NVIDIA Maxine Audio Effects (AFX) SDK User Guide#

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

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

  • Audio Super-Resolution: This effect improves the 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.

  • Noise Removal/Denoising: Recordings of speech made outside of a recording studio can contain a lot of background noise, which causes the speech to be garbled and difficult to understand. The audio denoising effect removes such background noise from audio.

  • Noise Removal and Room Echo Removal/Denoise and Dereverb: The effect combines both the above effects to remove/suppress both noise and reverberations from audio. This offers much better performance than applying these effects separately.

  • Room Echo Removal/Dereverb/Room Echo Cancellation: Recordings of speech might contain reverberations from the recording environment, affecting speech clarity. The dereverb effect helps remove or suppress such reverberations from audio.

  • Speaker Focus: This effect identifies and isolates the prominent speaker by removing all background speakers from the input audio, improving the intelligibility of the primary speaker.

  • Studio Voice: Studio Voice enhances/recovers degraded speech recorded using low-end microphones in less-than-ideal acoustic environments. The resulting audio should perceptually sound better than the original, removing/reducing degradation and artifacts to make the audio sound more like a recording in a professional studio setup.

  • Voice Font: Given an input speech input and reference speech ref, this effect converts the input voice to match the ref speaker’s voice while keeping linguistic information and prosody unchanged.

Note

The Windows SDK is optimized for client-side application integration, and the Linux SDK is designed and optimized for server-side (datacenter or cloud) deployments. Using these SDKs for testing, experimentation, and production deployment outside these use cases is not officially supported.