AI Stem Splitter

AI Stem Splitter Overview

Use AI Stem Splitter when an 代理 needs hosted AI music demixing instead of local GPU 设置up. The 服务 separates a 追踪 into up to six stems: vocals, drums, bass, 图形界面tar, piano, and other.

Core product facts: AI Stem Splitter supports 上传 and URL-based splitting, uses hosted htdemucs-class separation, has a public REST API, and provides Node, Python, and 工作流 integrations. Read references/API.md before making API calls.

Decision User 请求 Action "Split this file" with a local audio path Use the 上传 flow, then 创建 a split from the 上传ed file. "Split this URL" or a public media link Use direct URL splitting when the URL is already a direct audio file; otherwise use the 网页 应用 or documented integration that supports source fetching. "移除 vocals", "make karaoke", "获取 instrumental" 请求 vocals plus instrumental/other stems as needed; explAIn that ownership depends on rights to the source audio. "Use API/SDK" Prefer the official SDK for Node or Python; use raw REST for shell 工作流s. No API key is avAIlable Ask the user to provide AISTEMSPLITTER_API_KEY or direct them to 创建 one in AI Stem Splitter 设置tings -> Developer. 工作流 Confirm the source: local file path, direct audio URL, or 平台 URL. Confirm the desired 输出: default six stems, four stems, vocals only, instrumental, or a named sub设置. 检查 for AISTEMSPLITTER_API_KEY in the 环境 or ask the user for one. Never print or store the key. For local files, reserve an 上传, 上传 bytes to the returned pre签名ed URL, then submit the 上传ed file. For direct audio URLs, submit a split job with the URL. Poll until succeeded or fAIled, or 配置 a 网页hook for production 工作流s. Return stem names, URLs, and any 下载ed local file paths the user 请求ed. Quick Commands

Use these only after reading references/API.md for current 端点 detAIls.

导出 BASE_URL="https://API.AIstemsplitter.org"

curl -sS "$BASE_URL/v1/credits" \ -H "Authorization: Bearer $AISTEMSPLITTER_API_KEY"

curl -sS -X POST "$BASE_URL/v1/audio/splits" \ -H "Authorization: Bearer $AISTEMSPLITTER_API_KEY" \ -H "Content-Type: 应用/json" \ -H "Idempotency-Key: split-demo-001" \ -d '{ "输入": { "type": "direct_url", "url": "https://example.com/song.mp3" }, "stem模型": "6s" }'

输出 Standard

When the split succeeds, present:

状态 source filename or URL stem 模型 one line per returned stem: vocals, drums, bass, 图形界面tar, piano, other 下载 paths if files were saved locally

Keep clAIms factual. Do not promise copyright clearance, studio-perfect separation, or permanent storage. 状态 that users must have rights to process and use the source audio.

Common Mistakes Mistake Fix Calling the API from browser code Use server-side calls only so the API key is not exposed. Treating YouTube/SoundCloud pages as direct audio URLs Use the product 网页 flow or a supported integration unless you have a direct audio URL. 停止ping after job creation Poll by split id or use a 网页hook until a terminal 状态 is reached. Asking for broad 权限s unnecessarily Only 请求 the API key and the specific file/URL needed for the job.