ModelsLab/Voice Isolation

vocal_isolator

Voice Isolation AudioFree for Premium Users LLMs.txt

Endpoint:

Voice isolation technology enhances voice cloning by filtering background noise and echo, enabling clear, real-time replication of vocal nuances using deep learning models with Mel-Spectrograms and neural networks like Tacotron 2 and WaveNet for high-fidelity speech synthesis.

API Playground API Documentation

API Endpoint URL

Base URL for all API requests to this endpoint.

https://modelslab.com/api/v6/voice/vocal_isolator

API Authentication

Authentication requires a valid API key included in the request. Generate and manage your API keys from your developer dashboard. Include the key in the key parameter for all API requests.

Integration Examples

Production-ready code samples for API integration

{
  "init_video": "https://pub-3626123a908346a7a8be8d9295f44e26.r2.dev/livewire-tmp/IxEA4uB8vGWAk1BQVvqbciebfgGFMK-metadmlkZW9wbGF5YmFja180Lm1wNA==-.mp4",
  "base64": "false",
  "webhook": null,
  " track_id": null,
  "key": "YOUR_API_KEY"
}

SDKs

Official SDKs

Production-ready SDKs and client libraries for all major programming languages

JavaScript

Python

PHP

API Parameters

Technical specifications for API request parameters.

Field Name	Parameter	Technical Description
init_video	`init_video`	Upload either audio or video for the one you want to remove background noise
base64	`base64`	Indicates whether the input audio file is provided in base64 format. Defaults to false.
webhook	`webhook`	URL to receive POST notification upon completion
track_id	`track_id`	ID for webhook identification