Convert Markdown documents into MP3 podcasts using the gencast CLI.
npx skills add https://github.com/cadrianmae/claude-marketplace --skill gencast
Please help me install this Agent Skill. Skill: gencast Source: https://github.com/cadrianmae/claude-marketplace/tree/main/plugins/gencast/skills/gencast Command: npx skills add https://github.com/cadrianmae/claude-marketplace --skill gencast
This Skill automates podcast generation from documents, reducing manual recording and editing time by leveraging the gencast CLI with the --minimal flag to minimize context usage.
Run: gencast document.md --minimal -o podcast.mp3
High-intent search queries and answers about installing and using this skill.
Gencast converts markdown into MP3 podcasts by invoking the gencast CLI with the --minimal flag, which reduces context usage while generating audio from your document content with optional style and audience customization.
Yes, gencast supports batch processing and multi-file concatenation, allowing you to combine multiple markdown inputs into a single podcast output with unified styling and voice settings.
Gencast lets you customize host voices, apply different styles, target specific audiences, and optionally generate planning and dialogue artifacts alongside your MP3 output to tailor content to your needs.
Gencast processes standard markdown documents without requiring special markup; it handles educational, technical, and general-audience content directly, converting articles, lectures, or reports into spoken form with minimal configuration.
Beyond the MP3 podcast, gencast can generate optional planning artifacts and dialogue transcripts while reporting progress, giving you intermediate outputs for review and refinement before finalizing audio.
refly-aiGenerate MP3 or WAV audio from text using Fal.ai models.
hmzainjamilAutomate podcast production and distribution from recording assets to published episodes.
mindmorassAutomate podcast production from recording to RSS distribution with FFmpeg and Whisper.
fishyerConvert written text into spoken audio using the z-ai-web-dev-sdk.
