{"id":"c9b9bad5-ab44-45cd-ac0a-d8cc0be76d62","shortId":"mqfE6f","kind":"skill","title":"Audio Stem Separator with Demucs","tagline":"Separates audio tracks into individual stems (vocals, drums, bass, other) using Meta's Demucs neural network model via the demucs Python package. Supports batch processing of WAV and MP3 files, outputs isolated stems in FLAC or WAV format, and integrates with FFmpeg for format co","description":"# Audio Stem Separator with Demucs\n\nSeparates audio tracks into individual stems (vocals, drums, bass, other) using Meta's Demucs neural network model via the demucs Python package. Supports batch processing of WAV and MP3 files, outputs isolated stems in FLAC or WAV format, and integrates with FFmpeg for format conversion and loudness matching post-separation.\n\n## Installation\n\nUse the upstream install or setup path that matches your environment:\n- conda env update -f environment-cpu.yml # if you don't have GPUs\n- conda env update -f environment-cuda.yml # if you have GPUs\n- conda activate demucs\n- pip install -e .\n\nRequirements and caveats from upstream:\n- requires custom CUDA code that is not ready for release yet.\n- You will need at least Python 3.8. See requirements_minimal.txt for requirements for separation only,\n- Everytime you see python3, replace it with python.exe. You should always run commands from the\n\nBasic usage or getting-started notes:\n- and environment-[cpu|cuda].yml (or requirements.txt) if you want to train a new model.\n- ### For Windows users\n- Anaconda console.\n\n- Source: https://github.com/adefossez/demucs\n- Extracted from upstream docs: https://raw.githubusercontent.com/adefossez/demucs/HEAD/README.md\n\n## Source\n\n- [Agent Skill Exchange](https://agentskillexchange.com/skills/audio-stem-separator-demucs/)","tags":["audio","stem","separator","demucs","skills","agentskillexchange","agent-skills","ai-agents","ai-tools","awesome-list","claude-code","codex"],"capabilities":["skill","source-agentskillexchange","skill-audio-stem-separator-demucs","topic-agent-skills","topic-ai-agents","topic-ai-tools","topic-awesome-list","topic-claude-code","topic-codex","topic-cursor","topic-llm","topic-mcp","topic-npx-skills","topic-openclaw","topic-skills-catalog"],"categories":["skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/agentskillexchange/skills/audio-stem-separator-demucs","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add agentskillexchange/skills","source_repo":"https://github.com/agentskillexchange/skills","install_from":"skills.sh"}},"qualityScore":"0.454","qualityRationale":"deterministic score 0.45 from registry signals: · indexed on github topic:agent-skills · 8 github stars · SKILL.md body (1,350 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-18T19:09:29.180Z","embedding":null,"createdAt":"2026-05-18T13:15:13.843Z","updatedAt":"2026-05-18T19:09:29.180Z","lastSeenAt":"2026-05-18T19:09:29.180Z","tsv":"'/adefossez/demucs':220 '/adefossez/demucs/head/readme.md':227 '/skills/audio-stem-separator-demucs/)':234 '3.8':167 'activ':140 'agent':229 'agentskillexchange.com':233 'agentskillexchange.com/skills/audio-stem-separator-demucs/)':232 'alway':185 'anaconda':215 'audio':1,7,51,57 'basic':190 'bass':14,64 'batch':29,79 'caveat':147 'co':50 'code':153 'command':187 'conda':119,130,139 'consol':216 'convers':100 'cpu':199 'cuda':152,200 'custom':151 'demuc':5,19,25,55,69,75,141 'doc':224 'drum':13,63 'e':144 'env':120,131 'environ':118,198 'environment-cpu.yml':123 'environment-cuda.yml':134 'everytim':175 'exchang':231 'extract':221 'f':122,133 'ffmpeg':47,97 'file':35,85 'flac':40,90 'format':43,49,93,99 'get':194 'getting-start':193 'github.com':219 'github.com/adefossez/demucs':218 'gpus':129,138 'individu':10,60 'instal':107,111,143 'integr':45,95 'isol':37,87 'least':165 'loud':102 'match':103,116 'meta':17,67 'model':22,72,211 'mp3':34,84 'need':163 'network':21,71 'neural':20,70 'new':210 'note':196 'output':36,86 'packag':27,77 'path':114 'pip':142 'post':105 'post-separ':104 'process':30,80 'python':26,76,166 'python.exe':182 'python3':178 'raw.githubusercontent.com':226 'raw.githubusercontent.com/adefossez/demucs/head/readme.md':225 'readi':157 'releas':159 'replac':179 'requir':145,150,171 'requirements.txt':203 'requirements_minimal.txt':169 'run':186 'see':168,177 'separ':3,6,53,56,106,173 'setup':113 'skill':230 'skill-audio-stem-separator-demucs' 'sourc':217,228 'source-agentskillexchange' 'start':195 'stem':2,11,38,52,61,88 'support':28,78 'topic-agent-skills' 'topic-ai-agents' 'topic-ai-tools' 'topic-awesome-list' 'topic-claude-code' 'topic-codex' 'topic-cursor' 'topic-llm' 'topic-mcp' 'topic-npx-skills' 'topic-openclaw' 'topic-skills-catalog' 'track':8,58 'train':208 'updat':121,132 'upstream':110,149,223 'usag':191 'use':16,66,108 'user':214 'via':23,73 'vocal':12,62 'want':206 'wav':32,42,82,92 'window':213 'yet':160 'yml':201","prices":[{"id":"9dc12be1-db0d-4ca4-92c2-6cf48fab1dfc","listingId":"c9b9bad5-ab44-45cd-ac0a-d8cc0be76d62","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"agentskillexchange","category":"skills","install_from":"skills.sh"},"createdAt":"2026-05-18T13:15:13.843Z"}],"sources":[{"listingId":"c9b9bad5-ab44-45cd-ac0a-d8cc0be76d62","source":"github","sourceId":"agentskillexchange/skills/audio-stem-separator-demucs","sourceUrl":"https://github.com/agentskillexchange/skills/tree/main/skills/audio-stem-separator-demucs","isPrimary":false,"firstSeenAt":"2026-05-18T13:15:13.843Z","lastSeenAt":"2026-05-18T19:09:29.180Z"}],"details":{"listingId":"c9b9bad5-ab44-45cd-ac0a-d8cc0be76d62","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"agentskillexchange","slug":"audio-stem-separator-demucs","github":{"repo":"agentskillexchange/skills","stars":8,"topics":["agent-skills","ai-agents","ai-tools","awesome-list","claude-code","codex","cursor","llm","mcp","npx-skills","openclaw","skills-catalog"],"license":"mit","html_url":"https://github.com/agentskillexchange/skills","pushed_at":"2026-05-18T19:02:17Z","description":"The open catalog of AI agent skills — 2,000+ security-scanned skills for Claude Code, Cursor, Codex, and more.","skill_md_sha":"2351cb67fdf533a1d4cbe22e8ff74d542d4055ed","skill_md_path":"skills/audio-stem-separator-demucs/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/agentskillexchange/skills/tree/main/skills/audio-stem-separator-demucs"},"layout":"multi","source":"github","category":"skills","frontmatter":{"name":"Audio Stem Separator with Demucs","description":"Separates audio tracks into individual stems (vocals, drums, bass, other) using Meta's Demucs neural network model via the demucs Python package. Supports batch processing of WAV and MP3 files, outputs isolated stems in FLAC or WAV format, and integrates with FFmpeg for format conversion and loudness matching post-separation."},"skills_sh_url":"https://skills.sh/agentskillexchange/skills/audio-stem-separator-demucs"},"updatedAt":"2026-05-18T19:09:29.180Z"}}