Agent skill · creative production · sundial-org
audio-gen
Generate audiobooks, podcasts, or educational audio content on demand. User provides an idea or topic, Claude AI writes a script, and ElevenLabs converts it to high-quality audio. Supports multiple formats (audiobook, podcast, educational), custom lengths, and voice effects. Use when asked to create audio content, make a podcast, generate an audiobook, or produce educational audio. Returns MP3 audio file via MEDIA token.
Why this skill is useful
Adds specific workflows and content generation guidelines for creating audiobooks, podcasts, and educational audio that the AI wouldn't reliably generate on its own.
What it needs
Requires anthropic, elevenlabs account access. About 9k tokens when loaded. Last updated 2026-03-07. 639 stars on the source repository.
What this skill does
🎙️ Audio Content Generator Generate high-quality audiobooks, podcasts, or educational audio content on demand using AI-written scripts and ElevenLabs text-to-speech. Quick Start Create an audiobook chapter: Generate a podcast: Produce educational content: Content Formats Audiobook Style: Narrative storytelling with emotional depth Clear beginning, middle, and end Descriptive language and vivid imagery Dramatic pacing with thoughtful pauses Emotional tone that matches the story Use voice effects like [whispers], [excited], [serious] for impact Example Structure: Podcast Style: Conversational and engaging Warm, welcoming intro (15-30 seconds) Main content with natural flow Transitions between topics Memorable outro with key takeaways Conversational tone throughout Example Structure: Educational Content Style: Clear explanations for learning Simple introductions to complex topics Step-by-step breakdowns Real-world examples and analogies Recap of key concepts at the end Enthusiastic delivery with [excited] for important points Example Structure: Length Guidelines Word Count to Duration Conversion: 5 minutes = ~375 words 10 minutes = ~750 words 15 minutes = ~1,125 words 20 minutes = ~1,500 words 30 minutes = ~2,250 words Pacing: Average conversational speed is ~75 words per minute Practical Limits: Minimum: 2 minutes (~150 words) Maximum: 30 minutes (~2,250 words) Sweet spot: 5-15 minutes for best engagement Workflow Instructions Step 1: Understand the Request Parse the user's request for: 1. Content type (audiobook, podcast, educational, or inferred from topic) 2. Topic/theme (what should the content be about) 3. Target length (how many minutes) 4. Tone/style (dramatic, casual, educational, etc.) 5. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills sundial-org/audio-gen