IRIS SDK V3 Release

Transform audio with IRIS SDK V3. AI-powered noise removal, real-time denoising, and flexible deployment options for any application.

9 Apr '25

This week marks the release of the IRIS SDK V3—the ultimate toolkit for delivering premium audio experiences.

For years, IRIS technology has powered critical audio environments, from the racetracks of IndyCar to global contact centres, delivering unmatched clarity and reliability. With the IRIS SDK, we’re taking it a step further, giving third-party developers access to the same cutting-edge AI models and DSP algorithms that set IRIS apart.

Whether you’re building client-side, server-side, or in the cloud, the IRIS SDK is designed for seamless integration, rapid deployment, and industry-leading performance. It’s more than a toolkit, it’s your opportunity to unlock premium audio experiences and transform communication in any environment.

Why choose the IRIS SDK?

The IRIS SDK goes beyond being a tool—it’s your gateway to delivering exceptional audio clarity with unmatched efficiency and impact.

  • Rapid deployment: Achieve industry-leading audio solutions in just hours.
  • Flexible architecture: Deploy seamlessly on client-side, server-side, or cloud infrastructures.
  • Monetizable feature: Unlock new revenue streams by offering premium audio features.
  • Proven impact: Transform operations with noise-free, high-performance audio technology that ranks among the best noise suppression SDKs.

Enhance communications in any environment

Honed in the harshest audio environments and built on decades of experience, the IRIS SDK can be deployed in any environment to start delivering speech enhancement and real-time audio denoising in just hours.

Client-side

Available natively and as a WebRTC Audio Worklet Processor for browser-based applications , the IRIS SDK can process audio directly on the user’s device in real-time. Perfect for video conferencing suites or softphone platforms, there is no need to set up servers and all audio processing happens locally on the end-client.

Server-side

Available in C++, Python and NodeJS across Windows, MacOS and Linux, the IRIS SDK can run server-side for audio processing both online and offline.

With “faster-than-realtime” AI audio models, batch processing terabytes of audio is fast and simple; or integrate the IRIS SDK into your existing audio chain to remove background voices for more accurate voice bot and IVR interactions or as part of a speech analytics workflow to remove noise and improve clarity.

In the cloud

As well as native language bindings, the IRIS SDK can be deployed in your cloud with our Terraform modules, Helm charts, and Docker containers. Perfect for post-production, audio streaming, or enhancing real-time communication with a denoising API, the IRIS SDK integrates effortlessly into your existing processing stack.

Packed with features

The IRIS SDK is all you need to get the most from your audio and ships with a suite of audio tooling.

  • Audio analytics
  • Automatic resampling and buffering
  • Adaptive volume control
  • Proprietary processors for filtering, gain and compressors

Use cases

  • Real-Time Communication Applications: A perfect Krisp SDK alternative or NVIDIA noise removal SDK alternative for developers who need a powerful deep learning noise removal SDK with market-leading algorithms.
  • Interactive Voice Response (IVR) Systems: improve machine understanding and responses with more accurate speech-to-text transcriptions and natural language processing (NLP).
  • Virtual assistants and accessibility: enable users to interact with devices and services through voice commands even in noisy environments and enhance accessibility for individuals with disabilities.
  • Broadcasting: Deliver clear speech intelligibility in challenging audio environments, such as live motorsports or on-location reporting, with real-time noise suppression.
  • Podcasts: Create studio-quality sound by removing background noise, balancing audio levels, and enhancing clarity.
  • Call QA and intelligence: Enhance transcription accuracy and speech analytics by eliminating noise, enabling clearer insights into customer interactions and agent performance.

What’s next?

We move fast so you can expect new features and updates to ship just as quickly. Join our mailing list to be one of the first to get access to the IRIS SDK and stay up to date with all of the latest developments and tips on how to get the most out of our audio.

Get in touch to see how our technology can best support you and your audio needs.

Latest stories

IRIS SDK V3 Release

Transform audio with IRIS SDK V3. AI-powered noise removal, real-time denoising, and flexible deployment options for any application.