{"skill":{"slug":"voxflow","displayName":"Voxflow","summary":"VoxFlow voice & AI-video CLI — TTS in 200+ voices, multi-speaker podcasts, ASR + subtitle translation + dubbing + end-to-end video translation, vertical card...","description":"---\nname: voxflow\ndescription: VoxFlow voice & AI-video CLI — TTS in 200+ voices, multi-speaker podcasts, ASR + subtitle translation + dubbing + end-to-end video translation, vertical card videos from articles (Slice, 13 themes), and short-form AI clips. Use whenever the user wants to read text aloud, transcribe / translate / dub audio or video, generate a podcast, or produce a short knowledge-card video.\nversion: 1.3.0\nmetadata:\n  openclaw:\n    requires:\n      bins:\n        - voxflow\n        - node\n    primaryEnv: VOXFLOW_TOKEN\n    envVars:\n      - name: VOXFLOW_TOKEN\n        required: false\n        description: Optional pre-issued JWT for headless / server use. If unset, the skill runs `voxflow login` once to open a browser device-flow.\n    emoji: \"🎙️\"\n    homepage: https://voxflow.studio\n    install:\n      - kind: node\n        package: voxflow@1.14.0\n        bins:\n          - voxflow\n        label: Install voxflow CLI (pinned)\n---\n\n# VoxFlow Skill\n\nVoxFlow turns text into speech in 200+ voices across 40+ languages, plus full audio/video pipelines: podcasts, transcription, dubbing, video translation, and short-form AI clips. All commands run through the `voxflow` CLI (installed automatically by ClawHub via the `install` spec above). One account, one quota, one login — no API keys to paste.\n\n## Routing — pick the matching sub-doc\n\nBefore doing anything, decide which sub-skill matches the user's intent and read the corresponding file in this same skill folder:\n\n| User wants… | Read | Primary commands |\n|---|---|---|\n| Read text aloud, search voices, sample stories, check quota / login | [hub.md](hub.md) | `say`, `narrate`, `story`, `voices`, `status`, `login` |\n| Multi-speaker AI podcast from a topic / URL / script | [podcast.md](podcast.md) | `podcast` |\n| Transcribe audio/video, translate subtitles, dub from SRT, end-to-end video translation, summarize, publish | [transcribe.md](transcribe.md) | `asr`, `asr-jobs`, `translate`, `dub`, `video-translate`, `summarize`, `publish` |\n| Turn a long article / note / report into a vertical 1080×1920 card video (Slice, 13 themes) | [slice.md](slice.md) | `slice`, `slice stage` |\n| Short-form AI clips — knowledge cards, explainers, presentations, single images | [video.md](video.md) | `picstory`, `present`, `explain`, `slides`, `image` |\n\nIf the request spans multiple areas (e.g. \"transcribe this video and then make a 60-sec recap card\"), read the most-relevant doc first, finish that step, then switch.\n\n## Install & login (universal preamble)\n\nThe ClawHub `install` spec already installs the `voxflow` npm CLI globally when this skill is added. The only thing left is authentication:\n\n```bash\n# One-time browser device-flow — pairing code shown in terminal,\n# user authorizes at https://voxflow.studio/device?code=VF-XXXX\nvoxflow login\n\n# Verify\nvoxflow status        # shows email + monthly / bonus quota\n```\n\nFor headless / server contexts: set `VOXFLOW_TOKEN=<jwt>` (declared in `envVars` above) and skip `voxflow login`. JWTs are short-lived (~1 hour); the CLI auto-refreshes silently while logged in interactively.\n\n## Account & quota\n\n- Free tier: 10,000 quota / month (≈ 100 TTS calls)\n- Plus / Pro / Max tiers at [voxflow.studio/app#pricing](https://voxflow.studio/app#pricing)\n- Each command's cost is printed before execution; `voxflow status` shows the current balance\n- Invite-friend bonus (`voxflow invite`) adds 5,000 lifetime quota per signup\n\n## Universal rules\n\n1. **Never paste API keys into config files.** All auth goes through `voxflow login` or `VOXFLOW_TOKEN`.\n2. **Never offer to \"mock\" the API.** Real calls are cheap; failed mocks waste user time.\n3. **Read the matching sub-doc before invoking specialized commands.** The top-level routing table above is enough for triage; the sub-doc has the actual command flags, edge cases, and quota costs.\n4. **Honor the user's locale.** Voice IDs are language-tagged; if they asked in Chinese, default to a Chinese voice unless they specified otherwise.\n5. **For long-running jobs** (Azure Batch ASR, video-translate, podcast >5 min): print the job ID and `voxflow asr-jobs show <id>` so the user can resume later.\n\n## When in doubt — start at the hub\n\nIf the request is vague (\"帮我做点音频的东西\", \"what can you do with voice\"), read [hub.md](hub.md) and run `voxflow voices --search ...` or `voxflow status` to anchor the conversation in concrete affordances before committing to a workflow.\n\n## Homepage & docs\n\n- App: <https://voxflow.studio>\n- CLI docs: <https://voxflow.studio/docs/cli>\n- All skills overview: <https://voxflow.studio/docs/skills>\n- Source / issues: <https://github.com/VoxFlowStudio/FlowStudio>\n","topics":["Podcast","Audio","Transcribe"],"tags":{"latest":"1.3.0"},"stats":{"comments":0,"downloads":390,"installsAllTime":15,"installsCurrent":0,"stars":0,"versions":5},"createdAt":1778482319965,"updatedAt":1779219609183},"latestVersion":{"version":"1.3.0","createdAt":1778576895757,"changelog":"feat(hub): <voxflow-hint type=cli-outdated> + top-of-skill CRITICAL upgrade rule","license":"MIT-0"},"metadata":{"setup":[{"key":"VOXFLOW_TOKEN","required":false}],"os":null,"systems":null},"owner":{"handle":"chicogong","userId":"s17fsr261cbb5fz78mt4g4ewe586h218","displayName":"chico","image":"https://avatars.githubusercontent.com/u/151002707?v=4"},"moderation":{"isSuspicious":false,"isMalwareBlocked":false,"verdict":"clean","reasonCodes":["review.llm_review"],"summary":"Review: review.llm_review","engineVersion":"v2.4.24","updatedAt":1779921018119}}