跳到正文
TakoAPI
返回技能列表

audio-cog

由 nitishgargiitd 提供

Media & Streaming
3.6k下载量由 clawskills.sh 提供
5星标
1浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

AI audio generation powered by CellCog.

描述

该技能的功能

Generates professional audio using the CellCog SDK. Supports text-to-speech with 8 distinct voices, original music composition, and narration across 50+ languages. All generated music is royalty-free and cleared for commercial use.

Generated music is fully royalty-free and commercially licensed by default, so there are no stock audio fees or attribution requirements.

何时使用

  • Voiceover for a product launch video using a specific voice and style
  • Background lo-fi music for a YouTube study or tutorial video
  • Podcast intro jingle with a matching host narration track
  • E-learning module narration in a non-English language
  • Royalty-free soundtrack for a mobile app or game

示例工作流

输入

User asks: Generate a 90-second cinematic orchestral track for a product launch video, starting soft and building to a confident crescendo

智能体
  1. 1

    Receives the request and selects chat_mode="agent" for efficient execution

  2. 2

    Constructs a prompt specifying genre (cinematic orchestral), duration (90 seconds), mood arc (soft to confident crescendo), and tempo

  3. 3

    Calls client.create_chat with notify_session_key set so the daemon signals completion

  4. 4

    Waits for the async notification rather than polling

  5. 5

    Returns the generated MP3 file to the user

输出

A 90-second royalty-free orchestral MP3 ready for use in a video timeline

前置要求

  • CellCog API key or account (via cellcog skill setup)

安装

clawhub install nitishgargiitd/audio-cog

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接