Good day, and welcome to the SoundHound Second Quarter 2023 Earnings Conference Call. At this time, all participants are in a listen-only mode. After the speakers' presentation, there will be a question-and-answer session. [Operator Instructions] Please be advised that today's conference is being recorded. I would now like to hand the conference over to your speaker, Mr. Scott Smith, Head of Investor Relations. The floor is yours, sir.

Good afternoon and thank you for joining our second quarter 2023 conference call. With me today is our CEO, Keyvan Mohajer; and our CFO, Nitesh Sharan. We will begin with some short remarks before moving to Q&A. We'd also like to remind everyone that we'll be making forward-looking statements on this call. Actual results could differ materially from those suggested by our forward-looking statements. Please refer to our filings with the SEC for a detailed discussion of the risks and uncertainties that could affect our business and for discussion statements that qualify as forward-looking statements. In addition, we may discuss certain non-GAAP measures. Please refer to today's press release for more detailed financial results and further details on the definitions, limitations and uses of those measures and reconciliations from GAAP to non-GAAP. Also note that the forward-looking statements on this call are based on information available to us as of today's date. We undertake no obligation to update any forward-looking statements, except as required by law. Finally, this call is being audio webcast in its entirety on our Investor Relations website. An audio replay will be available shortly following today's call. With that, I'd like to turn the call over to our CEO, Keyvan Mohajer. Please go ahead, Keyvan.

Thank you, Scott, and thank you to everyone for joining the call today. In Q2, we started our second year as a public company. With our first full year coming to an end, we are happy to have reported over 80% revenue growth on a trailing 12-month basis. We ramped up our innovation cycle and at the same time, gained efficiencies across the Company as seen in the 50% year-over-year adjusted EBITDA improvement in Q2. Over the years, we've demonstrated our track record as a leading innovator in AI. This is one of the main reasons we've been able to attract strategic investors like NVIDIA, Samsung, Tencent, Hyundai, Naver, HTC, VIZIO, Foxconn, Oracle and others. While some organizations have spent billions of dollars trying to build voice and conversational AI technologies in-house, we were able to do that with a fraction of that investment with our creative innovation and focused dedication. As a result, our voice AI-powered millions of cars, TVs, apps and IoT devices, generating billions of successful user interactions each year. Because of our root in deep science, over the years, we've created groundbreaking advancements in voice AI from Speech-to-Meaning, Deep Meaning Understanding, Collective AI, Dynamic Interaction and our CaiLANCaiNET framework and globalize them in dozens of languages. As an example of another recent innovation, we introduced SoundHound Chat AI for automotives. This combines our proprietary voice AI with the latest generative AI built from large language models. In our view, SoundHound Chat AI is completely unique in the industry and no one else can claim this type of progress. Within a short time frame, several of our existing customers have started piloting the solution in their products and we've received proposal requests from new brands. We expect the increased performance resulting from SoundHound Chat AI will result…

Thank you, Keyvan, and good afternoon, everyone. We are pleased to report another strong quarter and solid first six months of the year with 48% year-over-year top line growth and a 75% gross margin, all while significantly reducing our operating loss. We have also vastly improved our cash position and closed the quarter with total cash of approximately $130 million. The accelerants and AI continue to expand our sales opportunities with existing customers and catalyze new customer interest. These new opportunities have only further validated our long-term vision to voice enable the world by bringing together billions of voice-enabled products and services and unleashing the flywheel of their interconnectivity and new monetization streams. This is the essence of the three-pillar business model we have described before; product royalties, service subscriptions and monetization. This quarter, we ended with $339 million in cumulative bookings backlog, up 20% year-over-year. To reiterate, our bookings are derived from committed customer contracts and reflect expected revenue to be realized from those contracts over its life. These contracts can have minimum guarantees or include work completed, but amortized revenue not yet recognized due to ASC 606 rules. And in many case, they include customer estimates of volumes for auto or device shipments, for example, generally supported by historical benchmarks. The cumulative bookings goes up as new deals are signed or if existing customers extend and goes down as revenue is recognized. As we have discussed previously, cumulative bookings backlog growth can be uneven given the scale of our enterprise customers relative to us. We've added customers across industries such as in telecommunications, printers and TVs to name a few. Including automotive, we have long-term contracts spanning up to 8.5 years with an average contract length of roughly 6.5 years. And as I've stated before, these are back-end…

Thank you. [Operator Instructions] And our first question will come from the line of Mike Latimore with Northland Capital Markets.

Congrats on the strong results here. In terms of the second half outlook, we should think about that as largely driven by license deals out of backlog? Is that still the key kind of second half driver?

Mike, I think it will come from Pillar 1 activity, a lot of backlog, but also some new deals, potentials that I mentioned are sort of in motion. So, we do continue to see great traction in the Pillar 2. As I articulated, there's -- we're building sort of our ARR pipe. But as I think you're alluding to, as those really end up being monthly recurring. So, those will build and be consistent over time. But as we keep adding more and more restaurants, that's going to be increasingly a 2024 and out story. So yes, I mean we have -- and I think I mentioned in the prepared remarks, there's been a seasonality that comes with our business, particularly with respect to autos and just the trending of vehicle shipments and so forth. So, it's a composition of a few different things, but I think that's kind of the mix.

And I might have missed it, but did you say whether OpEx should trend down a little bit from here? Or is this a good kind of run rate level?

It's -- yes, probably generally a good run rate level. What I'd say is we took most of those restructuring actions in Q1 itself. There was a little bit of restructuring expense in Q2 but largely complete. At this point, we feel like we're largely in the right place. We are being thoughtful about areas where things are moving around pretty quickly. So, where we need to be concerted about driving additional investments, we're not going to shy from doing that. Again, maintaining our commitment to getting to the right place on profitability. So, in a couple of pockets, we're making shifts, in a couple of places we're moving away from. So, I'd say, by and large, yes, it's appropriate to kind of think of it as this is a good level and it really kind of comes to scaling revenue.

And just last one. Great to see the White Castle expansion. Can you talk a little bit about the ROI they saw in initial launch? And then I guess it's going to roll out over 1.5 years. I'm assuming it was a good ROI. So, why wouldn't they roll out a little faster? I think you guys can kind of deploy faster than that, but...

Yes, the 100 number is by the end of next year, but it's not -- it's actually happening already quite fast. So, we are in multiple locations and they have an aggressive target to add more and more. It's just that drive-thru requires some hardware upgrade and it's not just a swap out of software, so that takes a bit of time. On your earlier question, they had a key metric that they were looking for in terms of order completion rate. That is correct. And we by far exceeded the number that they were looking for and we surpassed their human order takers. So, they're very happy with the partnership.

And by the way, on return, Mike, there's obviously labor cost benefits of utilizing AI. There is the opportunity to have upsell, which could generate revenue. There's consistency of service. I think in our press release, we commented it's 24/7. So, coverage over for a place that does operate 24/7, that's meaningful. You don't get deterioration of performance because you're tired if you're AI as an example. So, multiple things from an ROI perspective, I think, are very attractive to these restaurants.

[Operator Instructions] And that will come from the line of Brett Knoblauch with Cantor Fitzgerald.

I guess the first one, I think we look at like other AI companies in the market who are kind of training models and they're spending a lot of money on CapEx in this build-out. And I guess when we look at kind of your guys CapEx, it's quite minimal. So, can you maybe remind us why maybe you don't need the capital intensity of some of the other AI businesses that are trying to acquire compute and whatnot?

Well, we have been training models for over 10 years. So, some of that has accumulated. So, we have both AI models in dozens of languages. So, some of it is reflected in that. But yes, we have become very efficient in the way we train models and reducing cost. And also we have scale already with traffic that we have to serve with our real -- we process billions of queries and we are being smart about utilizing our capacity when the same hardware is not being used to serve the production traffic. So, we are trying to not have additional expenses to train large models beyond what we have already allocated going forward.

And Brett, as we've talked about before, we've migrated cloud providers. We utilize Oracle OCI and we have a great partnership there that gives us access to GPUs and all the kind of technologies that we need to be able to train our models. So, sort of in the business model already.

And then I guess now that you guys have like ample liquidity, what's going to be the investment strategy as it relates to building out your go-to-market strategy. This has historically been an area where you haven't invested much as you guys kind of been an R&D-focused or product-led company. So, I guess can you just maybe explain like what your vision is for what your go-to-market strategy would look like?

Yes, certainly. So, it depends on the pillar. On Pillar 1, we built a real great set of partnerships and customer base and with really just a handful of business development resources and that was kind of our history dating back many, many years, and it was on the foundation of great technology, differentiated technology in the marketplace, our capacity to work flexibly and with a lot of agility and scale. And so that was sort of, I think we'll continue to grow. We leverage channel partnerships. We mentioned Qualcomm example an opportunity to leverage a great partner, embed the voice AI with Snapdragon chip and get access. There's other partners. When we talk to Pillar 2, it's a little bit of a mix between direct go-to-market motion as well as channel partners. So, we have our own sales team. We've been growing. They're very active in engaging with small, medium enterprises, but also regional mid-market and going to conferences, getting our Dynamic Interaction technology in front of people because as Keyvan mentioned in the prepared remarks, when we get that out there, people see it, they're wow-ed, they really want to -- they want to keep the conversations going. But we supplement that and really complement that and get a lot of scale with channel partners. So, we've talked about how we can now integrate with Toast, Square, Oracle, Olo, we're adding others. And those are great because take Toast as an example. I believe they have 1,100 sales reps that we've been -- we trained the sales reps before to kind of showcase our technology, how we can integrate with them, and that just gives us greater reach. So that's sort of what we're doing on the go-to-market motion. I will say you're right, we are feeling great about where we are from the capital perspective and it's really around execution and going out and continuing to get scale and ways that we can just quickly get large enterprise franchises are interesting to us and we'll continue to look at both direct and indirect ways of accessing those customers.

And then for your full year guide, I guess, do you need any like one-time license or big one-time license deals for you to reach that midpoint? Or do you think that can come just from increased usage or inquiries from product royalties?

We do different -- in our licensing, there's sort of a royalty scaling. And then we do have one-time NREs from time we do various deals. We do professional services engagement. So that's all part of the contemplation. I don't know that I can break that up too much other than just scaling in units at the pace we're going, that gets you part of the way. But yes, I mean we need to do some other deals in that, but that's part of our overall motion as we work. If we have to do upfront custom development work, then we get that. And if we complete that within a certain period of time, we recognize it. If the performance obligation is longer, we amortize it. So, some of it is the rollout and some of it is we got to go do deals. We've got a lot of deals in motion. And I think I mentioned, especially with the generative AI stuff, there's just a lot more interesting conversations going on. But those are large deals and the timing is not always perfect. So, we're going to keep hammering away at those and showcase to you guys in future quarters what we've been able to accomplish.

And then maybe if I could just ask one more. I guess you guys said the auto units were up 60% year-over-year. Pricing was also up year-over-year. So, I guess if I'm looking at product royalty revenue, which is $5.5 million last year, if I assume that grew 60% or just 60%, that gets me to a number that's more than the revenue delivered in the quarter. So I guess, what am I missing from that equation in terms of units and pricing that kind of gets me to like where you guys are at for this quarter's revenue?

Yes. When we -- what I conveyed in the prepared remarks was around units and unit activity, which generally on our revenue recognition. As we get a royalty report, we invoice off the royalty report, we recognize that revenue. Revenue is also make comprised of previously completed NRE work that might amortize over the life of the support agreement, could also include professional services. So for example, on a year-over-year comp, that's included in the prior year number, last year, we had announced sort of we had one particular customer in Europe, an auto customer that we did some engineering work, and that was, I think, particularly related to like language deployments and some engineering work that we had to complete. So, those aren't necessarily related to shipments. So, you have to sort of adjust for those things. That's why I try to give the double click of like what's actually going on the ground with units that are shipped because there can't be that type of engineering numbers that they're playing out and I don't want to say reeking. They're just changing the numbers. So that's a reflection in our prior year numbers.

Thank you. As I'm showing no further questions in the queue at this time, this concludes today's program. Thank you all for participating. You may now disconnect.