voice-podcast-kit_skill

Overview

This skill produces complete multi-host podcast episodes with distinct cloned voices, intro/outro music, and clean transitions. It handles voice cloning or preset voice selection, segment scripting, TTS generation, and outputs all files ready for assembly. The workflow focuses on voice consistency so recurring hosts keep the same voice IDs across episodes.

How this skill works

You provide episode title, topic, speaker list (and optional audio samples) plus target length and segment count. I confirm the lineup, call voice_clone for provided samples or voice_list to choose presets, draft a timed segment outline, generate intro/outro music via generate_music, write segment scripts, and synthesize each line with tts into mp3 files. The result is a clear mapping of speaker -> voice_id, separate audio files per segment, the full episode script, and suggested assembly steps.

When to use it

• Launching a multi-host podcast episode with lifelike, distinct voices
• Producing guest interviews when you need consistent host voices across episodes
• Creating sample previews before committing to full episode production
• Repackaging written content into an audio episode with multiple characters
• Rapid prototyping of episode structure and timing for planning

Best practices

• Provide short, clean voice samples (10–30 seconds) per speaker for best cloning results
• Save returned voice_ids for recurring hosts to maintain consistency across episodes
• Specify clear segment timing and speaker turns to simplify scripting and TTS calls
• Request an intro + first 2 minutes preview if you want to verify voice clones before full production
• Use music preferences (genre, mood, tempo) to guide generate_music for coherent intro/outro

Example use cases

• Weekly news roundtable with three hosts and one guest, 30-minute target with intro, main, Q&A, outro
• Fictional audio drama episode with distinct character voices and transition soundscapes
• Interview series pilot where guest voice is cloned from a provided sample
• Preview build: generate intro + first 2 minutes to approve voices and style before full episode