AudioShake

AudioShake uses AI to separate audio stems from recordings, making sound more interactive, customizable, and accessible. The page describes capabilities for music (vocal and instrument stems, lyric transcription and alignment, music detection and identification), film and TV (dialogue isolation, music and effects separation, multi-speaker separation, copyright compliance), and voice (speech isolation, speech denoise, speech dereverb, multi-speaker separation). It lists use cases including mixing and mastering, localization and captioning, interactive audio, sync licensing, lyric transcription, audio analysis, A/V editing, and copyright compliance. Access is offered through a Studio option described as free to start with nothing to install, a REST API with quickstart, an SDK and developer platform, and data services with custom models and catalog prep. The page includes customer testimonials and case study references but pricing details beyond the free start are not specified.

Key features

• Vocal and instrument stem separation
• Dialogue, music, and effects separation
• Multi-speaker separation, including overlapping voices
• Speech isolation, speech denoise, and speech dereverb
• Lyric transcription and word-by-word alignment
• Music detection and music identification
• Real-time separation
• REST API with quickstart
• SDK, documentation, and developer platform
• Data services with custom models and catalog preparation

Best suited for

• Music mixing, mastering, and immersive mixes
• Localization, dubbing, and captioning workflows
• Sync licensing and instrumental creation
• Lyric transcription and karaoke services
• Audio analysis and A/V editing
• Copyright compliance and rights verification
• Interactive audio experiences in gaming, social media, and fitness

Pricing

Not stated on the website