Generate podcast episodes, explainers, narration, or images via the ListenHub API.
npx skills add https://github.com/marswaveai/skills --skill listenhub
Please help me install this Agent Skill. Skill: listenhub Source: https://github.com/marswaveai/skills/tree/main/skills/listenhub Command: npx skills add https://github.com/marswaveai/skills --skill listenhub
ListenHub addresses the complexity of turning ideas into shareable audio-visual content by orchestrating podcast episodes, explainer videos, voice narration, and AI-generated visuals through a consistent, script-driven workflow.
Describe your idea and desired mode, and ListenHub will produce podcast, explainer, TTS, or image output.
High-intent search queries and answers about installing and using this skill.
To generate a podcast episode, you provide a topic description, and ListenHub transforms it into audio using a script-driven workflow that orchestrates single- or multi-speaker formats via shell scripts.
Yes, you can create explainer videos by inputting article URLs or plain text, which the skill processes through its shell scripts to assemble narrated video outputs.
No, text-to-speech generation does not require direct API calls because the skill enforces a script-driven interface, relying entirely on provided shell scripts and tools like jq and curl to interact with the API.
AI voice narration and image generation support multiple inputs, including topic descriptions, YouTube links, article URLs, plain text, and image prompts, which are processed to produce audio or visual outputs.
Yes, you need jq and curl installed, as the skill depends on these shell tools to execute its scripts and interact with the ListenHub API for generating audio, video, and images.
Podcast mode generates audio episodes from ideas, while Explain mode produces explainer videos, with both supporting topic descriptions, URLs, and text inputs through a single script-driven entry point.
aivos-xieSearch and download GIFs from the Tenor API using curl and jq.
swyxioTranscribe long-form audio and generate publishing assets with chapter markers.
michaelboedingStitch, mix, and render audio/video outputs using FFmpeg scripts.
MuhammadUAGenerate speech, cloned voices, and sound effects via the ElevenLabs API.
