{ "schemaVersion": "1.0", "item": { "slug": "acestep-lyrics-transcription", "name": "acestep-lyrics-transcription", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/DumoeDss/acestep-lyrics-transcription", "canonicalUrl": "https://clawhub.ai/DumoeDss/acestep-lyrics-transcription", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/acestep-lyrics-transcription", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=acestep-lyrics-transcription", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "scripts/acestep-lyrics-transcription.sh", "scripts/config.example.json", "SKILL.md" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-07T17:22:31.273Z", "expiresAt": "2026-05-14T17:22:31.273Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentDisposition": "attachment; filename=\"afrexai-annual-report-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/acestep-lyrics-transcription" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/acestep-lyrics-transcription", "agentPageUrl": "https://openagent3.xyz/skills/acestep-lyrics-transcription/agent", "manifestUrl": "https://openagent3.xyz/skills/acestep-lyrics-transcription/agent.json", "briefUrl": "https://openagent3.xyz/skills/acestep-lyrics-transcription/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Lyrics Transcription Skill", "body": "Transcribe audio files to timestamped lyrics (LRC/SRT/JSON) via OpenAI Whisper or ElevenLabs Scribe API." }, { "title": "API Key Setup Guide", "body": "Before transcribing, you MUST check whether the user's API key is configured. Run the following command to check:\n\ncd \"{project_root}/{.claude or .codex}/skills/acestep-lyrics-transcription/\" && bash ./scripts/acestep-lyrics-transcription.sh config --check-key\n\nThis command only reports whether the active provider's API key is set or empty — it does NOT print the actual key value. NEVER read or display the user's API key content. Do not use config --get on key fields or read config.json directly. The config --list command is safe — it automatically masks API keys as *** in output.\n\nIf the command reports the key is empty, you MUST stop and guide the user to configure it before proceeding. Do NOT attempt transcription without a valid key — it will fail.\n\nUse AskUserQuestion to ask the user to provide their API key, with the following options and guidance:\n\nTell the user which provider is currently active (openai or elevenlabs) and that its API key is not configured. Explain that transcription cannot proceed without it.\nProvide clear instructions on where to obtain a key:\n\nOpenAI: Get an API key at https://platform.openai.com/api-keys — requires an OpenAI account with billing enabled. The Whisper API costs ~$0.006/min.\nElevenLabs: Get an API key at https://elevenlabs.io/app/settings/api-keys — requires an ElevenLabs account. Free tier includes limited credits.\n\n\nAlso offer the option to switch to the other provider if they already have a key for it.\nOnce the user provides the key, configure it using:\ncd \"{project_root}/{.claude or .codex}/skills/acestep-lyrics-transcription/\" && bash ./scripts/acestep-lyrics-transcription.sh config --set .api_key \n\n\nIf the user wants to switch providers, also run:\ncd \"{project_root}/{.claude or .codex}/skills/acestep-lyrics-transcription/\" && bash ./scripts/acestep-lyrics-transcription.sh config --set provider \n\n\nAfter configuring, re-run config --check-key to verify the key is set before proceeding.\n\nIf the API key is already configured, proceed directly to transcription without asking." }, { "title": "Quick Start", "body": "# 1. cd to this skill's directory\ncd {project_root}/{.claude or .codex}/skills/acestep-lyrics-transcription/\n\n# 2. Configure API key (choose one)\n./scripts/acestep-lyrics-transcription.sh config --set openai.api_key sk-...\n# or\n./scripts/acestep-lyrics-transcription.sh config --set elevenlabs.api_key ...\n./scripts/acestep-lyrics-transcription.sh config --set provider elevenlabs\n\n# 3. Transcribe\n./scripts/acestep-lyrics-transcription.sh transcribe --audio /path/to/song.mp3 --language zh\n\n# 4. Output saved to: {project_root}/acestep_output/.lrc" }, { "title": "Prerequisites", "body": "curl, jq, python3 (or python)\nAn API key for OpenAI or ElevenLabs" }, { "title": "Script Usage", "body": "./scripts/acestep-lyrics-transcription.sh transcribe --audio [options]\n\nOptions:\n -a, --audio Audio file path (required)\n -l, --language Language code (zh, en, ja, etc.)\n -f, --format Output format: lrc, srt, json (default: lrc)\n -p, --provider API provider: openai, elevenlabs (overrides config)\n -o, --output Output file path (default: acestep_output/.lrc)" }, { "title": "Post-Transcription Lyrics Correction (MANDATORY)", "body": "CRITICAL: After transcription, you MUST manually correct the LRC file before using it for MV rendering. Transcription models frequently produce errors on sung lyrics:\n\nProper nouns: \"ACE-Step\" → \"AC step\", \"Spotify\" → \"spot a fly\"\nSimilar-sounding words: \"arrives\" → \"eyes\", \"open source\" → \"open sores\"\nMerged/split words: \"lighting up\" → \"lightin' nup\"" }, { "title": "Correction Workflow", "body": "Read the transcribed LRC file using the Read tool\nRead the original lyrics from the ACE-Step output JSON file\nUse original lyrics as a whole reference: Do NOT attempt line-by-line alignment — transcription often splits, merges, or reorders lines differently from the original. Instead, read the original lyrics in full to understand the correct wording, then scan each LRC line and fix any misrecognized words based on your knowledge of what the original lyrics say.\nFix transcription errors: Replace misrecognized words with the correct original words, keeping the timestamps intact\nWrite the corrected LRC back using the Write tool" }, { "title": "What to Correct", "body": "Replace misrecognized words with their correct original versions\nKeep all [MM:SS.cc] timestamps exactly as-is (timestamps from transcription are accurate)\nDo NOT add structure tags like [Verse] or [Chorus] — the LRC should only have timestamped text lines" }, { "title": "Example", "body": "Transcribed (wrong):\n\n[00:46.96]AC step alive,\n[00:50.80]one point five eyes.\n\nOriginal lyrics reference:\n\nACE-Step alive\nOne point five arrives\n\nCorrected (right):\n\n[00:46.96]ACE-Step alive,\n[00:50.80]One point five arrives." }, { "title": "Configuration", "body": "Config file: scripts/config.json\n\n# Switch provider\n./scripts/acestep-lyrics-transcription.sh config --set provider openai\n./scripts/acestep-lyrics-transcription.sh config --set provider elevenlabs\n\n# Set API keys\n./scripts/acestep-lyrics-transcription.sh config --set openai.api_key sk-...\n./scripts/acestep-lyrics-transcription.sh config --set elevenlabs.api_key ...\n\n# View config\n./scripts/acestep-lyrics-transcription.sh config --list\n\nOptionDefaultDescriptionprovideropenaiActive provider: openai or elevenlabsoutput_formatlrcDefault output: lrc, srt, or jsonopenai.api_key\"\"OpenAI API keyopenai.api_urlhttps://api.openai.com/v1OpenAI API base URLopenai.modelwhisper-1OpenAI model (whisper-1 for word timestamps)elevenlabs.api_key\"\"ElevenLabs API keyelevenlabs.api_urlhttps://api.elevenlabs.io/v1ElevenLabs API base URLelevenlabs.modelscribe_v2ElevenLabs model" }, { "title": "Provider Notes", "body": "ProviderModelWord TimestampsPricingOpenAIwhisper-1Yes (segment + word)$0.006/minElevenLabsscribe_v2Yes (word-level)Varies by plan\n\nOpenAI whisper-1 is the only OpenAI model supporting word-level timestamps\nElevenLabs scribe_v2 returns word-level timestamps with type filtering\nBoth support multilingual transcription" }, { "title": "Examples", "body": "# Basic transcription (uses config defaults)\n./scripts/acestep-lyrics-transcription.sh transcribe --audio song.mp3\n\n# Chinese song to LRC\n./scripts/acestep-lyrics-transcription.sh transcribe --audio song.mp3 --language zh\n\n# Use ElevenLabs, output SRT\n./scripts/acestep-lyrics-transcription.sh transcribe --audio song.mp3 --provider elevenlabs --format srt\n\n# Custom output path\n./scripts/acestep-lyrics-transcription.sh transcribe --audio song.mp3 --output ./my_lyrics.lrc" } ], "body": "Lyrics Transcription Skill\n\nTranscribe audio files to timestamped lyrics (LRC/SRT/JSON) via OpenAI Whisper or ElevenLabs Scribe API.\n\nAPI Key Setup Guide\n\nBefore transcribing, you MUST check whether the user's API key is configured. Run the following command to check:\n\ncd \"{project_root}/{.claude or .codex}/skills/acestep-lyrics-transcription/\" && bash ./scripts/acestep-lyrics-transcription.sh config --check-key\n\n\nThis command only reports whether the active provider's API key is set or empty — it does NOT print the actual key value. NEVER read or display the user's API key content. Do not use config --get on key fields or read config.json directly. The config --list command is safe — it automatically masks API keys as *** in output.\n\nIf the command reports the key is empty, you MUST stop and guide the user to configure it before proceeding. Do NOT attempt transcription without a valid key — it will fail.\n\nUse AskUserQuestion to ask the user to provide their API key, with the following options and guidance:\n\nTell the user which provider is currently active (openai or elevenlabs) and that its API key is not configured. Explain that transcription cannot proceed without it.\nProvide clear instructions on where to obtain a key:\nOpenAI: Get an API key at https://platform.openai.com/api-keys — requires an OpenAI account with billing enabled. The Whisper API costs ~$0.006/min.\nElevenLabs: Get an API key at https://elevenlabs.io/app/settings/api-keys — requires an ElevenLabs account. Free tier includes limited credits.\nAlso offer the option to switch to the other provider if they already have a key for it.\nOnce the user provides the key, configure it using:\ncd \"{project_root}/{.claude or .codex}/skills/acestep-lyrics-transcription/\" && bash ./scripts/acestep-lyrics-transcription.sh config --set .api_key \n\nIf the user wants to switch providers, also run:\ncd \"{project_root}/{.claude or .codex}/skills/acestep-lyrics-transcription/\" && bash ./scripts/acestep-lyrics-transcription.sh config --set provider \n\nAfter configuring, re-run config --check-key to verify the key is set before proceeding.\n\nIf the API key is already configured, proceed directly to transcription without asking.\n\nQuick Start\n# 1. cd to this skill's directory\ncd {project_root}/{.claude or .codex}/skills/acestep-lyrics-transcription/\n\n# 2. Configure API key (choose one)\n./scripts/acestep-lyrics-transcription.sh config --set openai.api_key sk-...\n# or\n./scripts/acestep-lyrics-transcription.sh config --set elevenlabs.api_key ...\n./scripts/acestep-lyrics-transcription.sh config --set provider elevenlabs\n\n# 3. Transcribe\n./scripts/acestep-lyrics-transcription.sh transcribe --audio /path/to/song.mp3 --language zh\n\n# 4. Output saved to: {project_root}/acestep_output/.lrc\n\nPrerequisites\ncurl, jq, python3 (or python)\nAn API key for OpenAI or ElevenLabs\nScript Usage\n./scripts/acestep-lyrics-transcription.sh transcribe --audio [options]\n\nOptions:\n -a, --audio Audio file path (required)\n -l, --language Language code (zh, en, ja, etc.)\n -f, --format Output format: lrc, srt, json (default: lrc)\n -p, --provider API provider: openai, elevenlabs (overrides config)\n -o, --output Output file path (default: acestep_output/.lrc)\n\nPost-Transcription Lyrics Correction (MANDATORY)\n\nCRITICAL: After transcription, you MUST manually correct the LRC file before using it for MV rendering. Transcription models frequently produce errors on sung lyrics:\n\nProper nouns: \"ACE-Step\" → \"AC step\", \"Spotify\" → \"spot a fly\"\nSimilar-sounding words: \"arrives\" → \"eyes\", \"open source\" → \"open sores\"\nMerged/split words: \"lighting up\" → \"lightin' nup\"\nCorrection Workflow\nRead the transcribed LRC file using the Read tool\nRead the original lyrics from the ACE-Step output JSON file\nUse original lyrics as a whole reference: Do NOT attempt line-by-line alignment — transcription often splits, merges, or reorders lines differently from the original. Instead, read the original lyrics in full to understand the correct wording, then scan each LRC line and fix any misrecognized words based on your knowledge of what the original lyrics say.\nFix transcription errors: Replace misrecognized words with the correct original words, keeping the timestamps intact\nWrite the corrected LRC back using the Write tool\nWhat to Correct\nReplace misrecognized words with their correct original versions\nKeep all [MM:SS.cc] timestamps exactly as-is (timestamps from transcription are accurate)\nDo NOT add structure tags like [Verse] or [Chorus] — the LRC should only have timestamped text lines\nExample\n\nTranscribed (wrong):\n\n[00:46.96]AC step alive,\n[00:50.80]one point five eyes.\n\n\nOriginal lyrics reference:\n\nACE-Step alive\nOne point five arrives\n\n\nCorrected (right):\n\n[00:46.96]ACE-Step alive,\n[00:50.80]One point five arrives.\n\nConfiguration\n\nConfig file: scripts/config.json\n\n# Switch provider\n./scripts/acestep-lyrics-transcription.sh config --set provider openai\n./scripts/acestep-lyrics-transcription.sh config --set provider elevenlabs\n\n# Set API keys\n./scripts/acestep-lyrics-transcription.sh config --set openai.api_key sk-...\n./scripts/acestep-lyrics-transcription.sh config --set elevenlabs.api_key ...\n\n# View config\n./scripts/acestep-lyrics-transcription.sh config --list\n\nOption\tDefault\tDescription\nprovider\topenai\tActive provider: openai or elevenlabs\noutput_format\tlrc\tDefault output: lrc, srt, or json\nopenai.api_key\t\"\"\tOpenAI API key\nopenai.api_url\thttps://api.openai.com/v1\tOpenAI API base URL\nopenai.model\twhisper-1\tOpenAI model (whisper-1 for word timestamps)\nelevenlabs.api_key\t\"\"\tElevenLabs API key\nelevenlabs.api_url\thttps://api.elevenlabs.io/v1\tElevenLabs API base URL\nelevenlabs.model\tscribe_v2\tElevenLabs model\nProvider Notes\nProvider\tModel\tWord Timestamps\tPricing\nOpenAI\twhisper-1\tYes (segment + word)\t$0.006/min\nElevenLabs\tscribe_v2\tYes (word-level)\tVaries by plan\nOpenAI whisper-1 is the only OpenAI model supporting word-level timestamps\nElevenLabs scribe_v2 returns word-level timestamps with type filtering\nBoth support multilingual transcription\nExamples\n# Basic transcription (uses config defaults)\n./scripts/acestep-lyrics-transcription.sh transcribe --audio song.mp3\n\n# Chinese song to LRC\n./scripts/acestep-lyrics-transcription.sh transcribe --audio song.mp3 --language zh\n\n# Use ElevenLabs, output SRT\n./scripts/acestep-lyrics-transcription.sh transcribe --audio song.mp3 --provider elevenlabs --format srt\n\n# Custom output path\n./scripts/acestep-lyrics-transcription.sh transcribe --audio song.mp3 --output ./my_lyrics.lrc" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/DumoeDss/acestep-lyrics-transcription", "publisherUrl": "https://clawhub.ai/DumoeDss/acestep-lyrics-transcription", "owner": "DumoeDss", "version": "1.0.1", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/acestep-lyrics-transcription", "downloadUrl": "https://openagent3.xyz/downloads/acestep-lyrics-transcription", "agentUrl": "https://openagent3.xyz/skills/acestep-lyrics-transcription/agent", "manifestUrl": "https://openagent3.xyz/skills/acestep-lyrics-transcription/agent.json", "briefUrl": "https://openagent3.xyz/skills/acestep-lyrics-transcription/agent.md" } }