Generate music from text prompts using Riffusion, YuE, and Stable Audio Open.
npx skills add https://github.com/damionrashford/media-os --skill media-musicgen
Please help me install this Agent Skill. Skill: media-musicgen Source: https://github.com/damionrashford/media-os/tree/main/skills/media-musicgen Command: npx skills add https://github.com/damionrashford/media-os --skill media-musicgen
Open-source AI music generation with permissive-license models: Riffusion (MIT, spectrogram-to-audio music from text), YuE (Apache 2.0, Chinese Academy 2025 full-song generation with vocals), Stable Audio Open (Stability community license, commercial up to 1M ARR). Text-to-music, genre-conditioned generation, full song with structure, continuation from existing audio, stem splits via media-demucs. Use when the user asks to generate music from text, create AI songs, make background music for video, generate a jingle, produce royalty-free music with open-source models, make a full song with vocals, or continue an existing musical idea.
Generate a 60-second ambient track from a text prompt using the preferred model and export to output.wav.
High-intent search queries and answers about installing and using this skill.
You can generate AI music from text prompts using open-source models like Riffusion, YuE, and Stable Audio Open. This Skill processes your text descriptions to produce royalty-free audio tracks, full songs with vocals, or background music.
Yes, you can create full songs with vocals using open-source AI music generation. The YuE model (Apache 2.0) specifically supports full-song generation complete with vocal tracks and song structure.
Stable Audio Open uses the Stability community license, allowing commercial use up to 1M ARR. The licensing-aware workflows in this Skill help ensure your royalty-free AI generated music meets distribution requirements.
You extract stems from AI generated audio by routing the output through the media-demucs integration. This workflow separates your generated full songs into individual instrument or vocal stems for further production.
Yes, music continuation from existing audio is supported across the generation workflow. You can input existing audio to extend musical ideas, allowing Riffusion and other integrated models to build upon your initial audio segments.
Text-to-music generation requires Python dependencies including PyTorch, Diffusers, Transformers, and stable_audio_tools. These libraries provide the foundational machine learning frameworks needed to run the Riffusion, YuE, and Stable Audio models.
adiytharpansaGenerate videos from text prompts and images using open-source models.
whyiloveher2411Create beat-synced HyperFrames videos from music tracks using Python libraries.
calesthioGenerate music, vocal covers, and isolated stems via RunPod ACE-Step.
519labGenerate music from lyrics and tags using open-source AI models.
