Full Description
View Full Description
AI-Powered Clean-Up (Noise & Reverb)
VoiceAssist uses locally running AI models to reduce background noise and room reverb without stripping character from the voice. Traffic rumble, fan noise, reflections, and headphone bleed are intelligently identified and reduced, giving you a cleaner, drier signal to work with. This is especially useful when recordings come from untreated rooms or mobile setups. By starting with a more controlled vocal, you spend less time fixing problems and more time shaping tone and performance.
Recover Highs and restore the clarity
Dull or muddy recordings are often the result of poor mic placement or poor recording setups. VoiceAssist includes the Recover module to analyse the signal and rebuild missing high-frequency detail, restoring presence and intelligibility. It helps rescue takes that might otherwise feel flat, bringing vocals forward in the mix without harsh EQ boosts. The result is a clearer, more balanced sound that translates well across different playback systems.
Intelligent dynamics and levelling
VoiceAssist analyses vocal performances and writes custom volume automation based on your chosen settings. You can aim for subtle, transparent level riding or firmer control for spoken word and dialogue. Support for LUFS-I and LUFS-S workflows makes it easy to hit consistent loudness targets, while integrated peak control avoids over-compression. Levels stay even and natural, with far less need for manual automation or heavy dynamics processing.
Breath Detection & Control
Breaths are detected automatically and displayed as editable regions within the timeline. Reduce them globally for speed, or fine-tune individual breaths to preserve phrasing and realism. This makes it easy to clean up distracting inhales without flattening the performance. Everything remains adjustable, so you can strike the right balance between polish and natural delivery.
Sibilance Detection & Processing
Harsh sibilance is identified intelligently and can be controlled using either volume-based or spectral processing. Each sibilant remains fully editable, allowing precise adjustments where needed. Compared to traditional de-essers, this approach offers greater transparency and control, smoothing “S” sounds without dulling the vocal or introducing unwanted artefacts.
Fully Editable, Non-Destructive Workflow
All detected elements — breaths, sibilance, and dynamics — remain editable at every stage. You can add, remove, resize, or adjust regions freely, and manual edits are never overwritten by re-analysis. This non-destructive approach keeps you firmly in control, letting VoiceAssist handle repetitive tasks while you make the creative decisions.
Content-Aware Gate
The content-aware gate responds to voice activity rather than relying on a fixed threshold, reducing unnatural cuts and over-processing. It adapts well to changing mic positions, comped takes, and uneven performances. For full manual control, a traditional threshold-based mode is also available. The result is cleaner silences with fewer artefacts in real-world recording scenarios.
ARA Integration for Seamless Editing
In supported DAWs, VoiceAssist integrates via ARA directly into the timeline. Edits stay perfectly in sync with your session and move naturally with the audio. This provides a clearer overview and a faster, more intuitive editing experience that feels like part of your DAW rather than an external process.
Who is VoiceAssist for?
VoiceAssist is made for anyone working with vocals & dialogue, whether professionally or as a hobby. It’s perfect for those who want to spend less time on technical cleanup and more time focusing on the creative side of their work. By taking voice editing to the next level, VoiceAssist is a powerful assistant for: Editing podcasts, audiobooks, vocal tracks for songs or any kind of dialogue.
If you work with voice, VoiceAssist will save you time and help you achieve high-quality results. It gives you a clean and consistent starting point, no matter what kind of recording you're working with.
Features
- AI-powered clean to remove noise and reverb to get a clean and dry sound, even when the recording environment isn’t acoustically treated
- Clarity module recovers the high frequencies to improve presence and clarity
- Automatically analyses the vocal track and creates custom automation, based on your settings, to maintain a perfect level
- Supports LUFS-I and LUFS-S workflows with integrated peak controls
- Automated Breath control module displays breaths in the audio as editable sections to reduce globally or fine-tune individual breaths with precision
- Intelligent detection of sibilance which can be processed globally or independently using either volume-based or spectral-based reduction
- Edits are never overwritten, offering a non-destructive workflow to adjust breaths, sibilance and dynamics freely and make changes when needed
- Content-aware gate module dynamically reacts to vocal input, listening to the audio and silence instead of hitting a fixed threshold, preventing over-processing and unnatural cuts
- ARA integration offers seamless editing in supported DAWs
- Includes standalone application to process audio independently before importing back into your projects
- Runs 100% locally on your machine, meaning no audio is processed in the cloud
Specifications
- Operating system:
- Mac: macOS OS 12.0 + (Apple Silicon Support only)
- Windows: Windows 10 +
- Format: AU, VST, AAX
- Compatibility: Standalone, ARA
- Supported ARA DAWs: Pro Tools 2024.10+, Studio One, Luna Pro, Reaper, Cubase, Nuendo, Logic Pro (Intel & Apple Silicon via Rosetta)
- Graphics: NVIDIA / AMD dedicated graphics cards required – Integrated Graphics not supported
- Product code: 1246-4261
