byted-podcast-gen
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.
byted-podcast-gen converts topics, URLs, or text content into podcast audio files using Volcano Engine's synthesis.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-27
byted-podcast-gen converts topics, URLs, or text content into podcast audio files using Volcano Engine's synthesis. 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.
Use it when
- Yes.
- byted-podcast-gen synthesizes audio in multiple formats: MP3, WAV, and OGG.
Verify before relying
Read SKILL.md below before installing (7 files). Open directory: indexed for reading, not audited.
Install
bytedance/agentkit-samples/byted-podcast-gen · 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 input formats does byted-podcast-gen accept?
byted-podcast-gen accepts three input modes: a topic phrase, a web URL, or long-form text content. You can generate podcast audio from any of these sources, making it flexible for different content workflows.
Can I convert a webpage to podcast audio with byted-podcast-gen?
Yes. byted-podcast-gen can convert webpages to podcast format by accepting a URL as input. The skill processes the webpage content and synthesizes it into downloadable podcast audio files.
What audio formats does byted-podcast-gen support for output?
byted-podcast-gen synthesizes audio in multiple formats: MP3, WAV, and OGG. You can choose your preferred format when generating podcast files from your content.
Does byted-podcast-gen support multi-speaker podcasts?
Yes. byted-podcast-gen can create multi-speaker podcasts with segmented text output, allowing you to produce more dynamic and varied podcast content with different speaker voices.
How does byted-podcast-gen handle long-form content?
byted-podcast-gen processes long-form content into structured podcast episodes using Volcano Engine's PodcastTTS protocol. The skill segments text intelligently and synthesizes it into coherent audio files.
What license does byted-podcast-gen use?
byted-podcast-gen is released under the Apache-2.0 license, allowing free use and modification within the terms of that open-source license.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Podcast Skill
基于火山引擎豆包语音合成 WebSocket 协议（PodcastTTS，/api/v3/sami/podcasttts）将某个话题合成为播客音频并保存为本地文件。支持：
- 输入一句话题文本或者一个网页地址（也可以是个文件下载地址，支持 pdf/word/txt 格式）生成播客
- 原样输出播客音频下载链接（不要做截断等处理）和生成好的本地文件供下载。验证下载链接是否可下载，若可下载则返回给用户，不可下载的只是只返回本地文件。
- 输出播客分段文本（JSON）
适用场景
- 用户提到
生成播客或播客合成等相关关键词。 - 用户需要为某个话题生成播客形式的音频文件。
- 用户需要某个网页或文件内容生成播客形式的音频文件。
- 用户需要为用户上传的文件内容或者一个长上下文生成播客形式的音频文件。
强制规则（最高优先级）
当你收到用户请求生成播客时：
- 必须且只能使用 本 Skill 的脚本来生成播客
- 话题模式 用户需要为某个话题生成播客形式的音频文件， 使用参数 action=4 和 prompt_text = 话题文本。
- 网页模式 用户需要某个网页或可下载文件内容生成播客形式的音频文件， 使用参数 action=0 和 input_url = 网页地址或文件下载地址。
- 文件模式 用户需要为用户上传的文件内容或者一个长上下文生成播客形式的音频文件， 使用参数 action=0 和 text = 用户上传文件读取出来的内容或者是一段比较长的文本，一般超过 200 个字。
使用步骤
- 分析用户需要合成播客的内容，准备要合成的输入：
prompt_text（原始话题，一般不超过 20 个字）或input_url（网页地址或文件下载地址） 或者text（用户上传文件读取出来的内容或者是一个比较长的文本，一般超过 200 个字）。 - 运行脚本前先
cd到本技能目录：skills/byted-podcast-gen。 - 配置鉴权（环境变量或命令行参数）。
- 执行脚本：
python scripts/podcast.py [参数]。参考下面示例部分。 - 根据脚本输出的 JSON 里的
audio_path/texts/audio_url使用生成结果，如果有audio_url
(truncated - see the full file via the links below)
File tree — 7 files
skills/byted-podcast-gen/LICENSE
skills/byted-podcast-gen/SKILL.md
skills/byted-podcast-gen/requirements.txt
skills/byted-podcast-gen/scripts/api_key.py
skills/byted-podcast-gen/scripts/podcast.py
skills/byted-podcast-gen/scripts/protocols/__init__.py
skills/byted-podcast-gen/scripts/protocols/protocols.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 › “Generate podcast audio from a topic, URL, or text content”
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.
Byted Voice to Text transcribes audio using Volcano Engine's BigModel ASR, offering fast synchronous processing for files under 2 hours and 100MB, or asynchronous recognition for longer content up to 5 hours. It handles Feishu voice messages, local audio files, and direct URLs with automatic format detection.
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.
This skill transcodes audio files across multiple formats and adjusts encoding parameters like sample rate, bitrate, and channels through Volcengine's LAS service. It accepts files from TOS cloud storage or local uploads, processes them via ffmpeg-backed parameters, and returns converted audio ready for downstream use.
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.
Byted Web Search connects your agent to live internet data via Volcengine's official API, delivering web and image results for fact-checking, current events, and time-sensitive queries. Designed for scenarios where knowledge cutoff limits accuracy, it triggers automatically on temporal keywords and verification requests, with 500 free monthly searches included.
More skills podcast-generator (MIT) · byted-seedance-video-generate (Apache-2.0)