HARQ ClearVoice vs NoiseTorch-ng
HARQ ClearVoice
harq.aiNoiseTorch-ng
github.comSide by side
| Figure | HARQ ClearVoice | NoiseTorch-ng |
|---|---|---|
| Price from | — | Free |
| Free plan | — | Yes |
| Free trial | — | — |
| Open source | — | — |
| Windows | Yes | — |
| macOS | Yes | — |
| Linux | — | Yes |
| Plans published | 1 | 1 |
| Spec score · AI Noise Cancellation Software | 7.2 (#15) | 7.4 (#11) |
| Spec score · AI Speech Enhancement Software | 6.9 (#27) | 7.2 (#24) |
| Purpose | ClearVoice provides real-time AI noise cancellation and accent neutralization on an agent’s workstation. | NoiseTorch-ng is an easy-to-use open-source application for Linux that suppresses microphone noise in real time. |
Plans
In their own words
HARQ ClearVoice
HARQ ClearVoice is paid workstation software for real-time microphone noise cancellation and accent neutralization during calls. It filters sounds such as traffic, barking dogs, and other agents before audio reaches a softphone. HARQ states that processing has 40 ms latency, runs on the CPU, and does not require a GPU. Audio remains on the workstation instead of being sent to a server, and the software can work offline. Accent neutralization is described as signal-level speech enhancement that preserves natural speech; it is not translation or text-to-speech. A virtual audio device outputs the processed signal, which the user selects as the softphone input. Named compatibility includes Talkdesk, Genesys, Five9, Avaya, and any SIP client using that device. ClearVoice is enabled as a toggle on an existing HARQ presence agent, without a separate installer. Auto-updates are included per device. Pricing is metered per device per month through an AWS Marketplace private offer, with rates supplied by sales.
NoiseTorch-ng
NoiseTorch-ng is a free, open-source Linux application that reduces microphone noise in real time. It uses RNNoise and works with PulseAudio or PipeWire, creating a virtual “Filtered Microphone” for applications such as OBS, Mumble, and Discord. The project describes setup as a two-click process and distributes the app as a small, statically linked binary. A Voice Activation Threshold can be set as high as 95%, or set to 0% to dampen noise without deactivating the microphone. Optional output filtering routes applications through a virtual “Filtered Headphones” device. Microphone filtering adds 10 ms of inherent latency; output filtering is approximately 100 ms with PulseAudio. The project reports a suspected update-server and repository breach, says no malicious code was found, and says updates are retrieved from GitHub releases. GitHub reports no SECURITY.md file or published security advisories. Troubleshooting guidance, including how to collect debug logs, is in the project wiki. The latest listed release is v0.12.2, released June 17.