skills.rest
junainfinity
junainfinityCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

audio-jingle

Generate MP3 or WAV audio assets via Suno, MiniMax, and ElevenLabs.

Updated Aug 27, 2026
Search Tags:#audio#tts#voiceover#music-generation#audio-design#sfx#jingle
One-click install
npx skills add https://github.com/junainfinity/osmDesign --skill audio-jingle
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: audio-jingle
Source: https://github.com/junainfinity/osmDesign/tree/main/skills/audio-jingle
Command: npx skills add https://github.com/junainfinity/osmDesign --skill audio-jingle

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Audio production for marketing and content teams often requires quick, branded audio assets such as jingles, beds, voiceovers, and sound effects. This skill streamlines that workflow by providing an AI-driven, prompt-based pipeline that produces a finished audio file in the project folder.

Core Features & Use Cases

  • Three active sub-modes controlled by the project's audioKind: music, speech, and SFX, enabling flexible audio generation for ads, podcasts, and promos.
  • Music: routes to Suno V5 (default), Udio, and Lyria for genre, tempo, instrumentation, and mood-focused outputs; Speech: uses MiniMax TTS, Fish, and ElevenLabs V3 for scripted narration with target voices and pacing; SFX: leverages ElevenLabs SFX or AudioCraft for texture and impact.
  • Output is a single MP3 or WAV file saved to the project folder, suitable for quick reviews and iterative adjustments.

Quick Start

Provide your audio brief (genre, duration, vocal/no-vocal, mood) and run the audio-jingle workflow to generate the deliverable in your project folder.

Frequently Asked Questions about audio-jingle

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate an audio jingle for a marketing campaign?▼

Generate an audio jingle by providing a brief with genre, duration, mood, and vocal preference. The workflow routes music requests to Suno V5, Udio, or Lyria, saving a finished MP3 or WAV file to your project folder for rapid campaign iteration.

Can I use this to create voiceovers and sound effects in the same workflow?▼

Yes, you can create voiceovers and sound effects in the same workflow. Speech routes to MiniMax, Fish, or ElevenLabs for narration, while SFX uses ElevenLabs SFX or AudioCraft, all controlled by the project's audioKind setting.

What is the best way to produce branded audio beds for podcasts quickly?▼

The best way to produce branded audio beds is using a prompt-driven workflow that routes music generation to Suno V5. You specify mood and instrumentation, and it outputs a single MP3 or WAV file ready for podcast integration.

Does the audio generation process support custom pacing for TTS narration?▼

Yes, the audio generation process supports custom pacing for TTS narration. By routing speech to MiniMax, Fish, or ElevenLabs V3, you can generate scripted narration with target voices and specific pacing for your promos.

What audio file formats are output by this AI jingle and SFX generator?▼

The AI jingle and SFX generator outputs a single MP3 or WAV file. This predefined format is saved directly to your project folder, making it suitable for quick reviews and iterative adjustments across campaigns.

Related Skills

Explore More Design & Creative Skills→
shfahiimshfahiim

mood-music

Map user mood to Loudly API genres and generate music tracks.

Community
Advanced
levanminhduclevanminhduc

ffmpeg

Convert, encode, extract, and stream audio and video with FFmpeg.

Community
Advanced
guideopsguideops

brand

Enforce brand voice and visual identity standards across content.

Community
Advanced
SpiralCloudOmegaSpiralCloudOmega
1

music-generation

Generate DAW-ready WAV music tracks from text prompts using ACE-Step 1.5.

Community
Advanced