senseaudio-bedtime-radio

Generate a complete bedtime story audio program from a keyword — with intro, narration, character voices, and a sleepy outro. Use when parents or caregivers want a bedtime story, or when users ask for "睡前故事", "哄睡音频", "儿童故事音频", "给孩子讲故事", or any request to create a soothing story audio for children.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "senseaudio-bedtime-radio" with this command: npx skills add scikkk/bedtime-radio

SenseAudio Bedtime Radio

Generate a complete bedtime story audio program — not just a TTS read-aloud, but a structured radio-style show with intro, paced narration, character voices, and a sleepy outro.

Step 1: Collect Inputs

Ask the user for:

  • 故事关键词 — e.g., "月亮上的小兔子", "会飞的小猪", "森林里的魔法书"
  • 孩子年龄 — affects vocabulary and story complexity (default: 4–6岁)
  • 时长偏好 — 短版 (~2分钟) / 标准版 (~4分钟) / 长版 (~6分钟)

Step 2: Write the Story (LLM task)

Generate the story yourself — no API call needed for this step. Follow these rules based on age:

AgeVocabularySentence lengthStory complexity
2–3岁极简,常用词≤10字/句单线情节,重复句式
4–6岁简单,生动10–18字/句简单起承转合
7–10岁丰富,有细节15–25字/句有悬念和转折

Story structure:

  • 开头:交代主角和场景(1段)
  • 发展:遇到问题或冒险(2–3段)
  • 高潮:解决问题的关键时刻(1段)
  • 结尾:温馨收尾,引导入睡(1段,语气渐缓)

Length guide:

  • 短版:约300字
  • 标准版:约600字
  • 长版:约1000字

Mark dialogue lines with the character name: [小兔子]: "..." [老爷爷]: "..."

Step 3: Plan the Audio Program

Structure the full program before making any API calls:

[片头]  "晚安,小朋友。今天的故事叫做《<标题>》。"
        voice: female_0006_a, speed: 0.9

[正文段落1]  旁白第一段
        voice: female_0006_a, speed: 0.85
        + <break time="2000"> after paragraph

[对话]  角色台词(如有)
        小动物/儿童角色 → child_0001_b, speed: 0.9
        老人/长辈角色   → male_0004_a, speed: 0.85
        旁白继续        → female_0006_a

[正文后半段]  speed 逐段降低:0.85 → 0.80 → 0.75
        模拟催眠节奏

[片尾]  "故事讲完啦,闭上眼睛,晚安……"
        voice: female_0006_a, speed: 0.7

Step 4: Synthesize Each Segment

Generate each segment as a separate mp3 file, then list them for the user to assemble.

Segment synthesis pattern:

synthesize() {
  local TEXT="$1"
  local VOICE="$2"
  local SPEED="$3"
  local OUTFILE="$4"

  curl -s -X POST https://api.senseaudio.cn/v1/t2a_v2 \
    -H "Authorization: Bearer $SENSEAUDIO_API_KEY" \
    -H "Content-Type: application/json" \
    -d "{
      \"model\": \"SenseAudio-TTS-1.0\",
      \"text\": \"$TEXT\",
      \"stream\": false,
      \"voice_setting\": { \"voice_id\": \"$VOICE\", \"speed\": $SPEED },
      \"audio_setting\": { \"format\": \"mp3\" }
    }" -o "${OUTFILE}.json"

  jq -r '.data.audio' "${OUTFILE}.json" | xxd -r -p > "$OUTFILE"
  echo "$(jq '.extra_info.audio_length' "${OUTFILE}.json")ms — $OUTFILE"
}

Segment breakdown:

SegmentTextVoiceSpeedFile
片头"晚安,小朋友。今天的故事叫做《<标题>》。"female_0006_a0.900_intro.mp3
正文段1第一段旁白female_0006_a0.8501_narration.mp3
正文段2第二段旁白female_0006_a0.8502_narration.mp3
对话(如有)角色台词child_0001_b / male_0004_a0.903_dialogue.mp3
正文段3后半段旁白female_0006_a0.8004_narration.mp3
正文段4结尾段旁白female_0006_a0.7505_narration.mp3
片尾"故事讲完啦,闭上眼睛,晚安……"female_0006_a0.706_outro.mp3

Insert <break time=2000> at paragraph boundaries within a segment's text to create natural pauses between paragraphs.

Step 5: Output

List all generated files with durations and assembly instructions:

睡前故事电台生成完成:《<标题>》

文件列表(按顺序播放):
  00_intro.mp3        — 片头 (8秒)
  01_narration.mp3    — 第一段 (42秒)
  02_narration.mp3    — 第二段 (38秒)
  03_dialogue.mp3     — 对话 (25秒)
  04_narration.mp3    — 第三段,渐慢 (45秒)
  05_narration.mp3    — 结尾段,更慢 (40秒)
  06_outro.mp3        — 片尾 (12秒)

总时长:约 3分50秒

合并命令(需要 ffmpeg):
  ffmpeg -i "concat:00_intro.mp3|01_narration.mp3|..." -acodec copy story.mp3

If the user wants a different story or age group, regenerate only the story text and re-synthesize — the program structure stays the same.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Coding

Integrated Manufacturing Consulting

制造咨询全栈技能——以附件为素材,按5Part标准结构生成面向客户企业高层汇报的 正式咨询项目总结报告(非简单摘要)。整合四大模块:(1)7大部门调研方法论+ODP-I²诊断框架+改善项目定义(原manufacturing-consulting-toolkit); (2)原PPT图片提取复用+python-ppt...

Registry SourceRecently Updated
Coding

database_skill

Python-based database connectivity skill supporting MySQL, PostgreSQL, Oracle, SQL Server, and SQLite. Provides connection management, parameterized query ex...

Registry SourceRecently Updated
Coding

Miaoji Asin Clinic

基于ASIN和品类,快速诊断亚马逊Listing五维健康指数并智能排序修复优先级,提供详细分析与个性化修复方案。

Registry SourceRecently Updated
Coding

Web Publisher Skill

输入文章 URL **或本地文档(PDF/DOCX/PPTX/XLSX/EPUB/图片/音频/...)**,自动提取正文、可选 AI 改写、并发布到微信公众号;也可只把任意文档转成 Markdown 文本(不发布)。抓取 / 转换 / 改写 / 发布都在服务端 (tools.siping.me) 完成,CLI 不...

Registry SourceRecently Updated