ai-podcast-pipelineCreate Korean AI podcast packages from QuickView trend notes. Use for dual-host script writing (Callie × Nick), Gemini multi-speaker TTS audio generation, subtitle timing/render fixes, thumbnail+MP4 packaging, and YouTube title/description output. Supports both full (15~20 min) and compressed (5~7 min) editions.
Install via ClawdBot CLI:
clawdbot install jeong-wooseok/ai-podcast-pipelineGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://generativelanguage.googleapis.com/v1beta/models/{model}:generateContentUses known external API (expected, informational)
googleapis.comAudited Apr 17, 2026 · audit v1.0
Generated Mar 21, 2026
Agencies can use this skill to quickly produce Korean AI podcast episodes from trend reports for clients, creating engaging audio and video content for social media or websites. It automates scriptwriting, voice generation, and subtitle rendering, saving time on manual production.
Online learning platforms can leverage this skill to generate short, compressed podcast summaries of educational trends or quick tips, enhancing student engagement with multimedia content. The dual-host format makes lessons more conversational and accessible.
News organizations can automate the creation of podcast episodes from daily or weekly trend summaries, offering audio and video versions with subtitles for broader audience reach. It supports both full-length analysis and bite-sized updates.
Companies can use this skill to produce internal podcasts from business reports or trend notes, facilitating knowledge sharing among employees with engaging dual-host scripts. The compressed mode is ideal for quick updates in team meetings.
Individual creators can generate Korean AI podcast content from personal notes or online trends, building a library of episodes for YouTube or audio platforms with minimal technical expertise. The skill handles audio, subtitles, and thumbnails end-to-end.
Offer this skill as a cloud-based service where users pay a monthly fee to access the podcast pipeline, with API credits included for Gemini TTS and additional storage for generated assets. Revenue comes from tiered plans based on usage limits.
Provide a free version with basic features like script generation and limited audio output, then charge for advanced capabilities such as high-quality TTS voices, custom branding, or bulk processing. Revenue is generated through premium upgrades.
Operate a service where businesses outsource their podcast production, using this skill to efficiently create episodes for clients on a per-project or retainer basis. Revenue is earned through service fees and package deals.
💬 Integration Tip
Ensure the GEMINI_API_KEY is set as an environment variable before running scripts to avoid security risks, and test with small inputs first to adjust subtitle timing and font settings for optimal output.
Scored Apr 19, 2026
Local speech-to-text with the Whisper CLI (no API key).
ElevenLabs text-to-speech with mac-style say UX.
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
Text-to-speech conversion using node-edge-tts npm package for generating audio from text. Supports multiple voices, languages, speed adjustment, pitch control, and subtitle generation. Use when: (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, driving, cooking). (3) User wants a specific voice, speed, pitch, or format for TTS output.
Start voice calls via the OpenClaw voice-call plugin.
Local text-to-speech via sherpa-onnx (offline, no cloud)