Krisp Voice Isolation vs Sharpi
Krisp Voice Isolation
krisp.ai
Sharpi
augmentedhearing.ioSide by side
| Figure | Krisp Voice Isolation | Sharpi |
|---|---|---|
| Price from | — | — |
| Free plan | — | — |
| Free trial | Yes | — |
| Open source | — | — |
| Web | Yes | — |
| Windows | Yes | Yes |
| macOS | Yes | — |
| Linux | Yes | — |
| iOS | Yes | — |
| Android | Yes | — |
| API | Yes | — |
| Self-hosted | — | Yes |
| Plans published | 2 | 1 |
| Spec score · AI Voice Isolators | 7.8 (#10) | 6.8 (#21) |
| Company | Krisp's site identifies the company as Krisp Technologies, Inc. and lists its address in Berkeley, California. | Augmented Hearing says its founders began developing the idea in 2015, drawing on experience in the Danish audio industry and research at the Technical University of Denmark. |
| Deployment | VIVA runs server-side on-premises or in a customer's cloud and is designed to sit before the speech-to-text engine. | Sharpi is offered as a Windows app, a physical on-premises box, a SIP Bridge, and embedded solutions. |
| Integrations | Krisp lists LiveKit, Pipecat, and raw WebRTC pipelines as supported integrations, and says the SDK works with any STT engine. | The SIP Bridge uses standard SIP/RTP interfaces and supports SIP-based telephony systems without vendor-specific extensions. |
| Support | The Enterprise developer plan includes dedicated engineering support and custom SLAs. | The maker offers sales and engineering consultations to help select and integrate a deployment. |
Plans
Krisp Voice Isolation
- Early stagePriced on request
- EnterprisePriced on request
In their own words
Krisp Voice Isolation
Krisp Voice Isolation is a real-time voice model in Krisp VIVA, infrastructure for voice AI agents. It separates a main speaker from other voices, background chatter, and room echo before audio reaches speech-to-text processing. Krisp says Voice Isolation 2.5 runs on CPU with 15 ms latency and reduced word errors by 46% in its benchmark. The VIVA SDK also includes Turn Prediction, Interruption Prediction, Voice Activity Detection, and detectors for accent, gender, and synthetic speech. It runs server-side on premises or in a customer's cloud, ahead of the speech-to-text engine, and is designed to work with any STT engine. Listed integrations include LiveKit, Pipecat, and raw WebRTC pipelines. SDKs are listed for Python, Node.js, Go, and iOS; input and output are PCM S16LE, 16 kHz mono. The broader AI Voice SDK library supports Windows, Mac, Linux, web, iOS, and Android.