This ComfyUI workflow leverages the ElevenLabs API to achieve voice isolation from audio files with background noise. The workflow is designed to take an audio file as input, process it through the ElevenLabsAudioIsolation node, and output a clean voice track, effectively removing unwanted noise. The LoadAudio node is used to import the audio file into the workflow, while the SaveAudioMP3 node ensures the processed audio is saved in a widely compatible MP3 format. This workflow is particularly useful for enhancing audio quality in environments where background noise is unavoidable, such as live recordings or interviews conducted in busy settings. By isolating the voice, it ensures clarity and intelligibility, which is crucial for applications like podcasting, video production, and transcription services.
API
Use this workflow from code
Every Comfy workflow is a JSON graph. The payload below is this workflow, exactly as ComfyUI runs it — fetch it from the URL, keep it in version control, or load it in ComfyUI and run it node by node.
Run it from TypeScript or Python with the Comfy SDK. The same code targets Comfy Cloud or a ComfyUI you host yourself — only the base URL changes.
// Install (beta)
npm i @comfyorg/sdk
// Run "ElevenLabs：Voice Isolation" (TypeScript)
import { Comfy } from "@comfyorg/sdk";
const client = new Comfy({ apiKey: "comfyui-..." });
// This workflow, exported in API format (see note below)
const wf = await client.workflows.fromFile("api_elevenlabs_voice_isolation_api.json");
const job = await client.run(wf);
await job.getOutputs("133")[0].toFile("output.png"); // SaveAudioAdvancedThe SDK takes a workflow in API format: open this workflow in ComfyUI and use File → Export Workflow (API).
Comfy Cloud API access requires a plan with an API key.
FAQ
