Accusonus releases ERA Voice Leveler, a single-knob software tool that automatically detects and fixes audio level inconsistencies
Magix Audio has a plug-in to Sound Forge Pro for the Mac and iZotope’s RX 6 and 7 Advanced audio editors include a module called “Leveler”. Both allow you to correct audio levels, and now Accusonus has such a module too.
Accusonus develops audio software tools that are based on machine learning algorithms. The company has released the ERA Voice Leveler, which is a single-knob sound leveller using new patent-pending algorithms to automatically detect distracting level differences in voice recordings and correct them in real-time.
While Sound Forge Pro for the Mac does a good job of cranking up the volume across the timeline of a recording without introducing signal clipping, it depends on the included RX Elements plug-in module to let you delve deeper into audio levelling.
In contrast, the ERA Voice Leveler lets you adjust gain automatically by turning the knob – without leaving your DAW or NLE environment – with the AI touted as capable of fixing vocal and dialogue volume problems including moving speakers, recording two or more speakers with a single microphone (e.g. interviews, lectures, etc), sudden gain changes due to audio/video edits and re-arrangements in post-production and time-varying voice-overs.
The ERA Voice Leveler lets you control the fix with the turn of a dial. It also features a “Tight” mode that provides a more focused sound for standing out against background music. The “Emphasis” mode is said to automatically detect problems in tonal balance of voice recordings (for example when a speaker is not directly facing the microphone or has moved significantly from the mic between takes/scenes) and apply subtle processing to correct them and ensure consistent tone and intelligibility.
The product is targeted at uniquely tackling those problems. However, that is also its weakness as these problems usually occur together with others. For example, RX 7 Advanced applies iZotope’s machine-learning algorithm to a whole range of problems in the form of a Repair Assistant. Tests with it revealed that RX uses three or more of its dedicated dialogue modules to fix bad voice recordings with the Leveler module being only one of them.
To accomplish the same, you’ll need to buy the ERA Bundle Standard or the ERA Bundle Pro and those don’t come with an intelligent assistant that combines all corrections into one window with three different recommendations to choose from.
Nevertheless, I downloaded the trial and did a quick comparison between the RX 7 Advanced Leveler and the ERA Voice Leveler and found that the iZotope’s tool made the dialogue sound louder without introducing artefacts, even when pushing it close to clipping. The ERA Voice Leveler did a good job until I pushed it. That produced some irritating crackling noise that wasn’t there originally. It also sounded somewhat thinner than the original or the RX processed one.
Still, you can get your hands on the ERA Bundle Standard (Noise Remover, Reverb Remover, Voice Leveler, De-Esser, Plosive Remover) at an intro price of $119 (Reg: $354) until October 31st. The ERA Bundle Pro (Noise Remover, Reverb Remover, Voice Leveler, De-Esser, Plosive Remover, ERA-D) has an intro price of $349 (Reg: $653) until October 31st and ERA Voice Leveler is $59.