{
  "markdown": "# VoxFlow Skills\n\n> Skill files in this repo are auto-overwritten on each release. For feedback or fixes, please [open an issue](https://github.com/VoxFlowStudio/skills/issues) instead of submitting a PR.\n\n[![License](https://img.shields.io/badge/license-Apache%202.0-blue.svg)](LICENSE)\n[![npm version](https://img.shields.io/npm/v/voxflow.svg)](https://www.npmjs.com/package/voxflow)\n[![6 skills](https://img.shields.io/badge/skills-6-purple.svg)](#what-you-get)\n[![Works with](https://img.shields.io/badge/works%20with-Claude%20Code%20%C2%B7%20Cursor%20%C2%B7%20Codex%20%C2%B7%20Gemini-orange.svg)](#install)\n\n![VoxFlow CLI demo](https://github.com/VoxFlowStudio/skills/raw/main/demo.gif)\n\nVoice in your AI workflow. Six skills that let any AI coding agent (Claude Code · Cursor · Codex · Gemini CLI · Cline) speak in 200+ voices, generate podcasts, dub videos, transcribe audio, and turn text into card images or narrated card videos — through one CLI.\n\n**Why VoxFlow over a raw TTS API?** One CLI handles auth, voice search, multi-speaker dialogue, video pipelines, and quota. The skills layer makes it native to whichever agent you're already using — no new context-switch.\n\n## Install\n\nThe simplest path — let the VoxFlow CLI auto-detect your agent and run the right command:\n\n```bash\nnpm install -g voxflow\nvoxflow skills install\n```\n\nIt detects Claude Code / Cursor / Codex / Gemini / WorkBuddy / OpenClaw on your `$PATH`, picks the right install command, asks for confirmation, runs it, and prints next steps. Use `--all` to install for every detected agent, or `--for <agent>` to force one.\n\nIf you'd rather run the install command directly — **one command for every agent**:\n\n```bash\nnpx -y skills add VoxFlowStudio/skills --all --yes --global\n```\n\nThe `skills` npm package detects every AI agent on your machine (Claude Code,\nCursor, Codex CLI, Gemini CLI, Cline, Amp, Antigravity, CodeBuddy, OpenClaw…)\nand writes the 6 VoxFlow skills (`hub`, `podcast`, `transcribe`, `video`,\n`slice`, `card`) to each agent's standard skill location in a single shot.\n\n## Prerequisites\n\n```bash\nnpm install -g voxflow\nvoxflow login          # one-time browser auth\n```\n\n## What You Get\n\nSix focused skills, each loaded on demand:\n\n| Skill | Invoked as | What it covers |\n|-------|-----------|----------------|\n| **hub** | `voxflow:hub` | `say` · `narrate` · `story` · `voices` · auth · quota · feedback |\n| **podcast** | `voxflow:podcast` | Multi-speaker AI podcast from topic / URL / script |\n| **transcribe** | `voxflow:transcribe` | `asr` · `asr-jobs` · `translate` · `dub` · `video-translate` · `summarize` · `publish` |\n| **video** | `voxflow:video` | `picstory` · `present` · `slides` · `explain` · `image` |\n| **slice** | `voxflow:slice` | Article → vertical card video (1080×1920); 13 editorial / poster / magazine themes |\n| **card** | `voxflow:card` | Text → shareable card images (HTML/CSS + Playwright); 1:1 / 3:4 / 9:16, editorial design system. Optional narrated MP4 video via `voxflow card render` (TTS + FFmpeg, in-project output) |\n\nUse the hub skill as the starting point — it routes to the others automatically.\n\n## Example Interactions\n\n| You say | Agent runs |\n|---------|-----------|\n| \"Read this README out loud\" | `voxflow narrate README.md -o readme.mp3` |\n| \"Make a 5-min podcast on AI agents\" | `voxflow podcast \"AI agents\" --length short` |\n| \"Dub this tutorial into Japanese\" | `voxflow video-translate tutorial.mp4 --to ja` |\n| \"把这段话合成语音\" | `voxflow say \"...\" -o output.mp3` |\n| \"生成一个 AI 播客\" | `voxflow podcast \"topic\" --length medium` |\n| \"把这个视频翻译成日语\" | `voxflow video-translate video.mp4 --to ja` |\n| \"转录这段录音\" | `voxflow asr recording.mp3` |\n| \"做一个 AI 知识短视频\" | `voxflow picstory \"topic\" --style sketchnote` |\n| \"生成一套演示幻灯片\" | `voxflow slides \"topic\" --slides 8` |\n\n## Skills Layout\n\n```text\nvoxflow/\n  hub/SKILL.md          # TTS, voice search, auth, quota, feedback\n  podcast/SKILL.md      # AI dialogue podcast\n  transcribe/SKILL.md   # ASR, translation, dubbing\n  video/SKILL.md        # AI short video, slides, images\n  slice/SKILL.md        # Article → vertical card video (13 themes)\n  card/SKILL.md         # Text → shareable card images (1:1 / 3:4 / 9:16)\n```\n\n## Registry\n\n```text\nregistry.json           # VoxFlow CLI add-on recipes index\nvoxflow/\n  dub-anime-jp-zh/      # Anime fan-dub voice preset (JP→ZH)\n```\n\nInstall a recipe:\n```bash\nvoxflow add dub-anime-jp-zh\n```\n\n## Quota\n\nFree tier: 10,000 / month. Check before large jobs:\n\n```bash\nvoxflow status\n```\n\n| Operation | Cost |\n|-----------|------|\n| `say` (1 call) | ~100 |\n| `narrate` (per segment) | ~100 |\n| `podcast` (medium) | ~5,000 |\n| `picstory` (5 scenes) | ~3,100 |\n\n## Security\n\n- No API keys or tokens in this repository.\n- Use `voxflow login` for interactive auth or `VOXFLOW_TOKEN` env var for CI.\n- See [SECURITY.md](SECURITY.md) for vulnerability disclosure.\n\n## Links\n\n- [VoxFlow Studio](https://voxflow.studio) — Web app\n- [CLI on npm](https://www.npmjs.com/package/voxflow) — `npm install -g voxflow`\n- [CLI docs](https://voxflow.studio/docs/cli) — Full command reference\n",
  "bytes": 5088,
  "sha": "5538752b711454175af260d9dd738b04d581eecc721163d47c40b526ffc6f80d",
  "repo_slug": "voxflowstudio/skills",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_voxflowstudio_skills_voxflow_d172e4d8/readme"
}