At Krisp, we\u2019ve spent years building category-defining Voice AI technology that enhances human voices in real time. Since our founding in 2017, our focus on technical excellence and product quality has made us the leader in voice AI productivity tools.<\/p>\n
<\/p>\n
Recently, Sanas filed a lawsuit against Krisp. While we prefer to compete in the marketplace, we will not let this attempt to distort the facts and assail our reputation go unanswered.<\/p>\n
<\/p>\n
Let\u2019s set the record straight.<\/strong><\/p>\n <\/p>\n 1. The 2022 Sanas meetings went nowhere \u2014 and for good reason.<\/strong><\/p>\n Krisp met with Sanas under NDA in 2022, but those discussions were brief and unproductive. Sanas demonstrated an early version of its product, which lacked maturity and failed to meet our expectations. The company was vague, unresponsive to basic technical questions, and did not share any information that could remotely be considered a trade secret. Ultimately, there was no trust or alignment \u2014 and no basis for collaboration.<\/p>\n <\/p>\n 2. We walked away, citing product limitations and a lack of alignment.<\/strong><\/p>\n Based on Sanas\u2019s demonstration of the technology our conclusion was that Sanas\u2019 technology had very limited technical capabilities and obvious drawbacks. We made a clear decision not to move forward with Sanas. Our reasons were straightforward: we saw limited technology performance and integration visibility, and misalignment in business communication from Sanas.<\/p>\n <\/p>\n These factors made clear that a partnership with Sanas would not meet Krisp\u2019s standards or goals.<\/p>\n <\/p>\n 3. We built something fundamentally better.<\/strong><\/p>\n Accent conversion has always been part of Krisp\u2019s technology roadmap. With no viable market alternative, Krisp\u2019s world-class Voice AI team drew on its pioneering work in noise cancellation, background-voice isolation, emotion conversion, and other proprietary technologies to create a best-in-class accent conversion technology.<\/p>\n <\/p>\n We place a strong focus on solving the accent conversion problem offline with high fidelity and close retention of the original voice of the speaker. Once this version of the problem is settled, a new architecture, specifically designed for low-CPU footprint and real-time application, performs accent conversion, based, among other things, on the solution of the offline problem.\u00a0 A key component in the design of this architecture is the ability of retaining acoustic details of the input, allowing smooth and natural flow of the converted voice. Our design does not rely on specialized alignment modules, which are key components in Sanas’s patents. This critical difference is the key reason Krisp outperforms Sanas.<\/p>\n <\/p>\n We didn\u2019t use Sanas\u2019 technology \u2014 we far surpassed it.\u00a0 And now, as part of its lawsuit, Sanas is trying to claim rights to Krisp\u2019s technology, which Krisp independently developed and secured at great cost and effort.\u00a0 While Sanas would certainly benefit from copying Krisp\u2019s technology, its efforts to forcibly take Krisp\u2019s patent rights are completely baseless.<\/p>\n <\/p>\n