TRAX Pro SP builds on the foundation of the award-winning software, ADX TRAX, to offer the first full-feature, automated speech separation software. Separate, isolate and remove melodies, vocals, speech and dialogue from full mono or stereo mixes.

TRAX Pro SP introduces a speech-optimized separation algorithm which automatically detects and separates speech, allowing you to extract or remove dialogue from background elements. TRAX Pro SP also includes a new automatic consonants detection feature to help maintain the clarity of the separated voice. We’ve also expanded the lower pitch range on separations to improve the performance of the software on deeper voices.

The addition of the speech algorithm means more creative options, so TRAX Pro SP streamlines the separation workflow with new automatic extraction options. Drop in your audio file and easily select to separate dialogue, melodic content like vocals, or both.

TRAX Pro SP adds a unique approach to spectral editing to this already powerful technology. Using our innovative, non-destructive spectral editing tools, it is now possible to further refine the results you get from the initial TRAX separation process. TRAX Pro SP is simply the most comprehensive and powerful separation tool available.

Automatic Speech Targeting

ADX Automatic Voice Activity Detection has been expanded to include speech. This is perfect for post-production professionals who need to clean up noisy elements that interfere with dialogue. It’s finally possible to adjust and fix unusable production and field recordings.

Automatic Consonants Detection

The brand new Automatic Consonants Detection algorithm automatically identifies and highlights consonants to improve audibility of hard-to-distinguish noisy consonants.

New Automatic Extraction Options

Easily select the best target for your project from the start: Speech, Melodic vocals, both, or General melody target.

Speech-Optimized Pitchogram

The new, speech-optimized Pitchogram boasts an expanded lower frequency range down to 60Hz, allowing you to target lower fundamental frequencies to better separate deeper-voiced singers and speakers. Its newly optimized display allows users to easily visualize and target both speech and melodic content like never before.