[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77NCCRJSGX8QTW711AY66FP":3,"skill-same:01M77NCCRJSGX8QTW711AY66FP":47},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M77NCCRJSGX8QTW711AY66FP","audiopod",null,"Use SkillBoss API Hub for audio processing tasks including AI music generation (text-to-music, instrumentals, samples), text-to-speech, speech-to-text transcription, stem separation, noise reduction, and speaker separation. Use when the user needs to generate music\u002Fsongs from text, generate speech from text, transcribe audio\u002Fvideo, or process audio. Requires SKILLBOSS_API_KEY env var.","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\u002Fm\u002Fmodesty-audiopod\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: audiopod\ndescription: Use SkillBoss API Hub for audio processing tasks including AI music generation (text-to-music, instrumentals, samples), text-to-speech, speech-to-text transcription, stem separation, noise reduction, and speaker separation. Use when the user needs to generate music\u002Fsongs from text, generate speech from text, transcribe audio\u002Fvideo, or process audio. Requires SKILLBOSS_API_KEY env var.\n---\n\n> 📖 **Complete setup guide**: https:\u002F\u002Fskillboss.co\u002Fskill.md\n\n\n# SkillBoss Audio Processing\n\nFull audio processing via SkillBoss API Hub: music generation, TTS, STT, stem separation, noise reduction, speaker separation.\n\n## Setup\n\n```python\nimport requests, os\n\nSKILLBOSS_API_KEY = os.environ[\"SKILLBOSS_API_KEY\"]\nAPI_BASE = \"https:\u002F\u002Fapi.skillboss.co\u002Fv1\"\n\ndef pilot(body: dict) -> dict:\n    r = requests.post(\n        f\"{API_BASE}\u002Fpilot\",\n        headers={\"Authorization\": f\"Bearer {SKILLBOSS_API_KEY}\", \"Content-Type\": \"application\u002Fjson\"},\n        json=body,\n        timeout=60,\n    )\n    return r.json()\n```\n\nAuth: set `SKILLBOSS_API_KEY` env var. All requests use `Authorization: Bearer $SKILLBOSS_API_KEY`.\n\n---\n\n## AI Music Generation\n\nGenerate songs, instrumentals, samples, and vocals from text prompts via SkillBoss API Hub.\n\n**Capabilities:** music generation (full song with vocals), instrumental, rap, samples, audio-to-audio style transfer\n\n### Python\n\n```python\n# Generate a full song\nresult = pilot({\n    \"type\": \"music\",\n    \"inputs\": {\n        \"prompt\": \"Upbeat pop, synth, drums, 120 bpm, female vocals, radio-ready\",\n        \"lyrics\": \"Verse 1:\\nWalking down the street on a sunny day\\n\\nChorus:\\nWe're on fire tonight!\",\n        \"duration\": 60\n    },\n    \"prefer\": \"quality\"\n})\naudio_url = result[\"data\"][\"result\"][\"audio_url\"]\nprint(audio_url)\n\n# Generate instrumental (no lyrics needed)\nresult = pilot({\n    \"type\": \"music\",\n    \"inputs\": {\n        \"prompt\": \"Atmospheric ambient soundscape, uplifting, driving mood\",\n        \"duration\": 30\n    },\n    \"prefer\": \"balanced\"\n})\naudio_url = result[\"data\"][\"result\"][\"audio_url\"]\n\n# Generate rap\nresult = pilot({\n    \"type\": \"music\",\n    \"inputs\": {\n        \"prompt\": \"Lo-Fi Hip Hop, 100 BPM, male rap, melancholy, keyboard chords\",\n        \"lyrics\": \"Verse 1:\\nStarted from the bottom, now we climbing...\",\n        \"duration\": 60,\n        \"style\": \"rap\"\n    },\n    \"prefer\": \"balanced\"\n})\naudio_url = result[\"data\"][\"result\"][\"audio_url\"]\n\n# Generate samples\u002Floops\nresult = pilot({\n    \"type\": \"music\",\n    \"inputs\": {\n        \"prompt\": \"drum loop, sad mood\",\n        \"duration\": 15,\n        \"style\": \"samples\"\n    },\n    \"prefer\": \"balanced\"\n})\naudio_url = result[\"data\"][\"result\"][\"audio_url\"]\n```\n\n### cURL\n\n```bash\n# Generate full song\ncurl -X POST \"https:\u002F\u002Fapi.skillboss.co\u002Fv1\u002Fpilot\" \\\n  -H \"Authorization: Bearer $SKILLBOSS_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"type\":\"music\",\"inputs\":{\"prompt\":\"upbeat pop, synth, 120bpm, female vocals\",\"lyrics\":\"Walking down the street...\",\"duration\":60},\"prefer\":\"quality\"}'\n\n# Generate instrumental\ncurl -X POST \"https:\u002F\u002Fapi.skillboss.co\u002Fv1\u002Fpilot\" \\\n  -H \"Authorization: Bearer $SKILLBOSS_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"type\":\"music\",\"inputs\":{\"prompt\":\"ambient soundscape, uplifting\",\"duration\":30},\"prefer\":\"balanced\"}'\n\n# Generate rap\ncurl -X POST \"https:\u002F\u002Fapi.skillboss.co\u002Fv1\u002Fpilot\" \\\n  -H \"Authorization: Bearer $SKILLBOSS_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"type\":\"music\",\"inputs\":{\"prompt\":\"Lo-Fi Hip Hop, male rap, 100 BPM\",\"lyrics\":\"Started from the bottom...\",\"duration\":60,\"style\":\"rap\"}}'\n\n# Generate samples\ncurl -X POST \"https:\u002F\u002Fapi.skillboss.co\u002Fv1\u002Fpilot\" \\\n  -H \"Authorization: Bearer $SKILLBOSS_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"type\":\"music\",\"inputs\":{\"prompt\":\"drum loop, sad mood\",\"duration\":15,\"style\":\"samples\"}}'\n```\n\n### Parameters\n\n| Field | Required | Description |\n|-------|----------|-------------|\n| prompt | yes | Style\u002Fgenre description |\n| lyrics | for song\u002Frap\u002Fvocals | Song lyrics with verse\u002Fchorus structure |\n| duration | no | Duration in seconds (default: 30) |\n| style | no | `rap`, `samples`, `instrumental`, `vocals` — hints for routing |\n\n### Response\n\n```python\naudio_url = result[\"data\"][\"result\"][\"audio_url\"]\n```\n\n---\n\n## Stem Separation\n\nSplit audio into individual instrument\u002Fvocal tracks via SkillBoss API Hub audio routing.\n\n### Modes\n\n| Mode | Stems | Output | Use Case |\n|------|-------|--------|----------|\n| single | 1 | Specified stem only | Vocal isolation, drum extraction |\n| two | 2 | vocals + instrumental | Karaoke tracks |\n| four | 4 | vocals, drums, bass, other | Standard remixing (default) |\n| six | 6 | + guitar, piano | Full instrument separation |\n| producer | 8 | + kick, snare, hihat | Beat production |\n| studio | 12 | + cymbals, sub_bass, synth | Professional mixing |\n| mastering | 16 | Maximum detail | Forensic analysis |\n\n**Single stem options:** vocals, drums, bass, guitar, piano, other\n\n### Python\n\n```python\n# Extract stems from URL\nresult = pilot({\n    \"type\": \"audio\",\n    \"capability\": \"stem separation\",\n    \"inputs\": {\n        \"url\": \"https:\u002F\u002Fyoutube.com\u002Fwatch?v=VIDEO_ID\",\n        \"mode\": \"six\"\n    },\n    \"prefer\": \"quality\"\n})\ndownload_urls = result[\"data\"][\"result\"][\"download_urls\"]\nfor stem, url in download_urls.items():\n    print(f\"{stem}: {url}\")\n\n# Extract from local file (base64-encoded)\nimport base64\naudio_b64 = base64.b64encode(open(\"\u002Fpath\u002Fto\u002Fsong.mp3\", \"rb\").read()).decode()\nresult = pilot({\n    \"type\": \"audio\",\n    \"capability\": \"stem separation\",\n    \"inputs\": {\n        \"audio_data\": audio_b64,\n        \"filename\": \"song.mp3\",\n        \"mode\": \"four\"\n    },\n    \"prefer\": \"balanced\"\n})\ndownload_urls = result[\"data\"][\"result\"][\"download_urls\"]\n\n# Single stem extraction\nresult = pilot({\n    \"type\": \"audio\",\n    \"capability\": \"stem separation\",\n    \"inputs\": {\n        \"url\": \"https:\u002F\u002Fyoutube.com\u002Fwatch?v=ID\",\n        \"mode\": \"single\",\n        \"stem\": \"vocals\"\n    },\n    \"prefer\": \"quality\"\n})\nvocal_url = result[\"data\"][\"result\"][\"download_urls\"][\"vocals\"]\n```\n\n### cURL\n\n```bash\n# Extract stems from URL\ncurl -X POST \"https:\u002F\u002Fapi.skillboss.co\u002Fv1\u002Fpilot\" \\\n  -H \"Authorization: Bearer $SKILLBOSS_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"type\":\"audio\",\"capability\":\"stem separation\",\"inputs\":{\"url\":\"https:\u002F\u002Fyoutube.com\u002Fwatch?v=VIDEO_ID\",\"mode\":\"six\"},\"prefer\":\"quality\"}'\n\n# Single stem\ncurl -X POST \"https:\u002F\u002Fapi.skillboss.co\u002Fv1\u002Fpilot\" \\\n  -H \"Authorization: Bearer $SKILLBOSS_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"type\":\"audio\",\"capability\":\"stem separation\",\"inputs\":{\"url\":\"URL\",\"mode\":\"single\",\"stem\":\"vocals\"}}'\n```\n\n### Response Format\n\n```json\n{\n  \"data\": {\n    \"result\": {\n      \"download_urls\": {\n        \"vocals\": \"https:\u002F\u002F...\",\n        \"drums\": \"https:\u002F\u002F...\",\n        \"bass\": \"https:\u002F\u002F...\",\n        \"other\": \"https:\u002F\u002F...\"\n      },\n      \"quality_scores\": {\n        \"vocals\": 0.95,\n        \"drums\": 0.88\n      }\n    }\n  }\n}\n```\n\n---\n\n## Text to Speech\n\nGenerate speech from text with 50+ voices in 60+ languages via SkillBoss API Hub.\n\n### Python\n\n```python\n# Generate speech\nresult = pilot({\n    \"type\": \"tts\",\n    \"inputs\": {\n        \"text\": \"Hello, world! This is a test.\",\n        \"voice\": \"alloy\",\n        \"speed\": 1.0\n    },\n    \"prefer\": \"balanced\"\n})\naudio_url = result[\"data\"][\"result\"][\"audio_url\"]\nprint(audio_url)\n\n# Specify language\nresult = pilot({\n    \"type\": \"tts\",\n    \"inputs\": {\n        \"text\": \"Bonjour le monde\",\n        \"voice\": \"alloy\",\n        \"language\": \"fr\",\n        \"speed\": 1.0\n    },\n    \"prefer\": \"quality\"\n})\naudio_url = result[\"data\"][\"result\"][\"audio_url\"]\n```\n\n### cURL\n\n```bash\n# Generate speech\ncurl -X POST \"https:\u002F\u002Fapi.skillboss.co\u002Fv1\u002Fpilot\" \\\n  -H \"Authorization: Bearer $SKILLBOSS_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"type\":\"tts\",\"inputs\":{\"text\":\"Hello world, this is a test\",\"voice\":\"alloy\",\"speed\":1.0},\"prefer\":\"balanced\"}'\n```\n\n### Parameters\n\n| Field | Required | Description |\n|-------|----------|-------------|\n| text | yes | Text to speak (max 5000 chars) |\n| voice | no | Voice name or ID (e.g. `alloy`, `echo`, `fable`) |\n| speed | no | 0.25 - 4.0 (default: 1.0) |\n| language | no | ISO code, auto-detected if omitted |\n\n### Response\n\n```python\naudio_url = result[\"data\"][\"result\"][\"audio_url\"]\n```\n\n---\n\n## Speaker Separation\n\nSeparate audio by speaker with automatic diarization via SkillBoss API Hub.\n\n### Python\n\n```python\n# Diarize from file\nimport base64\naudio_b64 = base64.b64encode(open(\".\u002Fmeeting.mp3\", \"rb\").read()).decode()\nresult = pilot({\n    \"type\": \"stt\",\n    \"capability\": \"speaker diarization\",\n    \"inputs\": {\n        \"audio_data\": audio_b64,\n        \"filename\": \"meeting.mp3\",\n        \"num_speakers\": 3\n    },\n    \"prefer\": \"quality\"\n})\nfor segment in result[\"data\"][\"result\"][\"segments\"]:\n    print(f\"Speaker {segment['speaker']}: {segment['text']} [{segment['start']:.1f}s - {segment['end']:.1f}s]\")\n\n# Diarize from URL\nresult = pilot({\n    \"type\": \"stt\",\n    \"capability\": \"speaker diarization\",\n    \"inputs\": {\n        \"url\": \"https:\u002F\u002Fyoutube.com\u002Fwatch?v=VIDEO_ID\",\n        \"num_speakers\": 2\n    },\n    \"prefer\": \"balanced\"\n})\nsegments = result[\"data\"][\"result\"][\"segments\"]\n```\n\n### cURL\n\n```bash\n# Diarize from URL\ncurl -X POST \"https:\u002F\u002Fapi.skillboss.co\u002Fv1\u002Fpilot\" \\\n  -H \"Authorization: Bearer $SKILLBOSS_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"type\":\"stt\",\"capability\":\"speaker diarization\",\"inputs\":{\"url\":\"https:\u002F\u002Fyoutube.com\u002Fwatch?v=VIDEO_ID\",\"num_speakers\":2},\"prefer\":\"balanced\"}'\n```\n\n---\n\n## Speech to Text (Transcription)\n\nTranscribe audio\u002Fvideo with speaker diarization, word-level timestamps, and multiple output formats via SkillBoss API Hub.\n\n### Python\n\n```python\n# Transcribe from URL\nresult = pilot({\n    \"type\": \"stt\",\n    \"inputs\": {\n        \"url\": \"https:\u002F\u002Fyoutube.com\u002Fwatch?v=VIDEO_ID\",\n        \"speaker_diarization\": True,\n        \"word_timestamps\": True\n    },\n    \"prefer\": \"balanced\"\n})\ntext = result[\"data\"][\"result\"][\"text\"]\nsegments = result[\"data\"][\"result\"].get(\"segments\", [])\nprint(f\"Transcript: {text}\")\nfor seg in segments:\n    print(f\"[{seg.get('start', 0):.1f}s] {seg.get('speaker','?')}: {seg['text']}\")\n\n# Transcribe local file\nimport base64\naudio_b64 = base64.b64encode(open(\".\u002Frecording.mp3\", \"rb\").read()).decode()\nresult = pilot({\n    \"type\": \"stt\",\n    \"inputs\": {\n        \"audio_data\": audio_b64,\n        \"filename\": \"recording.mp3\",\n        \"language\": \"en\",\n        \"speaker_diarization\": True\n    },\n    \"prefer\": \"balanced\"\n})\ntext = result[\"data\"][\"result\"][\"text\"]\n```\n\n### cURL\n\n```bash\n# Transcribe from URL\ncurl -X POST \"https:\u002F\u002Fapi.skillboss.co\u002Fv1\u002Fpilot\" \\\n  -H \"Authorization: Bearer $SKILLBOSS_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"type\":\"stt\",\"inputs\":{\"url\":\"https:\u002F\u002Fyoutube.com\u002Fwatch?v=ID\",\"speaker_diarization\":true,\"word_timestamps\":true},\"prefer\":\"balanced\"}'\n```\n\n### Parameters\n\n| Field | Required | Description |\n|-------|----------|-------------|\n| url | yes (or audio_data) | URL to transcribe (YouTube, SoundCloud, direct links) |\n| audio_data | yes (or url) | Base64-encoded audio content |\n| filename | with audio_data | Original filename for format detection |\n| language | no | ISO 639-1 code (auto-detected if omitted) |\n| speaker_diarization | no | Enable speaker identification (default: false) |\n| word_timestamps | no | Enable word-level timestamps (default: true) |\n\n### Response\n\n```python\ntext = result[\"data\"][\"result\"][\"text\"]\nsegments = result[\"data\"][\"result\"].get(\"segments\", [])  # with speaker_diarization\n```\n\n---\n\n## Noise Reduction\n\nRemove background noise from audio files via SkillBoss API Hub.\n\n### Python\n\n```python\n# Denoise from file\nimport base64\naudio_b64 = base64.b64encode(open(\".\u002Fnoisy-audio.mp3\", \"rb\").read()).decode()\nresult = pilot({\n    \"type\": \"audio\",\n    \"capability\": \"noise reduction\",\n    \"inputs\": {\n        \"audio_data\": audio_b64,\n        \"filename\": \"noisy-audio.mp3\"\n    },\n    \"prefer\": \"quality\"\n})\nclean_url = result[\"data\"][\"result\"][\"audio_url\"]\nprint(f\"Clean audio: {clean_url}\")\n\n# Denoise from URL\nresult = pilot({\n    \"type\": \"audio\",\n    \"capability\": \"noise reduction\",\n    \"inputs\": {\n        \"url\": \"https:\u002F\u002Fexample.com\u002Fnoisy.mp3\"\n    },\n    \"prefer\": \"balanced\"\n})\nclean_url = result[\"data\"][\"result\"][\"audio_url\"]\n```\n\n### cURL\n\n```bash\n# Denoise from URL\ncurl -X POST \"https:\u002F\u002Fapi.skillboss.co\u002Fv1\u002Fpilot\" \\\n  -H \"Authorization: Bearer $SKILLBOSS_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"type\":\"audio\",\"capability\":\"noise reduction\",\"inputs\":{\"url\":\"https:\u002F\u002Fexample.com\u002Fnoisy.mp3\"},\"prefer\":\"quality\"}'\n```\n\n### Response\n\n```python\nclean_url = result[\"data\"][\"result\"][\"audio_url\"]\n```\n\n---\n\n## Chain Mode (Multi-step Workflow)\n\nUse SkillBoss Chain mode to combine multiple audio steps in one call.\n\n### Python\n\n```python\n# STT → Chat (summarize) → TTS pipeline\nresult = pilot({\n    \"chain\": [\n        {\"type\": \"stt\"},\n        {\"type\": \"chat\", \"capability\": \"summarize\"},\n        {\"type\": \"tts\"}\n    ]\n})\n\n# Transcribe and translate\nresult = pilot({\n    \"chain\": [\n        {\"type\": \"stt\"},\n        {\"type\": \"chat\", \"capability\": \"translate to English\"}\n    ]\n})\n```\n\n---\n\n## API Endpoint Summary\n\nAll capabilities route through a single endpoint:\n\n| Service | SkillBoss type | capability |\n|---------|---------------|------------|\n| Music generation | `music` | — |\n| TTS | `tts` | — |\n| STT \u002F Transcription | `stt` | — |\n| Speaker separation | `stt` | `speaker diarization` |\n| Stem separation | `audio` | `stem separation` |\n| Noise reduction | `audio` | `noise reduction` |\n\n**Single endpoint:** `POST https:\u002F\u002Fapi.skillboss.co\u002Fv1\u002Fpilot`\n**Auth:** `Authorization: Bearer $SKILLBOSS_API_KEY`\n\n## Response Format Summary\n\n| Capability | Result path |\n|-----------|-------------|\n| Music generation | `data.result.audio_url` |\n| TTS | `data.result.audio_url` |\n| STT (text) | `data.result.text` |\n| STT (segments) | `data.result.segments` |\n| Stem separation | `data.result.download_urls` |\n| Noise reduction | `data.result.audio_url` |\n","> 📖 **Complete setup guide**: https:\u002F\u002Fskillboss.co\u002Fskill.md\n\n\n# SkillBoss Audio Processing\n\nFull audio processing via SkillBoss API Hub: music generation, TTS, STT, stem separation, noise reduction, speaker separation.\n\n## Setup\n\n```python\nimport requests, os\n\nSKILLBOSS_API_KEY = os.environ[\"SKILLBOSS_API_KEY\"]\nAPI_BASE = \"https:\u002F\u002Fapi.skillboss.co\u002Fv1\"\n\ndef pilot(body: dict) -> dict:\n    r = requests.post(\n        f\"{API_BASE}\u002Fpilot\",\n        headers={\"Authorization\": f\"Bearer {SKILLBOSS_API_KEY}\", \"Content-Type\": \"application\u002Fjson\"},\n        json=body,\n        timeout=60,\n    )\n    return r.json()\n```\n\nAuth: set `SKILLBOSS_API_KEY` env var. All requests use `Authorization: Bearer $SKILLBOSS_API_KEY`.\n\n---\n\n## AI Music Generation\n\nGenerate songs, instrumentals, samples, and vocals from text prompts via SkillBoss API Hub.\n\n**Capabilities:** music generation (full song with vocals), instrumental, rap, samples, audio-to-audio style transfer\n\n### Python\n\n```python\n# Generate a full song\nresult = pilot({\n    \"type\": \"music\",\n    \"inputs\": {\n        \"prompt\": \"Upbeat pop, synth, drums, 120 bpm, female vocals, radio-ready\",\n        \"lyrics\": \"Verse 1:\\nWalking down the street on a sunny day\\n\\nChorus:\\nWe're on fire tonight!\",\n        \"duration\": 60\n    },\n    \"prefer\": \"quality\"\n})\naudio_url = result[\"data\"][\"result\"][\"audio_url\"]\nprint(audio_url)\n\n# Generate instrumental (no lyrics needed)\nresult = pilot({\n    \"type\": \"music\",\n    \"inputs\": {\n        \"prompt\": \"Atmospheric ambient soundscape, uplifting, driving mood\",\n        \"duration\": 30\n    },\n    \"prefer\": \"balanced\"\n})\naudio_url = result[\"data\"][\"result\"][\"audio_url\"]\n\n# Generate rap\nresult = pilot({\n    \"type\": \"music\",\n    \"inputs\": {\n        \"prompt\": \"Lo-Fi Hip Hop, 100 BPM, male rap, melancholy, keyboard chords\",\n        \"lyrics\": \"Verse 1:\\nStarted from the bottom, now we climbing...\",\n        \"duration\": 60,\n        \"style\": \"rap\"\n    },\n    \"prefer\": \"balanced\"\n})\naudio_url = result[\"data\"][\"result\"][\"audio_url\"]\n\n# Generate samples\u002Floops\nresult = pilot({\n    \"type\": \"music\",\n    \"inputs\": {\n        \"prompt\": \"drum loop, sad mood\",\n        \"duration\": 15,\n        \"style\": \"samples\"\n    },\n    \"prefer\": \"balanced\"\n})\naudio_url = result[\"data\"][\"result\"][\"audio_url\"]\n```\n\n### cURL\n\n```bash\n# Generate full song\ncurl -X POST \"https:\u002F\u002Fapi.skillboss.co\u002Fv1\u002Fpilot\" \\\n  -H \"Authorization: Bearer $SKILLBOSS_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"type\":\"music\",\"inputs\":{\"prompt\":\"upbeat pop, synth, 120bpm, female vocals\",\"lyrics\":\"Walking down the street...\",\"duration\":60},\"prefer\":\"quality\"}'\n\n# Generate instrumental\ncurl -X POST \"https:\u002F\u002Fapi.skillboss.co\u002Fv1\u002Fpilot\" \\\n  -H \"Authorization: Bearer $SKILLBOSS_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"type\":\"music\",\"inputs\":{\"prompt\":\"ambient soundscape, uplifting\",\"duration\":30},\"prefer\":\"balanced\"}'\n\n# Generate rap\ncurl -X POST \"https:\u002F\u002Fapi.skillboss.co\u002Fv1\u002Fpilot\" \\\n  -H \"Authorization: Bearer $SKILLBOSS_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"type\":\"music\",\"inputs\":{\"prompt\":\"Lo-Fi Hip Hop, male rap, 100 BPM\",\"lyrics\":\"Started from the bottom...\",\"duration\":60,\"style\":\"rap\"}}'\n\n# Generate samples\ncurl -X POST \"https:\u002F\u002Fapi.skillboss.co\u002Fv1\u002Fpilot\" \\\n  -H \"Authorization: Bearer $SKILLBOSS_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"type\":\"music\",\"inputs\":{\"prompt\":\"drum loop, sad mood\",\"duration\":15,\"style\":\"samples\"}}'\n```\n\n### Parameters\n\n| Field | Required | Description |\n|-------|----------|-------------|\n| prompt | yes | Style\u002Fgenre description |\n| lyrics | for song\u002Frap\u002Fvocals | Song lyrics with verse\u002Fchorus structure |\n| duration | no | Duration in seconds (default: 30) |\n| style | no | `rap`, `samples`, `instrumental`, `vocals` — hints for routing |\n\n### Response\n\n```python\naudio_url = result[\"data\"][\"result\"][\"audio_url\"]\n```\n\n---\n\n## Stem Separation\n\nSplit audio into individual instrument\u002Fvocal tracks via SkillBoss API Hub audio routing.\n\n### Modes\n\n| Mode | Stems | Output | Use Case |\n|------|-------|--------|----------|\n| single | 1 | Specified stem only | Vocal isolation, drum extraction |\n| two | 2 | vocals + instrumental | Karaoke tracks |\n| four | 4 | vocals, drums, bass, other | Standard remixing (default) |\n| six | 6 | + guitar, piano | Full instrument separation |\n| producer | 8 | + kick, snare, hihat | Beat production |\n| studio | 12 | + cymbals, sub_bass, synth | Professional mixing |\n| mastering | 16 | Maximum detail | Forensic analysis |\n\n**Single stem options:** vocals, drums, bass, guitar, piano, other\n\n### Python\n\n```python\n# Extract stems from URL\nresult = pilot({\n    \"type\": \"audio\",\n    \"capability\": \"stem separation\",\n    \"inputs\": {\n        \"url\": \"https:\u002F\u002Fyoutube.com\u002Fwatch?v=VIDEO_ID\",\n        \"mode\": \"six\"\n    },\n    \"prefer\": \"quality\"\n})\ndownload_urls = result[\"data\"][\"result\"][\"download_urls\"]\nfor stem, url in download_urls.items():\n    print(f\"{stem}: {url}\")\n\n# Extract from local file (base64-encoded)\nimport base64\naudio_b64 = base64.b64encode(open(\"\u002Fpath\u002Fto\u002Fsong.mp3\", \"rb\").read()).decode()\nresult = pilot({\n    \"type\": \"audio\",\n    \"capability\": \"stem separation\",\n    \"inputs\": {\n        \"audio_data\": audio_b64,\n        \"filename\": \"song.mp3\",\n        \"mode\": \"four\"\n    },\n    \"prefer\": \"balanced\"\n})\ndownload_urls = result[\"data\"][\"result\"][\"download_urls\"]\n\n# Single stem extraction\nresult = pilot({\n    \"type\": \"audio\",\n    \"capability\": \"stem separation\",\n    \"inputs\": {\n        \"url\": \"https:\u002F\u002Fyoutube.com\u002Fwatch?v=ID\",\n        \"mode\": \"single\",\n        \"stem\": \"vocals\"\n    },\n    \"prefer\": \"quality\"\n})\nvocal_url = result[\"data\"][\"result\"][\"download_urls\"][\"vocals\"]\n```\n\n### cURL\n\n```bash\n# Extract stems from URL\ncurl -X POST \"https:\u002F\u002Fapi.skillboss.co\u002Fv1\u002Fpilot\" \\\n  -H \"Authorization: Bearer $SKILLBOSS_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"type\":\"audio\",\"capability\":\"stem separation\",\"inputs\":{\"url\":\"https:\u002F\u002Fyoutube.com\u002Fwatch?v=VIDEO_ID\",\"mode\":\"six\"},\"prefer\":\"quality\"}'\n\n# Single stem\ncurl -X POST \"https:\u002F\u002Fapi.skillboss.co\u002Fv1\u002Fpilot\" \\\n  -H \"Authorization: Bearer $SKILLBOSS_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"type\":\"audio\",\"capability\":\"stem separation\",\"inputs\":{\"url\":\"URL\",\"mode\":\"single\",\"stem\":\"vocals\"}}'\n```\n\n### Response Format\n\n```json\n{\n  \"data\": {\n    \"result\": {\n      \"download_urls\": {\n        \"vocals\": \"https:\u002F\u002F...\",\n        \"drums\": \"https:\u002F\u002F...\",\n        \"bass\": \"https:\u002F\u002F...\",\n        \"other\": \"https:\u002F\u002F...\"\n      },\n      \"quality_scores\": {\n        \"vocals\": 0.95,\n        \"drums\": 0.88\n      }\n    }\n  }\n}\n```\n\n---\n\n## Text to Speech\n\nGenerate speech from text with 50+ voices in 60+ languages via SkillBoss API Hub.\n\n### Python\n\n```python\n# Generate speech\nresult = pilot({\n    \"type\": \"tts\",\n    \"inputs\": {\n        \"text\": \"Hello, world! This is a test.\",\n        \"voice\": \"alloy\",\n        \"speed\": 1.0\n    },\n    \"prefer\": \"balanced\"\n})\naudio_url = result[\"data\"][\"result\"][\"audio_url\"]\nprint(audio_url)\n\n# Specify language\nresult = pilot({\n    \"type\": \"tts\",\n    \"inputs\": {\n        \"text\": \"Bonjour le monde\",\n        \"voice\": \"alloy\",\n        \"language\": \"fr\",\n        \"speed\": 1.0\n    },\n    \"prefer\": \"quality\"\n})\naudio_url = result[\"data\"][\"result\"][\"audio_url\"]\n```\n\n### cURL\n\n```bash\n# Generate speech\ncurl -X POST \"https:\u002F\u002Fapi.skillboss.co\u002Fv1\u002Fpilot\" \\\n  -H \"Authorization: Bearer $SKILLBOSS_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"type\":\"tts\",\"inputs\":{\"text\":\"Hello world, this is a test\",\"voice\":\"alloy\",\"speed\":1.0},\"prefer\":\"balanced\"}'\n```\n\n### Parameters\n\n| Field | Required | Description |\n|-------|----------|-------------|\n| text | yes | Text to speak (max 5000 chars) |\n| voice | no | Voice name or ID (e.g. `alloy`, `echo`, `fable`) |\n| speed | no | 0.25 - 4.0 (default: 1.0) |\n| language | no | ISO code, auto-detected if omitted |\n\n### Response\n\n```python\naudio_url = result[\"data\"][\"result\"][\"audio_url\"]\n```\n\n---\n\n## Speaker Separation\n\nSeparate audio by speaker with automatic diarization via SkillBoss API Hub.\n\n### Python\n\n```python\n# Diarize from file\nimport base64\naudio_b64 = base64.b64encode(open(\".\u002Fmeeting.mp3\", \"rb\").read()).decode()\nresult = pilot({\n    \"type\": \"stt\",\n    \"capability\": \"speaker diarization\",\n    \"inputs\": {\n        \"audio_data\": audio_b64,\n        \"filename\": \"meeting.mp3\",\n        \"num_speakers\": 3\n    },\n    \"prefer\": \"quality\"\n})\nfor segment in result[\"data\"][\"result\"][\"segments\"]:\n    print(f\"Speaker {segment['speaker']}: {segment['text']} [{segment['start']:.1f}s - {segment['end']:.1f}s]\")\n\n# Diarize from URL\nresult = pilot({\n    \"type\": \"stt\",\n    \"capability\": \"speaker diarization\",\n    \"inputs\": {\n        \"url\": \"https:\u002F\u002Fyoutube.com\u002Fwatch?v=VIDEO_ID\",\n        \"num_speakers\": 2\n    },\n    \"prefer\": \"balanced\"\n})\nsegments = result[\"data\"][\"result\"][\"segments\"]\n```\n\n### cURL\n\n```bash\n# Diarize from URL\ncurl -X POST \"https:\u002F\u002Fapi.skillboss.co\u002Fv1\u002Fpilot\" \\\n  -H \"Authorization: Bearer $SKILLBOSS_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"type\":\"stt\",\"capability\":\"speaker diarization\",\"inputs\":{\"url\":\"https:\u002F\u002Fyoutube.com\u002Fwatch?v=VIDEO_ID\",\"num_speakers\":2},\"prefer\":\"balanced\"}'\n```\n\n---\n\n## Speech to Text (Transcription)\n\nTranscribe audio\u002Fvideo with speaker diarization, word-level timestamps, and multiple output formats via SkillBoss API Hub.\n\n### Python\n\n```python\n# Transcribe from URL\nresult = pilot({\n    \"type\": \"stt\",\n    \"inputs\": {\n        \"url\": \"https:\u002F\u002Fyoutube.com\u002Fwatch?v=VIDEO_ID\",\n        \"speaker_diarization\": True,\n        \"word_timestamps\": True\n    },\n    \"prefer\": \"balanced\"\n})\ntext = result[\"data\"][\"result\"][\"text\"]\nsegments = result[\"data\"][\"result\"].get(\"segments\", [])\nprint(f\"Transcript: {text}\")\nfor seg in segments:\n    print(f\"[{seg.get('start', 0):.1f}s] {seg.get('speaker','?')}: {seg['text']}\")\n\n# Transcribe local file\nimport base64\naudio_b64 = base64.b64encode(open(\".\u002Frecording.mp3\", \"rb\").read()).decode()\nresult = pilot({\n    \"type\": \"stt\",\n    \"inputs\": {\n        \"audio_data\": audio_b64,\n        \"filename\": \"recording.mp3\",\n        \"language\": \"en\",\n        \"speaker_diarization\": True\n    },\n    \"prefer\": \"balanced\"\n})\ntext = result[\"data\"][\"result\"][\"text\"]\n```\n\n### cURL\n\n```bash\n# Transcribe from URL\ncurl -X POST \"https:\u002F\u002Fapi.skillboss.co\u002Fv1\u002Fpilot\" \\\n  -H \"Authorization: Bearer $SKILLBOSS_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"type\":\"stt\",\"inputs\":{\"url\":\"https:\u002F\u002Fyoutube.com\u002Fwatch?v=ID\",\"speaker_diarization\":true,\"word_timestamps\":true},\"prefer\":\"balanced\"}'\n```\n\n### Parameters\n\n| Field | Required | Description |\n|-------|----------|-------------|\n| url | yes (or audio_data) | URL to transcribe (YouTube, SoundCloud, direct links) |\n| audio_data | yes (or url) | Base64-encoded audio content |\n| filename | with audio_data | Original filename for format detection |\n| language | no | ISO 639-1 code (auto-detected if omitted) |\n| speaker_diarization | no | Enable speaker identification (default: false) |\n| word_timestamps | no | Enable word-level timestamps (default: true) |\n\n### Response\n\n```python\ntext = result[\"data\"][\"result\"][\"text\"]\nsegments = result[\"data\"][\"result\"].get(\"segments\", [])  # with speaker_diarization\n```\n\n---\n\n## Noise Reduction\n\nRemove background noise from audio files via SkillBoss API Hub.\n\n### Python\n\n```python\n# Denoise from file\nimport base64\naudio_b64 = base64.b64encode(open(\".\u002Fnoisy-audio.mp3\", \"rb\").read()).decode()\nresult = pilot({\n    \"type\": \"audio\",\n    \"capability\": \"noise reduction\",\n    \"inputs\": {\n        \"audio_data\": audio_b64,\n        \"filename\": \"noisy-audio.mp3\"\n    },\n    \"prefer\": \"quality\"\n})\nclean_url = result[\"data\"][\"result\"][\"audio_url\"]\nprint(f\"Clean audio: {clean_url}\")\n\n# Denoise from URL\nresult = pilot({\n    \"type\": \"audio\",\n    \"capability\": \"noise reduction\",\n    \"inputs\": {\n        \"url\": \"https:\u002F\u002Fexample.com\u002Fnoisy.mp3\"\n    },\n    \"prefer\": \"balanced\"\n})\nclean_url = result[\"data\"][\"result\"][\"audio_url\"]\n```\n\n### cURL\n\n```bash\n# Denoise from URL\ncurl -X POST \"https:\u002F\u002Fapi.skillboss.co\u002Fv1\u002Fpilot\" \\\n  -H \"Authorization: Bearer $SKILLBOSS_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"type\":\"audio\",\"capability\":\"noise reduction\",\"inputs\":{\"url\":\"https:\u002F\u002Fexample.com\u002Fnoisy.mp3\"},\"prefer\":\"quality\"}'\n```\n\n### Response\n\n```python\nclean_url = result[\"data\"][\"result\"][\"audio_url\"]\n```\n\n---\n\n## Chain Mode (Multi-step Workflow)\n\nUse SkillBoss Chain mode to combine multiple audio steps in one call.\n\n### Python\n\n```python\n# STT → Chat (summarize) → TTS pipeline\nresult = pilot({\n    \"chain\": [\n        {\"type\": \"stt\"},\n        {\"type\": \"chat\", \"capability\": \"summarize\"},\n        {\"type\": \"tts\"}\n    ]\n})\n\n# Transcribe and translate\nresult = pilot({\n    \"chain\": [\n        {\"type\": \"stt\"},\n        {\"type\": \"chat\", \"capability\": \"translate to English\"}\n    ]\n})\n```\n\n---\n\n## API Endpoint Summary\n\nAll capabilities route through a single endpoint:\n\n| Service | SkillBoss type | capability |\n|---------|---------------|------------|\n| Music generation | `music` | — |\n| TTS | `tts` | — |\n| STT \u002F Transcription | `stt` | — |\n| Speaker separation | `stt` | `speaker diarization` |\n| Stem separation | `audio` | `stem separation` |\n| Noise reduction | `audio` | `noise reduction` |\n\n**Single endpoint:** `POST https:\u002F\u002Fapi.skillboss.co\u002Fv1\u002Fpilot`\n**Auth:** `Authorization: Bearer $SKILLBOSS_API_KEY`\n\n## Response Format Summary\n\n| Capability | Result path |\n|-----------|-------------|\n| Music generation | `data.result.audio_url` |\n| TTS | `data.result.audio_url` |\n| STT (text) | `data.result.text` |\n| STT (segments) | `data.result.segments` |\n| Stem separation | `data.result.download_urls` |\n| Noise reduction | `data.result.audio_url` |\n",{"name":5,"description":7},"master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fm\u002Fmodesty-audiopod",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":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill audiopod",{"tool":39,"command":40},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill audiopod",{"tool":42,"command":43},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill audiopod","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fm\u002Fmodesty-audiopod\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"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":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"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":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"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":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"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":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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",[],[]]