{ "schemaVersion": "1.0", "item": { "slug": "voiceai-voiceover-creator", "name": "Voice.ai: Creator Voiceover Forge", "source": "tencent", "type": "skill", "category": "内容创作", "sourceUrl": "https://clawhub.ai/gizmoGremlin/voiceai-voiceover-creator", "canonicalUrl": "https://clawhub.ai/gizmoGremlin/voiceai-voiceover-creator", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/voiceai-voiceover-creator", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=voiceai-voiceover-creator", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "README.md", "SKILL.md", "eslint.config.js", "examples/podcast_script.md", "examples/shorts_script.txt", "examples/youtube_script.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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-30T16:55:25.780Z", "expiresAt": "2026-05-07T16:55:25.780Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentDisposition": "attachment; filename=\"network-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/voiceai-voiceover-creator" }, "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/voiceai-voiceover-creator", "agentPageUrl": "https://openagent3.xyz/skills/voiceai-voiceover-creator/agent", "manifestUrl": "https://openagent3.xyz/skills/voiceai-voiceover-creator/agent.json", "briefUrl": "https://openagent3.xyz/skills/voiceai-voiceover-creator/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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Voice.ai Creator Voiceover Pipeline", "body": "This skill follows the Agent Skills specification.\n\nTurn any script into a publish-ready voiceover — complete with numbered segments, a stitched master, YouTube chapters, SRT captions, and a beautiful review page. Optionally, replace the audio track on an existing video.\n\nBuilt for creators who want studio-quality voiceovers without the studio. Powered by Voice.ai." }, { "title": "When to use this skill", "body": "ScenarioWhy it fitsYouTube long-formFull narration with chapter markers and captionsYouTube ShortsQuick hooks with the shortform templatePodcastsConsistent host voice, intro/outro templatesCourse contentProfessional narration for educational videosQuick iterationSmart caching — edit one section, only that segment re-rendersVideo audio replacementDrop AI voiceover onto screen recordings or B-roll" }, { "title": "The one-command workflow", "body": "Have a script and a video? Turn them into a finished video with AI voiceover in one shot:\n\nnode voiceai-vo.cjs build \\\n --input my-script.md \\\n --voice oliver \\\n --title \"My Video\" \\\n --video ./my-recording.mp4 \\\n --mux\n\nThis renders the voiceover, stitches the master audio, and drops it onto your video — all in one command. Output:\n\nout/my-video/muxed.mp4 — your video with the new voiceover\nout/my-video/master.wav — the standalone audio\nout/my-video/review.html — listen and review each segment\nout/my-video/chapters.txt — YouTube-ready chapter timestamps\nout/my-video/captions.srt — SRT captions\n\nUse --sync pad if the audio is shorter than the video, or --sync trim to cut it to match." }, { "title": "Requirements", "body": "Node.js 20+ — runtime (no npm install needed — the CLI is a single bundled file)\nVOICE_AI_API_KEY — set as environment variable or in a .env file in the skill root. Get a key at voice.ai/dashboard.\nffmpeg (optional) — needed for master stitching, MP3 encoding, loudness normalization, and video muxing. The pipeline still produces individual segments, the review page, chapters, and captions without it." }, { "title": "Configuration", "body": "The skill reads VOICE_AI_API_KEY from (in order):\n\nEnvironment variable VOICE_AI_API_KEY\nEnvironment variable VOICEAI_API_KEY (alternate)\n.env file in the skill root\n\necho 'VOICE_AI_API_KEY=your-key-here' > .env\n\nUse --mock on any command to run the full pipeline without an API key (produces placeholder audio)." }, { "title": "build — Generate a voiceover from a script", "body": "node voiceai-vo.cjs build \\\n --input \\\n --voice \\\n --title \"My Project\" \\\n [--template youtube|podcast|shortform] \\\n [--language en] \\\n [--video input.mp4 --mux --sync shortest] \\\n [--force] [--mock]\n\nWhat it does:\n\nReads the script and splits it into segments (by ## headings for .md, or by sentence boundaries for .txt)\nOptionally prepends/appends template intro/outro segments\nRenders each segment via Voice.ai TTS as a numbered WAV file\nStitches a master audio file (if ffmpeg is available)\nGenerates chapters, captions, a review page, and metadata files\nOptionally muxes the voiceover into an existing video\n\nFull options:\n\nOptionDescription-i, --input Script file (.txt or .md) — required-v, --voice Voice alias or UUID — required-t, --title Project title (defaults to filename)--template <name>youtube, podcast, or shortform--mode <mode>headings or auto (default: headings for .md)--max-chars <n>Max characters per auto-chunk (default: 1500)--language <code>Language code (default: en)--video <path>Input video for muxing--muxEnable video muxing (requires --video)--sync <policy>shortest, pad, or trim (default: shortest)--forceRe-render all segments (ignore cache)--mockMock mode — no API calls, placeholder audio-o, --out <dir>Custom output directory" }, { "title": "replace-audio — Swap the audio track on a video", "body": "node voiceai-vo.cjs replace-audio \\\n --video ./input.mp4 \\\n --audio ./out/my-project/master.wav \\\n [--out ./out/my-project/muxed.mp4] \\\n [--sync shortest|pad|trim]\n\nRequires ffmpeg. If not installed, generates helper shell/PowerShell scripts instead.\n\nSync policyBehaviorshortest (default)Output ends when the shorter track endspadPad audio with silence to match video durationtrimTrim audio to match video duration\n\nVideo stream is copied without re-encoding (-c:v copy). Audio is encoded as AAC. A mux report is saved alongside the output.\n\nPrivacy: Video processing is entirely local. Only script text is sent to Voice.ai for TTS." }, { "title": "voices — List available voices", "body": "node voiceai-vo.cjs voices [--limit 20] [--query \"deep\"] [--mock]" }, { "title": "Available voices", "body": "Use short aliases or full UUIDs with --voice:\n\nAliasVoiceGenderStyleellieEllieFYouthful, vibrant vloggeroliverOliverMFriendly BritishlilithLilithFSoft, femininesmoothSmooth Calm VoiceMDeep, smooth narratorcorpseCorpse HusbandMDeep, distinctiveskadiSkadiFAnime characterzhongliZhongliMDeep, authoritativefloraFloraFCheerful, high pitchchiefMaster ChiefMHeroic, commanding\n\nThe voices command also returns any additional voices available on the API. Voice list is cached for 10 minutes." }, { "title": "Build outputs", "body": "After a build, the output directory contains:\n\nout/<title-slug>/\n segments/ # Numbered WAV files (001-intro.wav, 002-section.wav, …)\n master.wav # Stitched audio (requires ffmpeg)\n master.mp3 # MP3 encode (requires ffmpeg)\n manifest.json # Build metadata: voice, template, segment list, hashes\n timeline.json # Segment durations and start times\n review.html # Interactive review page with audio players\n chapters.txt # YouTube-friendly chapter timestamps\n captions.srt # SRT captions using segment boundaries\n description.txt # YouTube description with chapters + Voice.ai credit" }, { "title": "review.html", "body": "A standalone HTML page with:\n\nMaster audio player (if stitched)\nIndividual segment players with titles and durations\nCollapsible script text for each segment\nRegeneration command hints" }, { "title": "Templates", "body": "Templates auto-inject intro/outro segments around the script content:\n\nTemplatePrependsAppendsyoutubetemplates/youtube_intro.txttemplates/youtube_outro.txtpodcasttemplates/podcast_intro.txt—shortformtemplates/shortform_hook.txt—\n\nEdit the files in templates/ to customize the intro/outro text." }, { "title": "Caching", "body": "Segments are cached by a hash of: text content + voice ID + language.\n\nUnchanged segments are skipped on rebuild — fast iteration\nModified segments are re-rendered automatically\nUse --force to re-render everything\nCache manifest is stored in segments/.cache.json" }, { "title": "Multilingual support", "body": "Voice.ai supports 11 languages. Use --language <code> to switch:\n\nen, es, fr, de, it, pt, pl, ru, nl, sv, ca\n\nThe pipeline auto-selects the multilingual TTS model for non-English languages." }, { "title": "Troubleshooting", "body": "IssueSolutionffmpeg missingPipeline still works — you get segments, review page, chapters, captions. Install ffmpeg for master stitching and video muxing.Rate limits (429)Segments render sequentially, which stays under most limits. Wait and retry.Insufficient credits (402)Top up at voice.ai/dashboard. Cached segments won't re-use credits on retry.Long scriptsCaching makes rebuilds fast. Text over 490 chars per segment is automatically split across API calls.Windows pathsWrap paths with spaces in quotes: --input \"C:\\My Scripts\\script.md\"\n\nSee references/TROUBLESHOOTING.md for more." }, { "title": "References", "body": "Agent Skills Specification\nVoice.ai\nreferences/VOICEAI_API.md — API endpoints, audio formats, models\nreferences/TROUBLESHOOTING.md — Common issues and fixes" } ], "body": "Voice.ai Creator Voiceover Pipeline\n\nThis skill follows the Agent Skills specification.\n\nTurn any script into a publish-ready voiceover — complete with numbered segments, a stitched master, YouTube chapters, SRT captions, and a beautiful review page. Optionally, replace the audio track on an existing video.\n\nBuilt for creators who want studio-quality voiceovers without the studio. Powered by Voice.ai.\n\nWhen to use this skill\nScenario\tWhy it fits\nYouTube long-form\tFull narration with chapter markers and captions\nYouTube Shorts\tQuick hooks with the shortform template\nPodcasts\tConsistent host voice, intro/outro templates\nCourse content\tProfessional narration for educational videos\nQuick iteration\tSmart caching — edit one section, only that segment re-renders\nVideo audio replacement\tDrop AI voiceover onto screen recordings or B-roll\nThe one-command workflow\n\nHave a script and a video? Turn them into a finished video with AI voiceover in one shot:\n\nnode voiceai-vo.cjs build \\\n --input my-script.md \\\n --voice oliver \\\n --title \"My Video\" \\\n --video ./my-recording.mp4 \\\n --mux\n\n\nThis renders the voiceover, stitches the master audio, and drops it onto your video — all in one command. Output:\n\nout/my-video/muxed.mp4 — your video with the new voiceover\nout/my-video/master.wav — the standalone audio\nout/my-video/review.html — listen and review each segment\nout/my-video/chapters.txt — YouTube-ready chapter timestamps\nout/my-video/captions.srt — SRT captions\n\nUse --sync pad if the audio is shorter than the video, or --sync trim to cut it to match.\n\nRequirements\nNode.js 20+ — runtime (no npm install needed — the CLI is a single bundled file)\nVOICE_AI_API_KEY — set as environment variable or in a .env file in the skill root. Get a key at voice.ai/dashboard.\nffmpeg (optional) — needed for master stitching, MP3 encoding, loudness normalization, and video muxing. The pipeline still produces individual segments, the review page, chapters, and captions without it.\nConfiguration\n\nThe skill reads VOICE_AI_API_KEY from (in order):\n\nEnvironment variable VOICE_AI_API_KEY\nEnvironment variable VOICEAI_API_KEY (alternate)\n.env file in the skill root\necho 'VOICE_AI_API_KEY=your-key-here' > .env\n\n\nUse --mock on any command to run the full pipeline without an API key (produces placeholder audio).\n\nCommands\nbuild — Generate a voiceover from a script\nnode voiceai-vo.cjs build \\\n --input <script.md or script.txt> \\\n --voice <voice-alias-or-uuid> \\\n --title \"My Project\" \\\n [--template youtube|podcast|shortform] \\\n [--language en] \\\n [--video input.mp4 --mux --sync shortest] \\\n [--force] [--mock]\n\n\nWhat it does:\n\nReads the script and splits it into segments (by ## headings for .md, or by sentence boundaries for .txt)\nOptionally prepends/appends template intro/outro segments\nRenders each segment via Voice.ai TTS as a numbered WAV file\nStitches a master audio file (if ffmpeg is available)\nGenerates chapters, captions, a review page, and metadata files\nOptionally muxes the voiceover into an existing video\n\nFull options:\n\nOption\tDescription\n-i, --input <path>\tScript file (.txt or .md) — required\n-v, --voice <id>\tVoice alias or UUID — required\n-t, --title <title>\tProject title (defaults to filename)\n--template <name>\tyoutube, podcast, or shortform\n--mode <mode>\theadings or auto (default: headings for .md)\n--max-chars <n>\tMax characters per auto-chunk (default: 1500)\n--language <code>\tLanguage code (default: en)\n--video <path>\tInput video for muxing\n--mux\tEnable video muxing (requires --video)\n--sync <policy>\tshortest, pad, or trim (default: shortest)\n--force\tRe-render all segments (ignore cache)\n--mock\tMock mode — no API calls, placeholder audio\n-o, --out <dir>\tCustom output directory\nreplace-audio — Swap the audio track on a video\nnode voiceai-vo.cjs replace-audio \\\n --video ./input.mp4 \\\n --audio ./out/my-project/master.wav \\\n [--out ./out/my-project/muxed.mp4] \\\n [--sync shortest|pad|trim]\n\n\nRequires ffmpeg. If not installed, generates helper shell/PowerShell scripts instead.\n\nSync policy\tBehavior\nshortest (default)\tOutput ends when the shorter track ends\npad\tPad audio with silence to match video duration\ntrim\tTrim audio to match video duration\n\nVideo stream is copied without re-encoding (-c:v copy). Audio is encoded as AAC. A mux report is saved alongside the output.\n\nPrivacy: Video processing is entirely local. Only script text is sent to Voice.ai for TTS.\n\nvoices — List available voices\nnode voiceai-vo.cjs voices [--limit 20] [--query \"deep\"] [--mock]\n\nAvailable voices\n\nUse short aliases or full UUIDs with --voice:\n\nAlias\tVoice\tGender\tStyle\nellie\tEllie\tF\tYouthful, vibrant vlogger\noliver\tOliver\tM\tFriendly British\nlilith\tLilith\tF\tSoft, feminine\nsmooth\tSmooth Calm Voice\tM\tDeep, smooth narrator\ncorpse\tCorpse Husband\tM\tDeep, distinctive\nskadi\tSkadi\tF\tAnime character\nzhongli\tZhongli\tM\tDeep, authoritative\nflora\tFlora\tF\tCheerful, high pitch\nchief\tMaster Chief\tM\tHeroic, commanding\n\nThe voices command also returns any additional voices available on the API. Voice list is cached for 10 minutes.\n\nBuild outputs\n\nAfter a build, the output directory contains:\n\nout/<title-slug>/\n segments/ # Numbered WAV files (001-intro.wav, 002-section.wav, …)\n master.wav # Stitched audio (requires ffmpeg)\n master.mp3 # MP3 encode (requires ffmpeg)\n manifest.json # Build metadata: voice, template, segment list, hashes\n timeline.json # Segment durations and start times\n review.html # Interactive review page with audio players\n chapters.txt # YouTube-friendly chapter timestamps\n captions.srt # SRT captions using segment boundaries\n description.txt # YouTube description with chapters + Voice.ai credit\n\nreview.html\n\nA standalone HTML page with:\n\nMaster audio player (if stitched)\nIndividual segment players with titles and durations\nCollapsible script text for each segment\nRegeneration command hints\nTemplates\n\nTemplates auto-inject intro/outro segments around the script content:\n\nTemplate\tPrepends\tAppends\nyoutube\ttemplates/youtube_intro.txt\ttemplates/youtube_outro.txt\npodcast\ttemplates/podcast_intro.txt\t—\nshortform\ttemplates/shortform_hook.txt\t—\n\nEdit the files in templates/ to customize the intro/outro text.\n\nCaching\n\nSegments are cached by a hash of: text content + voice ID + language.\n\nUnchanged segments are skipped on rebuild — fast iteration\nModified segments are re-rendered automatically\nUse --force to re-render everything\nCache manifest is stored in segments/.cache.json\nMultilingual support\n\nVoice.ai supports 11 languages. Use --language <code> to switch:\n\nen, es, fr, de, it, pt, pl, ru, nl, sv, ca\n\nThe pipeline auto-selects the multilingual TTS model for non-English languages.\n\nTroubleshooting\nIssue\tSolution\nffmpeg missing\tPipeline still works — you get segments, review page, chapters, captions. Install ffmpeg for master stitching and video muxing.\nRate limits (429)\tSegments render sequentially, which stays under most limits. Wait and retry.\nInsufficient credits (402)\tTop up at voice.ai/dashboard. Cached segments won't re-use credits on retry.\nLong scripts\tCaching makes rebuilds fast. Text over 490 chars per segment is automatically split across API calls.\nWindows paths\tWrap paths with spaces in quotes: --input \"C:\\My Scripts\\script.md\"\n\nSee references/TROUBLESHOOTING.md for more.\n\nReferences\nAgent Skills Specification\nVoice.ai\nreferences/VOICEAI_API.md — API endpoints, audio formats, models\nreferences/TROUBLESHOOTING.md — Common issues and fixes" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/gizmoGremlin/voiceai-voiceover-creator", "publisherUrl": "https://clawhub.ai/gizmoGremlin/voiceai-voiceover-creator", "owner": "gizmoGremlin", "version": "0.1.3", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/voiceai-voiceover-creator", "downloadUrl": "https://openagent3.xyz/downloads/voiceai-voiceover-creator", "agentUrl": "https://openagent3.xyz/skills/voiceai-voiceover-creator/agent", "manifestUrl": "https://openagent3.xyz/skills/voiceai-voiceover-creator/agent.json", "briefUrl": "https://openagent3.xyz/skills/voiceai-voiceover-creator/agent.md" } }