orchestra-research avatar

Audiocraft Audio Generation

Meta's AudioCraft library wrapped for Claude, giving you MusicGen for text-to-music and AudioGen for sound effects. You get models from 300M to 3.3B parameters, melody conditioning if you want to hum a tune and have it generate around that, and proper stereo output. Generation params are straightforward: set duration, temperature, and guidance strength. The HuggingFace integration works well if you're already in that ecosystem. Honest take: this is solid for prototyping music apps or generating background audio, but you're capped at 30 seconds and the quality ceiling is what it is. If you need longer commercial tracks, look at Stable Audio instead.

skills.sh installs
1.1K
GitHub stars
14.4K
last updated
Aug 21, 2026

Install

$ npx -y skills add orchestra-research/ai-research-skills --skill audiocraft-audio-generation --agent claude-code

Installs into .claude/skills of the current project.

Files

AudioCraft: Audio Generation

Comprehensive guide to using Meta's AudioCraft for text-to-music and text-to-audio generation with MusicGen, AudioGen, and EnCodec.

When to use AudioCraft

Use AudioCraft when:

  • Need to generate music from text descriptions
  • Creating sound effects and environmental audio
  • Building music generation applications
  • Need melody-conditioned music generation
  • Want stereo audio output
  • Require controllable music generation with style transfer

Key features:

  • MusicGen: Text-to-music generation with melody conditioning
  • AudioGen: Text-to-sound effects generation
  • EnCodec: High-fidelity neural audio codec
  • Multiple model sizes: Small (300M) to Large (3.3B)
  • Stereo support: Full stereo audio generation
  • Style conditioning: MusicGen-Style for reference-based generation

Use alternatives instead:

  • Stable Audio: For longer commercial music generation
  • Bark: For text-to-speech with music/sound effects
  • Riffusion: For spectogram-based music generation
  • OpenAI Jukebox: For raw audio generation with lyrics

Quick start

Installation

# From PyPI
pip install audiocraft

Sponsors

Details

Repository
github.com/orchestra-research/ai-research-skills
Categories
AI & Agent Building, Data Science & ML
First seen
Jun 3, 2026

More from orchestra-research/ai-research-skills

All 95
1dbt-labs avataranswering-natural-language-questions-with-dbtdbt-labs/dbt-agent-skillsWrites and executes SQL queries against the data warehouse using dbt's Semantic Layer or ad-hoc SQL to answer business questions. Use when a user asks about ana1.1Kskills.sh installs
2K-Dense-AI avatarpathogen-variant-surveillanceK-Dense-AI/scientific-agent-skillsQuery live pathogen genomic surveillance data through the GenSpectrum LAPIS API to find which viral lineages are circulating now, how fast they are growing, and1.1Kskills.sh installs
3openai avatardevelop-web-gameopenai/skillsUse when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based1.1Kskills.sh installs
4orchestra-research avatarray-trainorchestra-research/ai-research-skillsDistributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray1.1Kskills.sh installs
5orchestra-research avatarweights-and-biasesorchestra-research/ai-research-skillsTrack ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collabo1.1Kskills.sh installs
6steipete avatarvideo-transcript-downloadersteipete/agent-scriptsyt-dlp downloads: video, audio, subtitles, transcripts, clips, playlists.1.1Kskills.sh installs