菜单
Multi-speaker podcast and dialogue generation with TTS voice cloning. Triggers: podcast, 播客, multi-speaker audio, 多人对话, 多人语音, radio show, talk show, 对话生成, 锵锵三人行, 两人对话, 三人对话, voice dialogue, 用XX的声音, 用XX和XX的风格, 声音模仿, 角色对话, 配音.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/mofa-org/mofa-skills --skill mofa-podcast命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
AI-generated greeting cards as PNG images. Triggers: greeting card, 贺卡, mofa card, mofa 贺卡, make a card, CNY card, New Year card, 新年贺卡, ink-wash card. Generates full-bleed AI artwork via Gemini in various Chinese art styles.
AI-generated comic strips and illustrations. Triggers: comic, manga, xkcd, 漫画, comic strip, 四格漫画, panel comic, illustration strip, snoopy. Generates multi-panel comics via Gemini with optional Qwen-Edit refinement, stitched into a single image.
Extract a video frame at a specific timestamp. Triggers: extract frame, 提取画面, screenshot video, capture frame, 截图, grab frame, video frame at, 视频截图.
基于 SOC 职业分类
正在显示 SKILL.md
| name | mofa-podcast |
| description | Multi-speaker podcast and dialogue generation with TTS voice cloning. Triggers: podcast, 播客, multi-speaker audio, 多人对话, 多人语音, radio show, talk show, 对话生成, 锵锵三人行, 两人对话, 三人对话, voice dialogue, 用XX的声音, 用XX和XX的风格, 声音模仿, 角色对话, 配音. |
Generate professional multi-speaker podcasts from a topic or text. The pipeline collects speaker preferences, expands content into a scripted dialogue with emotion and music cues, lets you review before generation, then produces a final MP3.
[Speaker - voice, emotion] format.Do NOT call fm_voice_list from mofa-fm as a precheck before generating a
podcast. If the user names speaker voices, use those names directly in the
script and let podcast_generate / TTS return a recoverable unknown-voice
error if a voice is unavailable. Use voice-listing tools (podcast_voices,
fm_voice_list) only when the user explicitly asks to browse or choose voices.
The reference material lives next to this file. Load only what the current turn needs:
docs/script-format.md.docs/emotion-tags.md.[PAUSE] cues → docs/cues.md.docs/voices.md.podcast_generate actually does + output paths →
docs/generation-engine.md.Final artifacts land under skill-output/mofa-podcast/:
script.md.segments/*.wav.podcast_<timestamp>.mp3 (or .wav fallback when MP3
conversion is unavailable).