An AI-powered audio production skill that transforms simple keywords into fully produced, multi-character bedtime radio programs for children.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install bedtime-radio
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install bedtime-radio using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is SenseAudio Bedtime Radio?
SenseAudio Bedtime Radio is a sophisticated audio generation tool designed to go beyond simple text-to-speech. It acts as an automated radio producer, crafting structured stories with distinct intros, character-specific voices, and progressive pacing that slows down toward the end to help children drift off to sleep. By leveraging Openclaw Skills, developers and parents can create high-quality, soothing audio content tailored to specific age groups and duration preferences.
This skill automates the entire creative pipeline: from LLM-driven story drafting based on child development milestones to the technical synthesis of segmented audio files. It uses specialized voice profiles and dynamic speed adjustments to simulate a professional broadcast environment, making it a premier example of how Openclaw Skills can be used for family-centric AI applications.
SenseAudio Bedtime Radio Use Cases
- Creating personalized bedtime stories for children based on their favorite characters or themes.
- Generating educational audio content for toddlers with age-appropriate vocabulary and sentence complexity.
- Automating a 'radio-style' sleep aid for parents who need hands-free, high-quality audio narration.
- Building custom audio libraries for children's apps or smart home devices using Openclaw Skills.
How SenseAudio Bedtime Radio Works
- The system collects user inputs including story keywords, the child's age, and the desired program length.
- An LLM generates a structured story script following specific rules for vocabulary and sentence length based on the target age group.
- The skill plans the audio program, assigning different voice IDs and decreasing speech speeds for later segments to induce sleepiness.
- Each segment is synthesized individually via the SenseAudio API, incorporating natural pauses with break tags.
- The skill provides the final list of MP3 segments along with instructions for assembly into a complete radio program.
SenseAudio Bedtime Radio Setup
To use this skill, you must have a SenseAudio API key and the necessary CLI utilities installed. Ensure your environment is configured with Openclaw Skills requirements:
# Export your API key
export SENSEAUDIO_API_KEY='your_api_key_here'
# Ensure dependencies are installed
sudo apt-get install curl jq xxd ffmpeg
SenseAudio Bedtime Radio Data Schema & Taxonomy
The skill generates a series of audio files and metadata. The file structure and audio parameters are organized as follows:
| Segment Type | Default Filename | Voice ID | Pacing (Speed) |
|---|---|---|---|
| Intro | 00_intro.mp3 |
female_0006_a | 0.9 (Standard) |
| Narration | 01_narration.mp3 |
female_0006_a | 0.85 (Slow) |
| Dialogue | 03_dialogue.mp3 |
child_0001_b | 0.9 (Animated) |
| Outro | 06_outro.mp3 |
female_0006_a | 0.7 (Very Slow) |
All segments are initially saved as temporary JSON responses containing hex-encoded audio data before being converted to standard MP3 files.
SenseAudio Bedtime Radio Advanced Features
- Dynamic Pacing: Automatically reduces speech speed from 0.9x to 0.7x across segments to simulate a natural 'winding down' effect.
- Multi-Voice Casting: Automatically assigns distinct voice models to characters (e.g., elderly voices for grandparents, high-pitched voices for children).
- Custom Break Injection: Uses
<break time="2000">tags at paragraph boundaries for realistic breath and pause intervals. - Seamless Assembly: Provides ready-to-use ffmpeg commands for concatenating individual segments into a single high-fidelity broadcast file.
SKILL.md
Loading
Related Openclaw Skills
Eigenskill Builder
A meta-skill that empowers AI agents to architect, validate, and publish standardized skill modules on the ClawHub registry.
Pixwith AI Media Generation
A comprehensive AI media generation skill for Openclaw Skills that enables text-to-video, image-to-video, and multi-model image creation via the Pixwith MCP server.
Vuact
Vuact is a powerful compatibility layer that enables seamless two-way interoperability between React and Vue 3 components.
Agent Orchestration
A technical framework for coordinating multiple AI models through quality control loops, task routing, and cost-optimized fallback chains.
Xiaohongshu Publisher
A comprehensive automation skill for drafting, designing, and publishing high-engagement posts to Xiaohongshu using browser automation.
laomo-weather
A comprehensive bilingual weather skill providing real-time forecasts, air quality indices, and lifestyle advice using free global APIs.
Featured*
