Speaker Diarization

What’s New?

Description

Speaker Diarization – automatically split mixed-speaker audio into separate tracks, right inside your DAW. Transform any mono or stereo recording into isolated speaker stems—ideal for podcasts, interviews, post-production, and research. With a single plug-in instance, Speaker Diarization uses a lightweight ONNX model to detect speaker boundaries and export per-voice files, saving you hours of manual editing. Key Features: • Real-Time Speaker Segmentation: Runs entirely in your DAW — no round-trip to external apps. Choose number of speakers from 1 to 10 and browse a WAV recording file, wait a little bit, and your speakers will be automatically splitted and exported. • Lightweight ONNX Core: Ships with a statically-linked ONNX Runtime, so there’s nothing extra to install—just drop the .vst3 into your plugin folder. • Cross-Platform Compatibility: VST3 on Windows (x64 & x86), macOS (Intel & Apple Silicon). Fully tested in Adobe Audition, REAPER, Ableton Live, Logic Pro, Cubase, Audacity, and more • Zero Dependencies, Zero Crashes: Built with static linking to guarantee rock-solid performance and eliminate “missing DLL” nightmares. How It Works: 1. Open the Speaker Diarization plug-in in your DAW program. 2. Browse your recording in WAV format and choose number of speakers inside the recording. 3. Adjust sensitivity, minimum segment length, or expected speaker count. 4. Export speakers automatically in root folder. What’s Included: • SpeakerDiarization.vst3 (x86, x64, arm64) • ONNX model (.onnx) pre-optimized for real-time • Lifetime license with free minor updates Licensing & Support: • Perpetual License: Purchase once, use forever Take your podcast, interview, and post-production workflow to the next level. Buy Speaker Diarization now and stop manually chopping audio—let AI do the hard work!