when Azure is unavailable.\n\n> Docs: [Fast Transcription](https:\u002F\u002Flearn.microsoft.com\u002Fazure\u002Fai-services\u002Fspeech-service\u002Ffast-transcription-create) · [Speech service overview](https:\u002F\u002Flearn.microsoft.com\u002Fazure\u002Fai-services\u002Fspeech-service\u002Fspx-overview)\n\n## Why Fast Transcription (not Batch)\n\nAzure exposes three STT surfaces. OpenMontage uses **Fast Transcription** because\nthe pipeline transcribes **local audio files**:\n\n| Surface | Input | Latency | Needs |\n|---------|-------|---------|-------|\n| **Fast Transcription** (used here) | local file, multipart POST | synchronous, sub-real-time | key + region |\n| Batch Transcription | audio at a URL (Blob + SAS) | async job + polling | Blob storage plumbing |\n| Speech SDK (`spx`) | mic \u002F stream \u002F file | streaming | native `azure-cognitiveservices-speech` package |\n\nFast Transcription needs no Blob storage, no SAS URLs, and no native SDK — just\n`requests` and the two env vars.\n\n## Setup\n\nCreate a **Speech** resource in the [Azure portal](https:\u002F\u002Fportal.azure.com);\ncopy the key and region from its **Keys and Endpoint** page.\n\n```bash\nexport AZURE_SPEECH_KEY=your_speech_resource_key\nexport AZURE_SPEECH_REGION=eastus          # your resource's region\n# export AZURE_SPEECH_ENDPOINT=https:\u002F\u002F...  # optional: overrides region\n```\n\n`azure_stt` reports `AVAILABLE` once `AZURE_SPEECH_KEY` plus either\n`AZURE_SPEECH_REGION` or `AZURE_SPEECH_ENDPOINT` are set.\n\n## Using it in a pipeline\n\nPrefer `azure_stt` over `transcriber` unless the run must be offline. Its output\nmatches the `transcriber` schema exactly, so it is a drop-in for `subtitle_gen`\nand any stage that consumes a transcript.\n\n```python\nfrom tools.tool_registry import registry\nregistry.discover()\nstt = registry._tools[\"azure_stt\"]\n\nresult = stt.execute({\n    \"input_path\": \"projects\u002Fmy-video\u002Fassets\u002Faudio\u002Fnarration.mp3\",\n    # \"language\": \"en\",          # ISO 639-1 or BCP-47 (\"en-US\"); omit for auto-ID\n    # \"diarize\": True,           # speaker labels, no HuggingFace token needed\n    # \"max_speakers\": 4,\n    \"output_dir\": \"projects\u002Fmy-video\u002Fartifacts\",\n})\nif result.success:\n    segs = result.data[\"segments\"]          # [{id,start,end,text,words:[...]}]\n    words = result.data[\"word_timestamps\"]  # flat [{word,start,end,probability}]\n```\n\nIf `azure_stt` is unavailable (no key) or errors, fall back to `transcriber`\n(local whisper) — its `execute` signature and output are identical.\n\n## Parameters that matter\n\n- **`language`** — pass an ISO code (`\"en\"`) or a full locale (`\"en-US\"`). Pin it\n  when you know the language; it is faster and more accurate than auto-ID.\n- **`candidate_locales`** — when `language` is omitted, Azure runs language\n  identification across this shortlist. Narrow it to the languages you actually\n  expect; a huge list slows detection and invites misclassification.\n- **`diarize` \u002F `max_speakers`** — enable for multi-speaker audio (interviews,\n  podcasts). Set `max_speakers` to the real upper bound.\n- **`profanity_filter`** — `None` | `Masked` (default) | `Removed` | `Tags`.\n\n## Response shape (mapped to the transcriber schema)\n\nThe raw Azure response (`phrases[]` with `offsetMilliseconds` \u002F `words[]`) is\nconverted to seconds and the OpenMontage transcript schema:\n\n```json\n{\n  \"segments\": [\n    {\"id\": 0, \"start\": 0.0, \"end\": 2.4, \"text\": \"Hello world\",\n     \"speaker\": 1,\n     \"words\": [{\"word\": \"Hello\", \"start\": 0.0, \"end\": 0.5, \"probability\": 0.98}]}\n  ],\n  \"word_timestamps\": [{\"word\": \"Hello\", \"start\": 0.0, \"end\": 0.5, \"probability\": 0.98}],\n  \"language\": \"en-US\",\n  \"duration_seconds\": 2.4,\n  \"provider\": \"azure\"\n}\n```\n\nNote: Fast Transcription has no *per-word* confidence, so each word carries the\n**phrase** confidence in `probability`.\n\n## Limits & tips\n\n- Single file up to ~2 hours \u002F a few hundred MB per request. For longer or bulk\n  jobs, use Azure Batch Transcription instead.\n- Send clean audio (16 kHz+ mono is plenty). Transcode video to audio first if\n  you only need speech — smaller upload, same result.\n- Verify timing: word timestamps drive subtitle cues in `subtitle_gen`. Spot-check\n  the first and last cues against the source audio.\n","# Azure AI Speech — Speech-to-Text\n\nTranscribe audio to text with **Azure Fast Transcription** — synchronous,\nword-level timestamps, speaker diarization, and multi-language identification.\nIn OpenMontage this is exposed through the `azure_stt` tool (`capability=analysis`,\n`provider=azure`). It is an **optional cloud STT provider** — when\n`AZURE_SPEECH_KEY` is configured, prefer it for cloud transcription. The local\n`transcriber` tool (faster-whisper) remains the **default offline path** and the\nfallback when Azure is unavailable.\n\n> Docs: [Fast Transcription](https:\u002F\u002Flearn.microsoft.com\u002Fazure\u002Fai-services\u002Fspeech-service\u002Ffast-transcription-create) · [Speech service overview](https:\u002F\u002Flearn.microsoft.com\u002Fazure\u002Fai-services\u002Fspeech-service\u002Fspx-overview)\n\n## Why Fast Transcription (not Batch)\n\nAzure exposes three STT surfaces. OpenMontage uses **Fast Transcription** because\nthe pipeline transcribes **local audio files**:\n\n| Surface | Input | Latency | Needs |\n|---------|-------|---------|-------|\n| **Fast Transcription** (used here) | local file, multipart POST | synchronous, sub-real-time | key + region |\n| Batch Transcription | audio at a URL (Blob + SAS) | async job + polling | Blob storage plumbing |\n| Speech SDK (`spx`) | mic \u002F stream \u002F file | streaming | native `azure-cognitiveservices-speech` package |\n\nFast Transcription needs no Blob storage, no SAS URLs, and no native SDK — just\n`requests` and the two env vars.\n\n## Setup\n\nCreate a **Speech** resource in the [Azure portal](https:\u002F\u002Fportal.azure.com);\ncopy the key and region from its **Keys and Endpoint** page.\n\n```bash\nexport AZURE_SPEECH_KEY=your_speech_resource_key\nexport AZURE_SPEECH_REGION=eastus          # your resource's region\n# export AZURE_SPEECH_ENDPOINT=https:\u002F\u002F...  # optional: overrides region\n```\n\n`azure_stt` reports `AVAILABLE` once `AZURE_SPEECH_KEY` plus either\n`AZURE_SPEECH_REGION` or `AZURE_SPEECH_ENDPOINT` are set.\n\n## Using it in a pipeline\n\nPrefer `azure_stt` over `transcriber` unless the run must be offline. Its output\nmatches the `transcriber` schema exactly, so it is a drop-in for `subtitle_gen`\nand any stage that consumes a transcript.\n\n```python\nfrom tools.tool_registry import registry\nregistry.discover()\nstt = registry._tools[\"azure_stt\"]\n\nresult = stt.execute({\n    \"input_path\": \"projects\u002Fmy-video\u002Fassets\u002Faudio\u002Fnarration.mp3\",\n    # \"language\": \"en\",          # ISO 639-1 or BCP-47 (\"en-US\"); omit for auto-ID\n    # \"diarize\": True,           # speaker labels, no HuggingFace token needed\n    # \"max_speakers\": 4,\n    \"output_dir\": \"projects\u002Fmy-video\u002Fartifacts\",\n})\nif result.success:\n    segs = result.data[\"segments\"]          # [{id,start,end,text,words:[...]}]\n    words = result.data[\"word_timestamps\"]  # flat [{word,start,end,probability}]\n```\n\nIf `azure_stt` is unavailable (no key) or errors, fall back to `transcriber`\n(local whisper) — its `execute` signature and output are identical.\n\n## Parameters that matter\n\n- **`language`** — pass an ISO code (`\"en\"`) or a full locale (`\"en-US\"`). Pin it\n  when you know the language; it is faster and more accurate than auto-ID.\n- **`candidate_locales`** — when `language` is omitted, Azure runs language\n  identification across this shortlist. Narrow it to the languages you actually\n  expect; a huge list slows detection and invites misclassification.\n- **`diarize` \u002F `max_speakers`** — enable for multi-speaker audio (interviews,\n  podcasts). Set `max_speakers` to the real upper bound.\n- **`profanity_filter`** — `None` | `Masked` (default) | `Removed` | `Tags`.\n\n## Response shape (mapped to the transcriber schema)\n\nThe raw Azure response (`phrases[]` with `offsetMilliseconds` \u002F `words[]`) is\nconverted to seconds and the OpenMontage transcript schema:\n\n```json\n{\n  \"segments\": [\n    {\"id\": 0, \"start\": 0.0, \"end\": 2.4, \"text\": \"Hello world\",\n     \"speaker\": 1,\n     \"words\": [{\"word\": \"Hello\", \"start\": 0.0, \"end\": 0.5, \"probability\": 0.98}]}\n  ],\n  \"word_timestamps\": [{\"word\": \"Hello\", \"start\": 0.0, \"end\": 0.5, \"probability\": 0.98}],\n  \"language\": \"en-US\",\n  \"duration_seconds\": 2.4,\n  \"provider\": \"azure\"\n}\n```\n\nNote: Fast Transcription has no *per-word* confidence, so each word carries the\n**phrase** confidence in `probability`.\n\n## Limits & tips\n\n- Single file up to ~2 hours \u002F a few hundred MB per request. For longer or bulk\n  jobs, use Azure Batch Transcription instead.\n- Send clean audio (16 kHz+ mono is plenty). Transcode video to audio first if\n  you only need speech — smaller upload, same result.\n- Verify timing: word timestamps drive subtitle cues in `subtitle_gen`. Spot-check\n  the first and last cues against the source audio.\n",{"name":5,"license":14,"metadata":23,"description":7,"compatibility":29},{"openclaw":24},{"requires":25,"primaryEnv":27},{"env":26},[27,28],"AZURE_SPEECH_KEY","AZURE_SPEECH_REGION","Requires internet access and an Azure AI Speech resource (AZURE_SPEECH_KEY + AZURE_SPEECH_REGION).","main","a874417cb217f3c48ed2cf2e347260f83bda80f3",".cursor\u002Fskills\u002Fcommunity\u002Fopenmontage\u002F.claude\u002Fskills\u002Fazure-speech-to-text","https:\u002F\u002Fgithub.com\u002Fmakemoney2023\u002Fabracadabra","https:\u002F\u002Fabracadabra-lovat.vercel.app","https:\u002F\u002Fgithub.com\u002Fmakemoney2023","2026-10-26 09:15:55",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add makemoney2023\u002Fabracadabra --skill azure-speech-to-text",{"tool":43,"command":44},"bunx","bunx skills add makemoney2023\u002Fabracadabra --skill azure-speech-to-text",{"tool":46,"command":47},"pnpm","pnpm dlx skills add makemoney2023\u002Fabracadabra --skill azure-speech-to-text","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmakemoney2023\u002Fabracadabra\u002Fblob\u002Fmain\u002F.cursor\u002Fskills\u002Fcommunity\u002Fopenmontage\u002F.claude\u002Fskills\u002Fazure-speech-to-text\u002FSKILL.md",true,[],[52,59,66,74,81,88],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":18},"01M7CJZV04RF7XEF3K797X4S3A","vercel-react-best-practices","React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React\u002FNext.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.","https:\u002F\u002Fgithub.com\u002Fmakemoney2023\u002Fabracadabra\u002Fblob\u002Fmain\u002F.cursor\u002Fskills\u002Fplugins\u002Fvercel\u002Freact-best-practices\u002Fupstream\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":18},"01M7CJNGZC0AS6M9SFCXSJ1T5R","supabase-postgres-best-practices","Postgres performance optimization and best practices from Supabase. Use this skill when writing, reviewing, or optimizing Postgres queries, schema designs, or database configurations.","https:\u002F\u002Fgithub.com\u002Fmakemoney2023\u002Fabracadabra\u002Fblob\u002Fmain\u002F.cursor\u002Fskills\u002Fplugins\u002Fsupabase\u002Fsupabase-postgres-best-practices\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":70,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"01M7CJ9E816VBARCHX18AD88XX","ui-styling","Create beautiful, accessible user interfaces with shadcn\u002Fui components (built on Radix UI + Tailwind), Tailwind CSS utility-first styling, and canvas-based visual designs. Use when building user interfaces, implementing design systems, creating responsive layouts, adding accessible components (dialogs, dropdowns, forms, tables), customizing themes and colors, implementing dark mode, generating visual designs and posters, or establishing consistent styling patterns across applications.","https:\u002F\u002Fgithub.com\u002Fmakemoney2023\u002Fabracadabra\u002Fblob\u002Fmain\u002F.cursor\u002Fskills\u002Fcommunity\u002Fui-ux-pro-max-skill\u002Fui-styling\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fmakemoney2023\u002Fabracadabra\u002Fblob\u002Fmain\u002F.cursor\u002Fskills\u002Fcommunity\u002Fui-ux-pro-max-skill\u002Fui-styling\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M7CJ92XPH8CQHPSE34E9JTZ9","design","Comprehensive design skill: brand identity, design tokens, UI styling, logo generation (55 styles, Gemini AI), corporate identity program (50 deliverables, CIP mockups), HTML presentations (Chart.js), banner design (22 styles, social\u002Fads\u002Fweb\u002Fprint), icon design (15 styles, SVG, Gemini 3.1 Pro), social photos (HTML→screenshot, multi-platform). Actions: design logo, create CIP, generate mockups, build slides, design banner, generate icon, create social photos, social media images, brand identity, design system. Platforms: Facebook, Twitter, LinkedIn, YouTube, Instagram, Pinterest, TikTok, Threads, Google Ads.","https:\u002F\u002Fgithub.com\u002Fmakemoney2023\u002Fabracadabra\u002Fblob\u002Fmain\u002F.cursor\u002Fskills\u002Fcommunity\u002Fui-ux-pro-max-skill\u002Fdesign\u002FSKILL.md",[],[],{"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":87,"publishedAt":18},"01M7CJ8YVVNZ3G0Z8V621VXFY0","design-system","Token architecture, component specifications, and slide generation. Three-layer tokens (primitive→semantic→component), CSS variables, spacing\u002Ftypography scales, component specs, strategic slide creation. Use for design tokens, systematic design, brand-compliant presentations.","https:\u002F\u002Fgithub.com\u002Fmakemoney2023\u002Fabracadabra\u002Fblob\u002Fmain\u002F.cursor\u002Fskills\u002Fcommunity\u002Fui-ux-pro-max-skill\u002Fdesign-system\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":18},"01M7CJ8NZ8X3FTJEB8BJMXMZR7","banner-design","Design banners for social media, ads, website heroes, creative assets, and print. Multiple art direction options with AI-generated visuals. Actions: design, create, generate banner. Platforms: Facebook, Twitter\u002FX, LinkedIn, YouTube, Instagram, Google Display, website hero, print. Styles: minimalist, gradient, bold typography, photo-based, illustrated, geometric, retro, glassmorphism, 3D, neon, duotone, editorial, collage. Uses ui-ux-pro-max, frontend-design, ai-artist, ai-multimodal skills.","https:\u002F\u002Fgithub.com\u002Fmakemoney2023\u002Fabracadabra\u002Fblob\u002Fmain\u002F.cursor\u002Fskills\u002Fcommunity\u002Fui-ux-pro-max-skill\u002Fbanner-design\u002FSKILL.md",[],[]]