Convert topics or scripts into multi-speaker podcast MP3s with TTS voices.
npx skills add https://github.com/mofa-org/mofa-skills --skill mofa-podcast
Please help me install this Agent Skill. Skill: mofa-podcast Source: https://github.com/mofa-org/mofa-skills/tree/main/mofa-podcast Command: npx skills add https://github.com/mofa-org/mofa-skills --skill mofa-podcast
Generating professional multi-speaker podcasts from topic briefs or texts without expensive recording setups or editing.
Provide a topic or markdown script to generate a complete multi-speaker podcast using built-in or cloned voices.
High-intent search queries and answers about installing and using this skill.
You generate a multi-speaker podcast by providing a topic or an approved markdown script, which the system transforms into a scripted audio show using TTS voices, emotion cues, and music guidelines.
Yes, you can use cloned voices for podcast audio assembly. The system supports built-in voices and custom voice cloning via mofa-fm to assign distinct voices to 1-5 speakers per segment.
You do not strictly need FFmpeg to output podcast audio. The system outputs a final MP3 file when FFmpeg is available, but it defaults to generating WAV files if FFmpeg is missing from your environment.
You can include between 1 and 5 speakers in a single TTS podcast generation. The system supports multi-speaker configurations suitable for short-form podcasts, interviews, talk shows, and educational narrations.
The best way to add background music and emotion cues is by using an approved markdown script format. The system processes these script guidelines to drive per-segment timeline assembly and BGM integration during audio generation.
The audio formats outputted for post-production workflows are MP3 and WAV. The system generates ready-to-publish MP3s by default and provides individual segment audio files to allow further editing.
SheshiyerGenerate multi-speaker dialogue audio with Dia TTS speaker tags.
buda-aiGenerate VO prompts, SRT/ASS subtitles, and audio timelines from scene scripts.
cnbisonGenerate multi-speaker podcasts with cloned voices, emotion cues, and background music.
smarmen86Convert markdown blog content into audio narrations using Google Gemini TTS models.
