agentleFS
Sign inStart free
erlionaerliona/tunova-agent-plugin/skills/generate-music/SKILL.md

generate-music

Skill0 starsChanged 4 months agoMITView on GitHub

Generate original music — a full song with vocals or an instrumental — from a text prompt using the Tunova Suno API. Use whenever the user asks to create, make, or generate a song, jingle, theme, loop, or background music, or asks for a track in a specific genre/mood.

  • Reads credentials

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. flintfromthebasement/skills★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

Create a free account to mount
Files
SKILL.md

Generate music with Tunova

Turn a text prompt into a finished audio track using the tunova MCP server. Tools: generate_song, wait_for_song, check_song.

Setup (once)

The user needs a Tunova API key (sk_live_…) in the TUNOVA_API_KEY environment variable. If it is missing or a call returns an auth error, tell them:

Get a free Tunova key (50 tokens ≈ 5 songs, no card) at https://tunova.ai, then set TUNOVA_API_KEY.

Workflow

  1. Submit — call generate_song with the user's prompt. Optional: instrumental: true for no vocals, model: "v5.5". It returns a job_id immediately (generation is async).
  2. Wait — call wait_for_song with that job_id until the audio URL(s) are ready (a render takes ~30–120s). For a single non-blocking status check, use check_song instead.
  3. Deliver — give the user the returned audio URL(s).

Billing is on success only — if a render fails, the tokens are automatically refunded, so it is safe to retry.

Writing good prompts

Be concise and concrete: genre, mood, instrumentation, tempo, and (for vocals) a theme or a few lyric lines. Examples:

  • "calm rainy-night lofi hip-hop, mellow piano, vinyl crackle, instrumental"
  • "upbeat pop-punk birthday song for someone named Alex, energetic, cheerful"
  • "cinematic orchestral build, epic, no vocals, 90 bpm"

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free