Skip to main content
The Voice Isolation NC (VI_G_NC3.0) is a best-in-class model for denoising audio and clarifying speech. It extracts voices from any noisy environment in real time, removing unwanted background noise and background speech while preserving natural voice quality. With low latency and minimal computing cost, NC delivers clean speech waveforms suitable for human communication.

​
Hear the Difference

Voice Isolation NC preserves only the primary speaker by removing background voices, noise, and chatter.
Before · Primary speaker + background noise
After · Primary speaker only

​
Key Features

Removes background noise

Environmental noise, background speech, HVAC, keyboard, traffic — all removed without affecting the primary speaker.

Preserves voice quality

Natural voice quality preservation. Optimized for single-speaker scenarios.

Real-time, low cost

Minimal latency across any acoustic environment. Low compute cost for high concurrency.

​
Specifications

Model ID: VI_G_NC3.0
Category: Noise Cancellation
Type: Human ↔ Human

~40ms

Streaming latency

24kHz

Max sample rate

~1m

Primary speaker range

​
Use Cases

Contact Centers

Agent-customer calls. Clear communication in noisy call centers.

Remote Work

Video conferences. Professional audio from home offices.

Gaming

Voice chat. Crystal-clear team communication.

Telemedicine

Doctor-patient calls. Private, distraction-free consultations.

​
Code Example

Create an audio processor with the Voice Isolation NC model: 
audio_params = sanas_remote_sdk.AudioParams()
audio_params.modelName = "VI_G_NC3.0"
audio_params.sampleRate = 16000  # Or up to 24kHz

processor, create_result = sdk.CreateAudioProcessor(audio_params)
For full setup and initialization, see the Quick Start →

​
Next Steps

Quick Start

Get up and running with Sanas SDK in under 5 minutes.

API Reference

Full SDK documentation for classes, enums, and callbacks.

Processing Multiple Streams

Handle multiple concurrent audio streams.