AudioShake just released a game-changing SDK that separates audio in real-time

Key Highlights:

• AudioShake launches first real-time SDK enabling cross-platform audio separation with minimal coding
• Major industry partners already integrated including AutoTune, Tuned Global, and AI-Media
• Technology democratizes advanced stem separation for streaming, captioning, and music creation app

AudioShake launched its first software development kit on June 25, enabling developers to embed real-time audio separation into apps with just a few lines of code. The SDK works across iOS, Android, Windows, and Linux platforms, allowing applications to isolate vocals, separate speech from background noise, or extract individual instruments instantly.

Early adopters include AutoTune’s VoCap app, Tuned Global’s streaming platform, AI-Media’s captioning services, and music tools like Voloco and MashApp. “Stems are a gateway to a huge amount of potential innovation,” said Con Raso, Managing Director of Tuned Global.

The technology represents a major shift toward edge-device processing for audio separation, previously requiring cloud-based solutions. With streaming platforms increasingly seeking interactive features to maintain user engagement, AudioShake’s SDK positions developers to create next-generation audio experiences across entertainment, accessibility, and creative applications.