NVIDIA
NVIDIA
Linux Audio Effects SDK
Resource
NVIDIA
NVIDIA
Linux Audio Effects SDK

Audio Effects SDK for Linux delivers AI-based audio enhancement algorithms, improving end-to-end conversation quality.

Join or Subscribe to get accessSubscribe to the product below to access this premium content:
NVIDIA AI Enterprise
NVIDIA AI EnterpriseAccelerate your AI agent development
Subscribe Now
NVIDIA Developer Program
NVIDIA Developer ProgramJoin the Developer Program for access to free tools, support, and tech resources.
Get Access
Note: You can gain access to hundreds more GPU-optimized artifacts by creating a free NGC account.
Already Subscribed?Log in

NVIDIA Linux Audio Effects SDK

The NVIDIA Linux Audio Effects SDK provides the following audio effects for broadcast use cases with real-time audio processing:

  1. Background Noise Reduction: removes common background noise while preserving the speaker’s natural voice. A second version of this effect offers improved accuracy for automated speech recognition.

  2. Room Echo Cancellation: removes and suppresses reverbs from audio that might occur from the recording environment, improving speech clarity.

  3. Background Noise Reduction + Room Echo Cancellation: removes unwanted noises and reverberations from audio, improving speech intelligibility.

  4. Audio Super Resolution: improves sound quality by adding higher frequency content to the audio stream. For low-frequency audio, this feature predicts the higher frequency spectrum of input audio, which improves audio quality.

  5. Acoustic Echo Cancellation: removes acoustic echo and feedback from audio, which improves the bidirectional audio quality.

  6. Studio Voice: enables ordinary headset, laptop, and desktop microphones to deliver the sound of a high-end studio mic, even if recorded in less-than-ideal acoustic environments with distortions such as reverberations or static noise. Studio Voice enhances and recovers speech degraded by noise reduction filters and beamforming algorithms, making the audio sound like it was recorded in a professional studio. This effect has two variations: Studio Voice High Quality and Studio Voice Low Latency.

  7. Speaker Focus (Early Access): identifies and isolates the primary speaker from all other speakers and removes the speech of all other speakers from the input audio.

  8. Voice Font (Early Access): converts the speaker's voice in input audio to match the target voice while keeping linguistic information and prosody (for example, rhythm and intonation) unchanged.

  9. For more detailed information, please refer to the documentation guide in the SDK packages.


Get Help for NVIDIA AI Enterprise

Enterprise Support

Get access to knowledge base articles and support cases or submit a ticket.

NVIDIA AI Enterprise Documentation

Visit the NVIDIA AI Enterprise Documentation Hub for release documentation, deployment guides and more.

NVIDIA Licensing Portal

Go to the NVIDIA Licensing Portal to manage your software licenses.

Publisher
NVIDIA
NVIDIA
Latest Version2.1.0
UpdatedMarch 16, 2026 UTC
Compressed Size1.4 GB