podcast

To turn text into a two-host podcast, this Skill generates a conversational JSON script between two roles and converts it into a stitched MP3 using Fish Audio TTS. You simply provide pasted text, a local file, or a URL as input.

Yes, you can generate an audio podcast from a URL or local file by passing the link or file path to the pipeline. The system reads the content, creates a dialogue script, and synthesizes the audio locally.

Yes, you need ffmpeg and Fish Audio to generate text-to-speech podcast episodes. Fish Audio handles the voice synthesis for each script segment, while ffmpeg and pydub assemble the audio segments into a single MP3 file.

RSS feed publishing works by creating or updating a GitHub Pages-backed RSS feed with your generated MP3 episodes. This allows standard podcast apps to automatically discover and subscribe to your new audio content.

The best way to convert long articles into listenable audio is using a local pipeline that transforms dense text into a two-host dialogue. This approach avoids manual reading by automating script generation and MP3 audio stitching.

Limitations of local Python pipelines for audio generation include requiring specific environment dependencies like httpx, pydub, audioop-lts, and ffmpeg. You must also configure a YAML entry point and a valid Fish Audio TTS connection before processing.