podcast-generator
Transform Chinese articles and reports into conversational podcast audio featuring two speakers. The skill handles format selection (MP3, OGG Opus, PCM, AAC), speech rate adjustment, voice customization, and resume-on-failure for interrupted generations. Requires Volcano Engine credentials and works best with structured text between 500–3000 characters.
Podcast Generator converts Chinese text into dual-speaker podcast audio using Volcano Engine's AI model.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-21
Podcast Generator converts Chinese text into dual-speaker podcast audio using Volcano Engine's AI model. Transform Chinese articles and reports into conversational podcast audio featuring two speakers. The skill handles format selection (MP3, OGG Opus, PCM, AAC), speech rate adjustment, voice customization, and resume-on-failure for interrupted generations. Requires Volcano Engine credentials and works best with structured text between 500–3000 characters.
Use it when
- Yes.
- podcast-generator supports four audio formats: MP3, OGG Opus, PCM, and AAC.
Verify before relying
Read SKILL.md below before installing (3 files). Open directory: indexed for reading, not audited.
Install
staruhub/ClaudeSkills/Geek-skills-podcast-generator · repository language: Python
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What can podcast-generator do with my written content?
podcast-generator transforms Chinese articles and reports into conversational podcast audio featuring two speakers. It converts your written content into engaging dual-speaker dialogue, handles multiple audio formats (MP3, OGG Opus, PCM, AAC), lets you customize voice selection and speech rate, and can resume interrupted generations without restarting from scratch.
Can I turn text into spoken podcast with podcast-generator?
Yes. podcast-generator specializes in turning text into spoken podcast format. It works best with structured text between 500–3000 characters and generates conversational audio with two speakers. You can customize the voices, adjust speech rate, and choose your preferred audio format before generation begins.
What audio formats does podcast-generator support?
podcast-generator supports four audio formats: MP3, OGG Opus, PCM, and AAC. You can select your preferred format when creating the podcast, allowing flexibility depending on your distribution platform or playback device requirements.
Does podcast-generator work with Chinese content?
podcast-generator is optimized for Chinese content. It generates Chinese dialogue-based podcasts from articles and reports, supporting both simplified and traditional workflows. The skill requires Volcano Engine credentials to function and delivers natural-sounding dual-speaker conversations in Chinese.
What happens if podcast-generator generation gets interrupted?
podcast-generator includes resume-on-failure capability, allowing you to continue interrupted podcast generation without restarting the entire process. This saves time and resources when dealing with longer content or unstable connections.
What are the content requirements for using podcast-generator?
podcast-generator works best with structured text between 500–3000 characters. You'll need valid Volcano Engine credentials to authenticate the service. The skill handles format selection, voice customization, and speech rate adjustment to create your ideal podcast output.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
播客生成器（火山引擎双人对话）
把中文文本变成双人对话播客音频，接口封装在 scripts/generate_podcast.py。
验收标准（每次生成完成前自查）
- [ ] 音频文件已落盘，把实际路径与文件大小回报用户
- [ ] 输入文本 ≤25,000 字符（超长必须先与用户确认拆分方案，不能让模型静默截断）
- [ ] 生成中断时使用了 retry_info 续传而不是从头重来
- [ ] 参数选择有依据：分发用 mp3，后期加工用 pcm；教学内容语速 -20 左右
- [ ] 凭证缺失时未硬试：告知用户去火山引擎控制台（speech/service/10028）获取
不做什么
- 不写播客文稿——输入文本的质量是上游任务（文稿创作找写作类 skill）
- 不做单人朗读、配音、音效制作
- 不在输出里回显用户的 ACCESS_KEY
工作流程
1. 准备输入
必需：中文文本（≤25k 字符）+ APP_ID + ACCESS_KEY（无则告知获取方式后停止）。 可选：格式（默认 mp3）/ 采样率（默认 24000）/ 语速（-50~100，0=正常，100=2 倍速）/ 音色 / 开场音乐（默认关）。
最佳文本长度 500-3000 字——播客时长与听感的最优区间；一篇长文建议先摘要再生成。
2. 生成
python scripts/generate_podcast.py \
--text "播客话题或内容文本" \
--output "/path/to/output.mp3" \
--app-id "$VOLC_APP_ID" --access-key "$VOLC_ACCESS_KEY" \
--format mp3 --sample-rate 24000 --speech-rate 0
脚本会流式接收音频、按轮次显示进度、落盘后返回统计（大小/轮次数）。 Python 模块调用、自定义音色 ID、断点续传 retry_info 的写法见脚本内 docstring 与
(truncated - see the full file via the links below)
File tree — 3 files
lab/Geek-skills-podcast-generator/SKILL.md
lab/Geek-skills-podcast-generator/references/api_reference.md
lab/Geek-skills-podcast-generator/scripts/generate_podcast.py
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Convert written content into dual-speaker podcast audio”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Byted-Text-to-Speech transforms written content into audio using Volcano Engine's speech synthesis service. Configure speaker voice, speech rate, pitch, volume, and output format—with optional Markdown filtering and LaTeX formula support for technical content.
ListenHub TTS transforms written content into spoken audio through three synthesis modes: rapid processing for short text, multi-speaker dialogue for scripts, and streaming synthesis for lengthy documents. Select from available voices or use the default voice, with options to adjust playback speed and output format.
Doubao TTS converts text to natural-sounding speech via Volcengine's API, handling both quick responses under 300 characters and longer content up to 100K characters asynchronously. Choose from multiple Chinese male and female voices, adjust speed and pitch, and build podcasts with multi-voice support.
Byted-vms-voice-notify wraps Volcano Engine's voice notification API to deliver single or batch voice calls to phone numbers. It handles TTS template lifecycle (create, update, delete, query), recording file uploads and management, and resource operations—serving as the unified gateway for all voice notification and template operations.
byted-podcast-gen synthesizes podcast audio from a topic phrase, web URL, or long-form text using Volcano Engine's PodcastTTS protocol. The skill handles three input modes—topic-based, URL-based, and file-based—and outputs audio files in MP3, WAV, or OGG format along with segmented speaker text.
Podcast Workflow streamlines the entire podcast handling pipeline, from YouTube video discovery to Feishu knowledge base publication. It offers two entry points: fetch recent updates from followed channels for manual selection, or process a YouTube link directly. The skill extracts transcripts, generates core insights and highlights, saves locally, and publishes to Feishu—with optional image poster generation for social sharing.
More skills byted-voice-to-text (Apache-2.0)