Generate and edit Draw.io, Mermaid, and Excalidraw diagrams from natural language using a structured JSON spec.
Coding
Music Generation
Try itGenerate original instrumental and vocal music from a text prompt, 5 seconds to 10 minutes, royalty-free for YouTube, podcasts, apps, games, ads, and films.
What it does
Generate original music from a text description — specify genre, mood, duration, and instrumentation, and the model handles arrangement, dynamics, and lyrics. Output is MP3 (44.1kHz, 128kbps), ranging from 5 seconds to 10 minutes, either instrumental or with AI vocals. A Composition Plan mode lets you set exact section durations for syncing to video segments or presentation slides. Per CellCog's terms of service, generated tracks are royalty-free for commercial use.
When to use it
- Cinematic scores and game soundtracks
- Lo-fi beats, podcast intros, and jingles
- Pop, hip-hop, rock, and ballad songs with AI vocals
- Ambient soundscapes and background tracks
The skill document
Music Generation - Original Music, Fully Yours
Music generation — 5 seconds to 10 minutes. Instrumental and vocal tracks with high-quality AI vocals.
Generated tracks are royalty-free for commercial use per CellCog's terms of service — YouTube, podcasts, apps, games, ads, films, streaming.
How to Use
For your first CellCog task in a session, read the cellcog skill for the full SDK reference — file handling, chat modes, timeouts, and more.
OpenClaw (fire-and-forget):
result = client.create_chat(
prompt="[your task prompt]",
notify_session_key="agent:main:main",
task_label="my-task",
chat_mode="agent",
)
All agents except OpenClaw (blocks until done):
from cellcog import CellCogClient
client = CellCogClient(agent_provider="openclaw|cursor|claude-code|codex|...")
result = client.create_chat(
prompt="[your task prompt]",
task_label="my-task",
chat_mode="agent",
)
print(result["message"])
Two Ways to Create Music
Simple Prompt (Use This 99% of the Time)
Just describe what you want. The model handles the rest — genre, arrangement, instrumentation, dynamics, and even lyrics:
"Compose a 90-second cinematic score. Start with solo piano, layer in strings at 30 seconds, build to a full orchestral swell, then resolve softly. Mood: bittersweet turning hopeful."
"Create a 3-minute lo-fi hip-hop track with soft piano, vinyl crackle, and mellow drums. 75 BPM. Study vibes."
"Write a 2-minute upbeat pop song with female vocals about starting fresh on a Monday morning. Catchy chorus, feel-good energy."
The model is exceptionally sophisticated — it handles any genre, genre fusion, songs with lyrics, complex arrangements, and mood transitions from a simple description.
Composition Plan (For Precise Timing Control)
Only use this when you need exact section durations — for example, syncing music to specific video segments or presentation slides:
"I need music that syncs with my video:
- Intro: exactly 10 seconds, soft ambient
- Build: exactly 20 seconds, energy rising
- Climax: exactly 15 seconds, full orchestra
- Outro: exactly 10 seconds, gentle fade"
This mode gives precise timing control per section but should only be used when timing accuracy matters for syncing with other media.
What Music You Can Create
Instrumental
| Type | Example |
|---|---|
| Cinematic scores | Epic orchestral, tense thriller, emotional piano, sci-fi ambient |
| Background tracks | Lo-fi beats, corporate background, cafe jazz, ambient soundscapes |
| Podcast intros/outros | 5-10 second branded stings, transitions, bumpers |
| Game soundtracks | Battle themes, exploration music, boss fights, menu themes |
| Jingles | Ad jingles, notification sounds, reveal stingers |
| Ambient | Meditation, nature soundscapes, focus music |
Vocal Tracks
CellCog generates songs with perfect AI vocals — just describe the lyrical theme:
| Type | Example |
|---|---|
| Pop songs | Catchy hooks, verse-chorus structure, radio-ready |
| Ballads | Emotional, piano-driven, storytelling |
| Hip-hop/Rap | Rhythmic vocals, beats, flow |
| Rock | Guitar-driven, powerful vocals |
| R&B/Soul | Smooth, melodic, groove |
Specs
| Parameter | Range |
|---|---|
| Duration | 5 seconds to 10 minutes |
| Output | MP3 (44.1kHz, 128kbps) |
| Vocals | Instrumental or with AI vocals |
| Licensing | Royalty-free per CellCog terms of service |
Chat Mode
Use chat_mode="agent" for music generation. Music executes well in agent mode.
Example Prompts
Cinematic score:
"Compose a 2-minute cinematic score for a nature documentary finale. Begin with solo cello (melancholic), layer in strings and piano at 40 seconds, build to a hopeful orchestral swell, resolve with gentle piano. Think Planet Earth meets Interstellar."
Lo-fi background:
"Create 5 minutes of lo-fi study beats. Soft piano, mellow drums, vinyl crackle, gentle bass. 75 BPM. Warm and unobtrusive — good for focus."
Podcast intro + outro:
"Create a podcast intro (8 seconds) and outro (6 seconds). Show is a tech startup podcast. Intro: energetic, modern electronic with a hook. Outro: same vibe but mellower wind-down. Should feel like the same show."
Song with vocals:
"Write a 3-minute upbeat indie pop song with female vocals. Theme: the excitement of moving to a new city. Catchy chorus, acoustic guitar foundation, builds with drums and synth. Feel-good, sing-along energy."
Game soundtrack:
"Compose a 2-minute boss battle theme for a fantasy RPG. Intense orchestral with choir, driving percussion, escalating tension. Think Dark Souls meets Final Fantasy."
Tips
-
Describe the feeling, not just the genre: "Music that makes a startup pitch feel like the future" works better than "electronic music."
-
Specify duration: "45 seconds" vs "3 minutes" changes composition structure significantly.
-
Reference moods, not copyrighted songs: "Hans Zimmer-style epic" and "ChilledCow lo-fi vibes" work well. Do not reference specific copyrighted songs.
-
For vocals: Set the lyrical theme and mood. The model writes lyrics that fit. Or provide specific lyrics you want sung.
-
Energy arc matters: "Starts quiet, builds at midpoint, resolves softly" gives clear compositional structure.
-
For video background music: If the music is for a CellCog video, mention it in your video prompt instead — CellCog handles music as part of video production automatically.
If CellCog is not installed
Claude Code, Cursor, Codex + 70 more agents: npx skills add cellcog/skills --skill cellcog
OpenClaw: clawhub install cellcog
CellCog plugin users: run /cellcog-setup (or /cellcog:cellcog-setup depending on your tool)
Manual setup: pip install -U cellcog and set CELLCOG_API_KEY. See the cellcog skill for SDK reference.
Related skills
Join a video meeting as an AI bot with voice, avatar, and screenshare across four operating modes.
Stores durable facts in a categorized, plain-markdown vault on disk, alongside your agent's built-in memory.
Find why your productivity system keeps failing, then apply the smallest fix — capacity math, bottleneck routing, durable local notes.
Fetch raw ad creative, app, ranking, and revenue data from AdMapix as structured JSON.
Site audit, content writing, and competitor analysis for organic search rankings.
More from CellCog
Browse all skillsGenerate up to 4-minute videos from a single prompt — scripted, voiced, scored, and edited automatically.
Citation-backed research reports across markets, competitors, investments, and academic topics via the CellCog agent.
Get tutoring that breaks any concept into multiple angles — diagrams, analogies, worked examples, practice problems, and full study guides.
Generate voiceovers, music, sound effects, and cloned-voice audio from text prompts using three voice providers.
Generate polished PDF and DOCX documents from prompts — resumes, contracts, reports, proposals, and more.
Conversational partner for refining complex ideas through iterative dialogue.