[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77VHMC8WENH92ACRVG7VF20":3,"skill-same:01M77VHMC8WENH92ACRVG7VF20":56},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":33,"commitSha":34,"skillDirectory":35,"forksCount":36,"repositoryHtmlUrl":37,"repositoryHomepageUrl":38,"ownerHtmlUrl":39,"ownerBlogUrl":6,"ownerDescription":40,"updatedAt":41,"install":42,"resources":55},"01M77VHMC8WENH92ACRVG7VF20","stepfun-step-audio-r1-1",null,"Use StepFun Chat Completions with model step-audio-r1.1 for non-streaming speech turns that can send text with optional local audio input and save the returned audio, transcript, and raw response object.","Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fs\u002Fstepfun-step-audio-r1-1\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: stepfun-step-audio-r1-1\ndescription: Use StepFun Chat Completions with model step-audio-r1.1 for non-streaming speech turns that can send text with optional local audio input and save the returned audio, transcript, and raw response object.\nmetadata:\n  openclaw:\n    emoji: \"🔊\"\n    requires:\n      bins: [\"python3\"]\n      env: [\"STEPFUN_API_KEY\", \"STEP_API_KEY\"]\n    primaryEnv: \"STEPFUN_API_KEY\"\n---\n\n# StepFun step-audio-r1.1\n\nCall StepFun's `POST \u002Fv1\u002Fchat\u002Fcompletions` endpoint with `stream: false` and\n`model: step-audio-r1.1`.\n\nUse this skill when the user explicitly wants StepFun audio generation,\nspeech-style replies through the Chat API, a standard non-streaming chat\ncompletion object, or local audio input encoded as `input_audio`.\n\nDo not use this skill for realtime duplex voice sessions. Use StepFun Realtime\nAPI instead when the user wants low-latency live conversation.\n\n`step-audio-r1.1` does not support tool call. If the user needs tool calling,\nprefer `step-audio-2` instead of this skill.\n\n## Quick Start\n\nText in, audio out:\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fstepfun_audio_chat.py \\\n  --prompt \"用中文介绍一下苏州的春天，语气自然一点。\" \\\n  --voice wenrounansheng \\\n  --format wav\n```\n\nCheck available voice ids before a run:\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fstepfun_audio_chat.py \\\n  --list-voices\n```\n\nText + local audio in, audio out:\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fstepfun_audio_chat.py \\\n  --prompt \"听完这段语音后，总结重点，并用更简洁的话复述。\" \\\n  --input-audio \u002Fpath\u002Fto\u002Finput.wav \\\n  --voice wenrounansheng \\\n  --format wav\n```\n\nBuild and inspect the non-streaming request without sending it:\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fstepfun_audio_chat.py \\\n  --prompt \"测试 step-audio-r1.1 非流式 payload\" \\\n  --dry-run \\\n  --print-json\n```\n\n## What The Script Produces\n\nThe helper writes a fresh output directory for each run unless `--output-dir`\nis provided. Typical files are:\n\n- `request.json`: saved only for `--dry-run`\n- `response.json`: full non-streaming response object\n- `response.\u003Cformat>`: decoded audio from `choices[0].message.audio.data`\n- `transcript.txt`: `choices[0].message.audio.transcript`\n- `content.txt`: textual assistant content when present\n\n## Common Flags\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fstepfun_audio_chat.py --help\n```\n\nImportant flags:\n\n- `--prompt`: user text to send with the request\n- `--input-audio`: local audio file that will be base64-encoded into\n  `input_audio`; non-WAV files are converted to WAV first when `ffmpeg` or\n  `afconvert` is available\n- `--system`: optional system instruction\n- `--voice`: output voice name\n- `--list-voices`: query StepFun for account-level custom\u002Fcloned voices and\n  print a few official voice hints\n- `--format`: non-streaming output audio format; this skill uses `wav`\n- `--no-audio-output`: request text-only output while still using the Chat API\n- `--temperature`: optional sampling override\n- `--max-tokens`: optional generation cap\n- `--print-json`: echo request or response JSON to stdout\n- `--dry-run`: build payload and stop before the network call\n\n## Configuration\n\nSet `STEPFUN_API_KEY` in the environment, or inject it through OpenClaw skill\nconfig:\n\n```json5\n{\n  skills: {\n    entries: {\n      \"stepfun-step-audio-r1-1\": {\n        env: {\n          STEPFUN_API_KEY: \"STEP_KEY_HERE\",\n        },\n      },\n    },\n  },\n}\n```\n\nThe script still accepts `STEP_API_KEY` as a legacy alias for backward\ncompatibility, but the official name is `STEPFUN_API_KEY`.\n\nOptional environment variables:\n\n- `STEP_API_BASE_URL`: overrides the default `https:\u002F\u002Fapi.stepfun.com`\n\nInput audio note:\n\n- StepFun expects `input_audio.data` in `data:audio\u002Fwav;base64,...` format\n- Official docs mention WAV and MP3 input support\n- This script normalizes local input to WAV for maximum compatibility\n- If you pass `m4a`, `mp3`, `aiff`, or similar, this script will try to convert\n  to WAV via `ffmpeg` or macOS `afconvert`\n- The normalized `input_audio` payload must stay within StepFun's 10MB base64\n  limit\n\nVoice selection note:\n\n- `step-audio-r1.1` needs `audio.voice` whenever you request audio output\n- The script defaults to `wenrounansheng`, which was validated in real smoke\n  tests for this skill\n- For production use, prefer passing `--voice` explicitly\n- Use `--list-voices` to inspect account-level custom\u002Fcloned voice ids\n- Read [references\u002Fstepfun-voices.md](references\u002Fstepfun-voices.md) for how\n  `step-audio-r1.1`, `step-audio-2`, and `step-tts-*` differ in voice usage\n\n## Workflow\n\n1. Confirm the user wants StepFun `step-audio-r1.1` through Chat API.\n2. Choose whether the turn is text-only or text plus local audio input.\n3. Run the helper script with `stream: false`.\n4. Return the saved transcript, the audio file path, and any important response\n   fields to the user.\n\n## Reference\n\nRead [references\u002Fstepfun-chat-api.md](references\u002Fstepfun-chat-api.md) when you\nneed the exact request shape, supported audio fields, or the non-streaming\nresponse layout. Read [references\u002Fstepfun-voices.md](references\u002Fstepfun-voices.md)\nwhen you need voice-selection guidance.\n","# StepFun step-audio-r1.1\n\nCall StepFun's `POST \u002Fv1\u002Fchat\u002Fcompletions` endpoint with `stream: false` and\n`model: step-audio-r1.1`.\n\nUse this skill when the user explicitly wants StepFun audio generation,\nspeech-style replies through the Chat API, a standard non-streaming chat\ncompletion object, or local audio input encoded as `input_audio`.\n\nDo not use this skill for realtime duplex voice sessions. Use StepFun Realtime\nAPI instead when the user wants low-latency live conversation.\n\n`step-audio-r1.1` does not support tool call. If the user needs tool calling,\nprefer `step-audio-2` instead of this skill.\n\n## Quick Start\n\nText in, audio out:\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fstepfun_audio_chat.py \\\n  --prompt \"用中文介绍一下苏州的春天，语气自然一点。\" \\\n  --voice wenrounansheng \\\n  --format wav\n```\n\nCheck available voice ids before a run:\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fstepfun_audio_chat.py \\\n  --list-voices\n```\n\nText + local audio in, audio out:\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fstepfun_audio_chat.py \\\n  --prompt \"听完这段语音后，总结重点，并用更简洁的话复述。\" \\\n  --input-audio \u002Fpath\u002Fto\u002Finput.wav \\\n  --voice wenrounansheng \\\n  --format wav\n```\n\nBuild and inspect the non-streaming request without sending it:\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fstepfun_audio_chat.py \\\n  --prompt \"测试 step-audio-r1.1 非流式 payload\" \\\n  --dry-run \\\n  --print-json\n```\n\n## What The Script Produces\n\nThe helper writes a fresh output directory for each run unless `--output-dir`\nis provided. Typical files are:\n\n- `request.json`: saved only for `--dry-run`\n- `response.json`: full non-streaming response object\n- `response.\u003Cformat>`: decoded audio from `choices[0].message.audio.data`\n- `transcript.txt`: `choices[0].message.audio.transcript`\n- `content.txt`: textual assistant content when present\n\n## Common Flags\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fstepfun_audio_chat.py --help\n```\n\nImportant flags:\n\n- `--prompt`: user text to send with the request\n- `--input-audio`: local audio file that will be base64-encoded into\n  `input_audio`; non-WAV files are converted to WAV first when `ffmpeg` or\n  `afconvert` is available\n- `--system`: optional system instruction\n- `--voice`: output voice name\n- `--list-voices`: query StepFun for account-level custom\u002Fcloned voices and\n  print a few official voice hints\n- `--format`: non-streaming output audio format; this skill uses `wav`\n- `--no-audio-output`: request text-only output while still using the Chat API\n- `--temperature`: optional sampling override\n- `--max-tokens`: optional generation cap\n- `--print-json`: echo request or response JSON to stdout\n- `--dry-run`: build payload and stop before the network call\n\n## Configuration\n\nSet `STEPFUN_API_KEY` in the environment, or inject it through OpenClaw skill\nconfig:\n\n```json5\n{\n  skills: {\n    entries: {\n      \"stepfun-step-audio-r1-1\": {\n        env: {\n          STEPFUN_API_KEY: \"STEP_KEY_HERE\",\n        },\n      },\n    },\n  },\n}\n```\n\nThe script still accepts `STEP_API_KEY` as a legacy alias for backward\ncompatibility, but the official name is `STEPFUN_API_KEY`.\n\nOptional environment variables:\n\n- `STEP_API_BASE_URL`: overrides the default `https:\u002F\u002Fapi.stepfun.com`\n\nInput audio note:\n\n- StepFun expects `input_audio.data` in `data:audio\u002Fwav;base64,...` format\n- Official docs mention WAV and MP3 input support\n- This script normalizes local input to WAV for maximum compatibility\n- If you pass `m4a`, `mp3`, `aiff`, or similar, this script will try to convert\n  to WAV via `ffmpeg` or macOS `afconvert`\n- The normalized `input_audio` payload must stay within StepFun's 10MB base64\n  limit\n\nVoice selection note:\n\n- `step-audio-r1.1` needs `audio.voice` whenever you request audio output\n- The script defaults to `wenrounansheng`, which was validated in real smoke\n  tests for this skill\n- For production use, prefer passing `--voice` explicitly\n- Use `--list-voices` to inspect account-level custom\u002Fcloned voice ids\n- Read [references\u002Fstepfun-voices.md](references\u002Fstepfun-voices.md) for how\n  `step-audio-r1.1`, `step-audio-2`, and `step-tts-*` differ in voice usage\n\n## Workflow\n\n1. Confirm the user wants StepFun `step-audio-r1.1` through Chat API.\n2. Choose whether the turn is text-only or text plus local audio input.\n3. Run the helper script with `stream: false`.\n4. Return the saved transcript, the audio file path, and any important response\n   fields to the user.\n\n## Reference\n\nRead [references\u002Fstepfun-chat-api.md](references\u002Fstepfun-chat-api.md) when you\nneed the exact request shape, supported audio fields, or the non-streaming\nresponse layout. Read [references\u002Fstepfun-voices.md](references\u002Fstepfun-voices.md)\nwhen you need voice-selection guidance.\n",{"name":5,"metadata":24,"description":7},{"openclaw":25},{"emoji":26,"requires":27,"primaryEnv":29},"🔊",{"env":28,"bins":31},[29,30],"STEPFUN_API_KEY","STEP_API_KEY",[32],"python3","master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fs\u002Fstepfun-step-audio-r1-1",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":8,"skillName":5,"commands":43,"prompt":53,"zipAvailable":54},[44,47,50],{"tool":45,"command":46},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill stepfun-step-audio-r1-1",{"tool":48,"command":49},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill stepfun-step-audio-r1-1",{"tool":51,"command":52},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill stepfun-step-audio-r1-1","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fs\u002Fstepfun-step-audio-r1-1\u002FSKILL.md",true,[],[57,64,71,78,85,92],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":19},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]