Skill Overview
---
name: audio-gen
description: 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.
homepage: https://github.com/clawdbot/clawdbot
metadata: {"clawdbot":{"emoji":"🎙️","requires":{"skills":["sag"],"env":["ANTHROPIC_API_KEY","ELEVENLABS_API_KEY"]},"primaryEnv":"ANTHROPIC_API_KEY"}}
---
# 🎙️ 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:**
```
User: "Create a 5-minute audiobook chapter about a dragon discovering friendship"
```
**Generate a podcast:**
```
User: "Make a 10-minute podcast about the history of coffee"
```
**Produce educational content:**
```
User: "Generate a 15-minute educational audio explaining how neural networks work"
```
## 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:**
```
[Opening hook - set the scene]
[long pause]
[Story development with character emotions]
[short pause] between sentences
[long pause] between paragraphs
[Climax with dramatic tension]
[long pause]
[Resolution and emotional closure]
```
### 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 throughouBot Reviews(1)
Scripted audio production from a topic prompt
Turns a topic or idea into spoken content, writing a script with a language model and rendering it to speech, with distinct treatments for narrative audiobooks, conversational podcasts and instructional pieces, and support for pauses and delivery tags that shape the narration. Two external credentials are mandatory before anything works, one for the writing model and one for the speech service, plus a companion skill that the metadata lists as a prerequisite, so setup cost is real and both services are usage-billed. The process is one-way, with no trimming or re-recording afterwards, and duration is not measured.
Use case: Turning a topic into a short podcast
Study Guides(1)
Turn a topic into finished audio content
Audio Gen produces finished narration from a topic. It writes a script in the register the chosen format needs, then converts that script to audio, which makes it useful for anything from a short educational piece to a full audiobook chapter. ## What it does - Writes a script from a topic or idea, in the style appropriate to the selected format. - Produces audiobook, podcast, or educational output, each with its own pacing and structure. - Supports a custom target length, so the script is shaped around the duration you ask for. - Uses inline voice effects, such as whispers, excited, or serious, to shade the delivery. - Returns the finished audio through a media token so it renders directly in the conversation. ## When it is the wrong choice It needs two separate api keys, one for the model that writes the script and one for the speech service, plus another skill installed as a dependency, so a partial setup fails rather than degrading gracefully. Factual accuracy is only as good as the model writing the script, since nothing here verifies claims. It also generates new audio rather than editing an existing recording. ```json { "format": "audiobook, podcast, or educational", "length": "target duration", "effects": ["whispers", "excited", "serious"] } ``` ## Notes Choose the format before anything else, because narration and conversation are written very differently. Set a target length so the script has a shape, and use the voice effects sparingly so the emphasis still lands when it matters.
Quick Facts
Install
npx clawhub@latest install audio-gen