# Send audio-cog to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
## Suggested prompts
### New install

```text
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
```
### Upgrade existing

```text
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "audio-cog",
    "name": "audio-cog",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/nitishgargiitd/audio-cog",
    "canonicalUrl": "https://clawhub.ai/nitishgargiitd/audio-cog",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/audio-cog",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=audio-cog",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "SKILL.md"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "slug": "audio-cog",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-04T17:46:47.965Z",
      "expiresAt": "2026-05-11T17:46:47.965Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=audio-cog",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=audio-cog",
        "contentDisposition": "attachment; filename=\"audio-cog-1.0.12.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "audio-cog"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/audio-cog"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/audio-cog",
    "downloadUrl": "https://openagent3.xyz/downloads/audio-cog",
    "agentUrl": "https://openagent3.xyz/skills/audio-cog/agent",
    "manifestUrl": "https://openagent3.xyz/skills/audio-cog/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/audio-cog/agent.md"
  }
}
```
## Documentation

### Audio Cog - AI Audio Generation Powered by CellCog

Create professional audio with AI - from voiceovers and narration to background music and sound design.

### Prerequisites

This skill requires the cellcog skill for SDK setup and API calls.

clawhub install cellcog

Read the cellcog skill first for SDK setup. This skill shows you what's possible.

Quick pattern (v1.0+):

# Fire-and-forget - returns immediately
result = client.create_chat(
    prompt="[your audio request]",
    notify_session_key="agent:main:main",
    task_label="audio-task",
    chat_mode="agent"  # Agent mode is optimal for all audio tasks
)
# Daemon notifies you when complete - do NOT poll

### Text-to-Speech / Voiceover

Convert text to natural-sounding speech:

Narration: "Generate a professional male voiceover for this product video script"
Audiobook Style: "Create an engaging narration of this short story with emotional delivery"
Podcast Intros: "Generate a warm, friendly podcast intro: 'Welcome to The Daily Tech...'"
E-Learning: "Create clear, instructional voiceover for this training module"
IVR/Phone Systems: "Generate professional phone menu prompts"

### Available Voices

CellCog provides 8 high-quality voices with distinct characteristics:

VoiceGenderBest ForCharacteristicscedarMaleProduct videos, announcementsWarm, resonant, authoritative, trustworthymarinFemaleProfessional content, tutorialsBright, articulate, emotionally agileballadMaleStorytelling, flowing narrativesSmooth, melodic, musical qualitycoralFemaleEnergetic content, adsVibrant, lively, dynamic, spiritedechoMaleThoughtful content, documentariesCalm, measured, deliberatesageFemaleEducational, knowledge contentWise, contemplative, reflectiveshimmerFemaleGentle content, wellnessSoft, gentle, soothing, approachableverseMaleCreative, artistic contentPoetic, rhythmic, expressive

### Voice Recommendations by Use Case

For product videos and announcements:

Use cedar (male) or marin (female) - both project confidence and professionalism.

For storytelling and audiobooks:

Use ballad (male) or sage (female) - designed for engaging, flowing narratives.

For high-energy content:

Use coral (female) - vibrant and dynamic, perfect for ads and exciting announcements.

For calm, educational content:

Use echo (male) or shimmer (female) - measured pacing ideal for learning.

### Voice Style Customization

Beyond selecting a voice, you can fine-tune delivery with style instructions:

Accent & dialect: American, British, Australian, Indian, etc.
Emotional range: Excited, serious, warm, mysterious, dramatic
Pacing: Slow and deliberate, conversational, fast and energetic
Special effects: Whispering, character impressions

Example with style instructions:

"Generate voiceover using cedar voice with a warm, conversational tone. Speak at medium pace with slight enthusiasm when mentioning features. American accent."

### Music Generation

Create original background music and soundtracks:

Background Music: "Create calm lo-fi background music for a study video, 2 minutes"
Podcast Music: "Generate an upbeat intro jingle for a tech podcast, 15 seconds"
Video Soundtracks: "Create cinematic orchestral music for a product launch video"
Ambient/Mood: "Generate peaceful ambient sounds for a meditation app"
Genre-Specific: "Create energetic electronic music for a fitness video"

### Music Specifications

ParameterOptionsDuration15 seconds to 5+ minutesGenreElectronic, rock, classical, jazz, ambient, lo-fi, cinematic, pop, hip-hopTempo60 BPM (slow) to 180+ BPM (fast)MoodUpbeat, calm, dramatic, mysterious, inspiring, melancholicInstrumentsPiano, guitar, synth, strings, drums, brass, etc.

### Music Licensing

All AI-generated music from CellCog is royalty-free and fully yours to use commercially.

You have complete rights to use the generated music for:

YouTube videos (including monetized content)
Commercial projects and advertisements
Podcasts and streaming
Apps and games
Any other commercial or personal use

No attribution required. No licensing fees. The music is generated uniquely for you.

### Audio Output Formats

FormatBest ForMP3Standard audio delivery, voiceovers, musicCombined with videoBackground music for video-cog outputs

### Chat Mode for Audio

Use chat_mode="agent" for all audio generation tasks.

Audio generation—whether voiceovers, music, or sound design—executes efficiently in agent mode. CellCog's audio capabilities don't require multi-angle deliberation; they require precise execution, which agent mode excels at.

There's no scenario where agent team mode provides meaningfully better audio output. Save agent team for research and complex creative work that benefits from multiple reasoning passes.

### Example Audio Prompts

Professional voiceover with specific voice:

"Generate a professional voiceover using the marin voice for this script:
'Introducing TaskFlow - the project management tool that actually works. With intelligent automation, seamless collaboration, and powerful analytics, TaskFlow helps teams do their best work.'
Style: Confident and friendly, medium pace. Suitable for a product launch video."

Podcast intro with voice selection:

"Create a podcast intro voiceover using cedar voice:
'Welcome to Future Forward, the podcast where we explore the technologies shaping tomorrow. I'm your host, and today we're diving into...'
Style: Warm and engaging, conversational tone. Also generate a 10-second upbeat intro music bed to go underneath."

Background music:

"Generate 2 minutes of calm, lo-fi hip-hop style background music. Should be chill and unobtrusive, good for studying or working. Include soft piano, mellow beats, and gentle vinyl crackle. 75 BPM."

Audiobook narration:

"Create an audiobook-style narration using ballad voice for this passage:
[passage text]
Style: Warm storytelling quality, measured pace with appropriate pauses for drama."

Cinematic music:

"Generate 90 seconds of cinematic orchestral music for a tech company's 'About Us' video. Start soft and inspiring, build to a confident crescendo, then resolve to a hopeful ending."

### Multi-Language Support

CellCog can generate speech in 50+ languages:

English (multiple accents)
Spanish, French, German, Italian, Portuguese
Chinese (Mandarin, Cantonese)
Japanese, Korean
Hindi, Arabic
Russian, Polish, Dutch
And many more

Specify the language in your prompt:

"Generate this text in Japanese with a native female speaker using shimmer voice: 'いらっしゃいませ...'"

### Tips for Better Audio

Choose the right voice: Match the voice to your content type. Cedar/marin for professional, ballad/sage for storytelling, coral for energy.


Provide the complete script: Don't say "something about our product" - write out exactly what should be said.


Include style instructions: "Confident but warm", "slow and deliberate", "with slight excitement" helps shape delivery.


For music: Specify duration, tempo (BPM if you know it), mood, and genre.


Pronunciation guidance: For names or technical terms, add hints: "CellCog (pronounced SELL-kog)"


Emotional beats: For longer voiceovers, indicate tone shifts: "[excited] And now for the big reveal... [serious] But there's a catch."
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: nitishgargiitd
- Version: 1.0.3
## Source health
- Status: healthy
- Item download looks usable.
- Yavira can redirect you to the upstream package for this item.
- Health scope: item
- Reason: direct_download_ok
- Checked at: 2026-05-04T17:46:47.965Z
- Expires at: 2026-05-11T17:46:47.965Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/audio-cog)
- [Send to Agent page](https://openagent3.xyz/skills/audio-cog/agent)
- [JSON manifest](https://openagent3.xyz/skills/audio-cog/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/audio-cog/agent.md)
- [Download page](https://openagent3.xyz/downloads/audio-cog)