audio-jingle — Claude Code skill: audio generation, how to install
audio-jingle generates jingles, voiceover, and sound effects. Routes music to Suno V5, Udio, or Lyria; speech to MiniMax TTS or ElevenLabs V3; SFX to ElevenLabs SFX or AudioCraft.
Apache-2.0 211 installs ★ 108,855 updated 2026-10-25
npx skills add nexu-io/open-design --skill audio-jingle -a claude-codeWhat audio-jingle does
The skill runs in three modes. The audioKind parameter in project metadata picks which one: music calls Suno V5 by default, speech calls MiniMax TTS, sfx calls ElevenLabs SFX. Duration is set via audioDuration in seconds; for speech you can specify voice — the provider's voice identifier. The skill builds a prompt for the chosen model and runs a unified dispatcher via od media generate, which saves an MP3 or WAV to the project folder.
For music the plan covers genre, tempo, instruments, and vocals (if any). For speech it's the final script, which TTS reads verbatim, including commas. For SFX it's texture, attack, and duration. MiniMax TTS needs a concrete voice_id like male-qn-qingse, not a voice description: if you don't have one, leave out the --voice flag. Tracks under 30 seconds are a single section, 30 to 90 seconds get intro and body, longer tracks get a full arc.
What it helps with
- generate a 30-second jingle for a coffee shop launch
- voice a script using MiniMax TTS
- create a sound effect with specific attack and duration
- route a music request to Suno, Udio, or Lyria
- save the audio file to the project and show the player
Example prompts for the agent
- Make a 30-second upbeat indie-pop jingle for a coffee shop — warm electric piano, brushed drums, bass, choir on the chorus, no vocals
- Voice this script with
male-qn-qingse, 45 seconds - Create an impact sound effect — sharp attack, 2 seconds, single layer
How to install audio-jingle
1Skills CLI (Vercel)
npx skills add nexu-io/open-design --skill audio-jingle -a claude-code2Manually: put the files in place
~/.claude/skills/audio-jingle/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/audio-jingle/
1Skills CLI (Vercel)
npx skills add nexu-io/open-design --skill audio-jingle -a codex2Manually: put the files in place
.agents/skills/audio-jingle/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add nexu-io/open-design --skill audio-jingle -a cursor2Manually: put the files in place
.cursor/skills/audio-jingle/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install nexu-io/open-design design-templates/audio-jingle/SKILL.md2Manually: put the files in place
.github/skills/audio-jingle/SKILL.md1Skills CLI (Vercel)
npx skills add nexu-io/open-design --skill audio-jingle -a gemini-cli2Platform CLI
gemini skills install https://github.com/nexu-io/open-design --path design-templates/audio-jingleManually: put the files in place
.devin/skills/audio-jingle/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add nexu-io/open-design --skill audio-jingle -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about audio-jingle
How do I install audio-jingle in Claude Code?
Run npx skills add nexu-io/open-design --skill audio-jingle -a claude-code. The skill file lands in ~/.claude/skills/audio-jingle/SKILL.md.
What does audio-jingle do?
It generates music, voiceover, and sound effects. The audioKind parameter in project metadata picks the model: for music it uses Suno V5, Udio, or Lyria; for speech it uses MiniMax TTS, Fish, or ElevenLabs V3; for SFX it uses ElevenLabs SFX or AudioCraft. Output is saved to the project as MP3 or WAV.
How do I set the voice for MiniMax TTS?
Specify a concrete voice_id from the provider in project metadata (for example male-qn-qingse). If you pass a voice description instead of an identifier, MiniMax will reject the request. If you don't have an identifier, leave out the --voice flag and the default voice applies.
Source text
SKILL.md · Apache-2.0
---
name: audio-jingle
description: |
Audio generation skill — jingles, beds, voiceover, and sound effects.
Routes music requests to Suno V5 / Udio / Lyria, speech to MiniMax
TTS / FishAudio / ElevenLabs V3, and SFX to ElevenLabs SFX or
AudioCraft. Output is one MP3/WAV file saved to the project folder.
triggers:
- "music"
- "jingle"
- "bed"
- "voiceover"
- "tts"
- "sound effect"
- "音乐"
- "配音"
- "音效"
od:
mode: audio
surface: audio
scenario: marketing
preview:
type: html
entry: example.html
design_system:
requires: false
example_prompt: |
A 30-second upbeat indie-pop jingle for a coffee shop launch — warm
electric piano lead, brushed drums, gentle bass, a single sun-soaked
"ahhh" choir on the chorus. No vocals. Loop-friendly tail.
---
# Audio Jingle Skill
Three sub-modes. The active project's `audioKind` decides which one
runs:
| `audioKind` | Models we route to | Plan focus |
|---|---|---|
| `music` | Suno V5 (default), Udio, Lyria 2 | genre + tempo + instrumentation |
| `speech` | MiniMax TTS (default), Fish, ElevenLabs V3 | script + voice + pacing |
| `sfx` | ElevenLabs SFX (default), AudioCraft | texture + impact + duration |
## Resource map
```
audio-jingle/
├── SKILL.md
└── example.html
```
## Workflow
### Step 0 — Read the project metadata
`audioKind`, `audioModel`, `audioDuration` (seconds), and (for speech)
`voice`. Branch by known values and use them verbatim. Missing metadata is not
an instruction to ask: infer a safe default when possible, and emit a
clarifying form only when the missing answer would materially change the
requested output or prevent generation.
Important: `voice` is provider-specific. For `minimax-tts`, `--voice`
must be a valid MiniMax `voice_id` (for example `male-qn-qingse`), not
a natural-language description. If you only have a prose voice brief
("warm female narrator", "neutral Mandarin"), keep that in your plan
but omit `--voice` so the daemon's default voice id applies, or ask the
user to choose a specific id.
### Step 1 — Plan
**Music**
- Genre + reference artists (1-2)
- Tempo (BPM) + key
- Instrumentation (3-5 instruments max)
- Vocals: yes / no / hummed / choir
- Mood arc (intro → chorus → outro)
**Speech**
- Script (final, not draft — TTS runs verbatim)
- Voice target + pacing
For MiniMax this means a real `voice_id`, not prose in `--voice`
- Pronunciation hints for proper nouns / acronyms
**SFX**
- Texture (impact / whoosh / ambience / foley)
- Duration + envelope (sharp attack vs. gentle swell)
- Layering note (single hit vs. stacked)
State the plan in 2-3 sentences before dispatching.
### Step 2 — Compose the prompt
Use the format the upstream model prefers. Bind `audioDuration` to the
API parameter directly; never put "make it 30 seconds" in prose.
### Step 3 — Dispatch via the media contract
Use the unified dispatcher — do **not** call provider APIs by hand:
```bash
"$OD_NODE_BIN" "$OD_BIN" media generate \
--project "$OD_PROJECT_ID" \
--surface audio \
--audio-kind "<music|speech|sfx>" \
--model "<audioModel from metadata>" \
--duration <audioDuration seconds> \
[--voice "<provider voice id (speech only)>"] \
--output "<short-slug>-<duration>s.mp3" \
--prompt "<assembled prompt from Step 2 — for speech, the literal script>"
```
The command prints one line of JSON: `{"file": {"name": "...", ...}}`.
The bytes land in the project; the FileViewer renders the audio
transport controls automatically.
### Step 4 — Hand off
Reply with: plan summary, the filename returned by the dispatcher, and
one sentence on what to try if the user wants a variation (e.g. "swap
tempo from 92 to 108 BPM" rather than "make it different").
## Hard rules
- TTS runs your script **literally**. Proof it before dispatching —
even one stray comma changes the cadence.
- MiniMax TTS rejects free-form voice prose in `--voice`. Use a real
MiniMax `voice_id` (for example `male-qn-qingse`) or omit the flag
and let the daemon's default voice apply.
- Music: under 30s = single section; 30–90s = intro + body; 90s+ =
full arc. Don't try to fit a 3-act song into 15 seconds.
- SFX: prefer one well-described layer over a paragraph of "make it
cool" — generators reward specific texture words.
- Save the file every turn. The audio viewer shows transport controls
the moment the file lands.
© nexu-io · Apache-2.0 · nexu-io/open-design