SoundHound AI Q2 2023 Earnings Call Transcript

There are 8 speakers on the call.

Operator

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 speaker presentation, there will be a question and answer session. You will then hear an automated message advising your hand is raised. Please be advised that today's conference is being recorded.

Operator

I would now like to hand the conference over to your speaker, Mr. Scott Smith, Head of Investor Relations. The floor is yours, sir.

Speaker 1

Good afternoon, and thank you for joining our Q2 2023 conference call. With me today is our CEO, Kevan Mahajar and our CFO, Nitesh Sharan. We'll begin with some short remarks before moving to Q and 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.

Speaker 1

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.

Speaker 1

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, Kevan Mahajer. Please go ahead, Kevan.

Speaker 2

Thank you, Scott, and thank you to everyone for joining the call today. In Q2, we started our 2nd year as a public company. With our 1st full year coming to an end, we are happy to have reported over 80% revenue growth on a trailing 12 month basis. We've 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.

Speaker 2

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 1,000,000,000 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 roots in deep science, over the years, we've created groundbreaking advancements in voice AI from speech to meaning, Keep meaning understanding, collective AI, dynamic interaction and our Kailan Kinetics framework and globalize them in dozens of languages. As an example of another recent innovation, we introduced Samhan Chat AI for Automotive.

Speaker 2

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 Please type off progress. Within a short timeframe, 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 We'll result in faster adoption, better user experience, more frequent usage and ultimately more revenue per device from our Pillar 1 category of automotive and IoT customers. In a recent pilot conducted by one of our key customers, the usage increased by an order of magnitude after enabling the features.

Speaker 2

We expect adoption of our chat AI platform from some of our customers as early as this year. In Pillar 2, which offers conversational AI for customer service solutions, our smart ordering continues to benefit from our unique technology advantage Handling complex and compound queries, which is especially important in food ordering conversations over the phone. In the last quarter, we were able to further improve our solution by applying our generative AI integration, really taking it to the next level. Now I'd like to play a sample dialogue with our next generation of smart ordering AI that is rolling out in the coming weeks to our existing and new restaurant customers.

Speaker 3

What can I get for you?

Speaker 4

Hi. I'm calling to place an order. My daughter is 3 years old and she's a picky eater. Do you have any recommendations for her?

Speaker 3

Of course. For your picky eater, I would recommend our kids' mac and cheese. It's a classic favorite among children. We also have kids' chicken fingers and kids' grilled cheese if she prefers those options. Let me know if you need any more information or if you'd like

Speaker 4

Yes. Can I get the kids' mac and cheese with apple juice and yogurt?

Speaker 3

I've added a kids mac and cheese with apple juice and yogurt to your order. Can I get you anything else?

Speaker 4

Yes. I was there last We had one of those cheeseburgers that was really good. I don't remember what you call it. It was something like traditional Or actually classic, yeah, classic, can I get one of those with cheddar cheese?

Speaker 3

Sure. I've added a classic cheeseburger with cheddar to your order. What else can I get you?

Speaker 4

That's all. Thank you so much.

Speaker 2

Most recently, we are excited to have launched our low touch out of the box AI customer service solution, SmartAnswering, which will be formally announced soon. With SmartAnswering, we expand our AI customer service offering from just restaurants to any business, Even a single location barbershop that can benefit from Samhain's AI customer service. Here's a short demo of smart answering with the barbershop.

Speaker 3

Thank you for calling Smith Brothers Luxury Grooming Salon for men. This call is recorded and if you need privacy info, just ask. How can I help you today?

Speaker 4

Yes. Hi. I wanted to surprise my daughter who loves the new Barbie movie by dyeing my hair blonde like Ken. Is that something you guys do?

Speaker 3

Yes. We offer hair coloring for men at Smith Brothers Salon. The cost starts from $2.50 Is there anything else I can help you with today?

Speaker 4

Well, honestly, I've never colored my hair. So I don't really know how it would react. I was wondering if I could schedule something just to ask a few questions and get some advice.

Speaker 3

Great. We offer professional consultations for hair coloring. You can easily make an appointment on our website. Would you like me to text you a link to make it easy for you?

Speaker 4

Sure. That sounds great.

Speaker 3

Okay. I have sent the link to you. Is there anything else I can help you with today?

Speaker 4

Do you have any advice on how to get there? Should I drive or take public transit?

Speaker 3

To get to Smith Brothers Salon via public transit, you can take the Brown Line to Addison Station, which is a 5 minute walk from our location. If you decide to drive, we don't have any dedicated But there is usually street parking available on Lincoln Avenue. Is there anything else I can help you with today?

Speaker 4

Well, actually, yes. Do you allow dogs?

Speaker 3

Yes. We allow dogs in our salon. If you'd like to learn more about our pet policy, I'd be happy to text you a link to our website where you can read additional details. Would you like me to do that now?

Speaker 4

Well, the problem is that my new dog is a rescue and she gets a bit rowdy when around other dogs. I want her to get used to going out, But it's best that there aren't any other dogs in the salon at the same time. Is it possible to figure out a time when that would work?

Speaker 3

Okay. I will pass along a message to owner Jared Smith, so that he can be in touch with you via text to discuss arranging a time when no other dogs will be present. Is there anything else I can help you with today?

Speaker 4

No, that's it.

Speaker 3

Thanks for thinking of us for your hair coloring needs. Have a great day. Goodbye. Awesome. Thanks.

Speaker 3

Take care.

Speaker 2

These were examples of our AI customer service solutions that are fully autonomous And a key differentiator for SoundCloud, separating us from other vendors that use a human in the background when users engage with their AI offering. As compared to human centric low margin call center solutions, our fully autonomous solution is affordable and can attract brands of all sizes, Whether the brand has a single location or thousands of locations. When a caller interacts with our AI, They're only interacting with AI and there is no human involvement. If a caller specifically asked to talk to a human, usually at the beginning of the call, Our merchants have the option to receive the call directly or forward to an agent. For example, using the last week of July, About 93% of orders placed with our smart ordering solution were handled by AI and only 7% were prompt transfers.

Speaker 2

We expect the rate of these transfers to decrease over time as callers become more comfortable and confident speaking to an AI. In fact, We expect the callers will ultimately prefer to speak to an AI instead of a human. Our AI is also always learning both generically and specific to a merchant. After going live with a merchant, our AI capabilities and accuracy improve as it learns to interact with users With this technology, we believe we can unlock long term value for businesses. We've heard from restaurants loud and clear.

Speaker 2

We are hungry for this type of automation as it directly creates financial returns by addressing labor shortages, Overall cost pressures and help them generate revenue. We are deeply engaged with thousands of brands and have already closed with hundreds of them, thanks to our direct sales And strong channel partner ecosystem, including Toast, Square, Oracle and Ollo. Last week, we announced that we are significantly expanding Our relationship with White Castle, where they've committed to provide AI covered ordering to 100 drug through lanes by the end of 2024. And because our products are designed to be scalable, we can address a wide variety of restaurants across a diverse array of cuisines and different sizes. For example, we are also delighted to be providing voice AI technology to Beef O'Brady's, which is a part of FSC Franchise Co, a restaurant company with multiple brands That span 25 states and more than 180 locations.

Speaker 2

And you're adding more customers every day. For instance, neither's bakeries, Hot Table, Naza's Halal, Slim and Husky's, Krust Pizza, Kimori Sushi, Noe Thai, Ozellis Italian and Darla Cafe among hundreds of others. Note especially the diversity of cuisine types and brand sizes, which give us access to a larger market share than vendors that Due to technology and scale limitations, we need to focus on just enterprise customers or specific cuisines. And with SmartAnswering, we're just getting started, Allowing any business to handle nearly any inbound customer inquiry using automated and customizable voice assistant. Using generative AI to automatically incorporate data from the business website in its AI knowledge base, Smart Answering provides quick and easy onboarding, allowing the customers to test it out within minutes and be live on the same day.

Speaker 2

The service can handle multiple calls at once 20 fourseven And conveniently filters out spam calls, saving hours of wasted time for any business. It can also provide convenient SMS responses in addition to verbal answers and can seamlessly transfer to any employee of the business if necessary. Smart ordering and smart answering are Complemented by our visually enhanced sound hand dynamic interaction, which is our multimodal full duplex interface for kiosk, drive through or any device with a screen. Dynamic interaction is unmatched as a breakthrough and we believe will mark the next generation of digital assistants and AI interfaces, which allows input via speech or touch and provides real time responses via visual and audio with no turn taking or wait for it. I encourage everyone to visit our website and watch the demo of Dynamic Interaction.

Speaker 2

We consistently get a wow response anytime someone is introduced with product For the first time, when we attended the National Restaurant Association Conference this year, Dynamic Interaction stole the show. Trade Media selected Dynamic Interaction as one of the top things to see on the show floor among all vendors in all categories, so not just technology. A typical reaction from our target customers is not just if they're interested in handheld dynamic interaction, But how can we go live with this as fast as possible? We are already working with a number of potential customers, including a Fast growing large franchisor that operates in 30 states and we plan to start rolling out dynamic interactions in the coming weeks. While we're excited about our Pillar 2 business, there is more to share in our Pillar 1 category, where we power products such as cars, TVs and IoT devices.

Speaker 2

This has been a critical part of our business since launching our voice AI platform in 2016. In particular, growth in the automotive industry requires long term investments, Global reach and it's difficult to penetrate. Thanks to our track record and differentiated technology, we continue to expand into our large customer base of about 20 brands including Hyundai and Stellantis as well as initiate production with new companies such as TOG, a transformational Turkish electric car manufacturer. Overall, we are seeing expansion of usage in our categories, seeing more inquiries with the device that we power, which have increased our annual run rate to over 2,800,000,000. This frequency of usage increases, the performance of our AI systems will continue to get even better and more intuitive as they learn from the new data and large amounts of existing data.

Speaker 2

Our extensive experience and data so far have already fine tuned our machine learning tools To make our products highly valuable to businesses and more useful to users, we now predict faster adoption, new kinds of use cases and ultimately more revenue per device. Our strategic channel partnerships are also generating momentum. For example, Qualcomm has integrated FanHand voice AI on its chipset With the Snapdragon digital chassis and is showcasing it on the concept vehicle. These types of channel partnerships are critical in developing growth in the automotive industry. I also wanted to specifically call out the traction we are seeing in TVs, where we've increased the usage by over 80% compared to this time last year.

Speaker 2

Last quarter, we discussed a new revolutionary television manufacturer we signed. They entered the market with our technology in Q2, And you will hear more about them later this year. This should drive further usage of our technology in a space where we believe there is significant opportunity. For IoT, we have also either signed, extended or gone into production with multiple brands such as robots, printers, coffee machines and kiosks. And we are collaborating with a large home automation IoT company and one of the largest telcos in the U.

Speaker 2

S. As I mentioned earlier, With the launch of Tanhansha AR for Automotive, we created a number of off sell opportunities and we are in conversation with the majority of our automotive customers as well as quickly gaining interest from new major brands. We continue to see a surge in enthusiasm for AI, which has brought Samhain significant interest from customers and AI followers. We believe the new AI disruption that is catalyzed by generative AI We'll have a larger impact in nearly all industries than the last mobile disruption. We believe Townhounds is uniquely positioned to achieve significant long term success In the new AI era, given our deep voice and conversational AI expertise, robust patent portfolio, full technology stack And our years of collaborating with major brands within key industries, including automotive, smart devices and now customer service.

Speaker 2

In line with our track record as a leading innovator in AI, Sangham is training its own foundational model in generative AI. But our approach is different. Instead of yet another large language model, we are combining everything you've learned in nearly 2 decades To take it to the next level, our foundational model will be multimodal, supporting audio and text input And audio and text output with prompt based instant customization capabilities that used to take significant software engineering and machine learning to achieve. We'll focus on features that we know will change the equation in the numerous applications we are building. We'll be able to use billions of real conversation and over a 1000000 hours of audio data in dozens of languages that we've so carefully accumulated over the years.

Speaker 2

The amount and highly relevant nature of this data gives Sandhounds a unique advantage. Our internal name for this foundational model is Polaris, Matching our ambition to create the brightest star in the constellation of foundational models. You will have more to share about Polaris soon. We have an amazing and passionate team that makes all this possible. I want to thank them for their tireless efforts To get us to where we are today and for playing a lead role in harnessing the technology at the heart of one of the biggest disruptions in history and making it practical and real.

Speaker 2

In closing, we are innovating faster than ever. We are growing. We are on our way to profitability and have significantly increased our cash position. We have the core voice and conversational AI technology built from the ground up, which gives us distinct competitive advantage to maintain our leadership position And further add to the AI disruption that will make the world a better place and create tremendous value. With that, I'll now turn the call over to Nitesh to talk about our financial performance, key growth drivers and full year outlook in more detail.

Speaker 5

Thank you, Kevan, and good afternoon, everyone. We are pleased to report another strong quarter and solid 1st 6 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 $130,000,000 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 3 pillar business model we have described before: Product royalties, service subscriptions and monetization.

Speaker 5

This quarter, we ended with $339,000,000 And 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 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 the industries such as in telecommunications, And as I've stated before, these are back end weighted.

Speaker 5

In Pillar 1, where we voice enabled products, we continue to extend our offering across new units, while adding more features. In autos, which represents the majority of this pillar, we increased our new units by 60% And our active cloud users increased by close to 70% versus prior year. Within pillar 2, where we voice enabled services, We are expanding our offering beyond restaurants to a much broader customer base with SmartAnswering. Although it's very early because of the more streamlined onboarding, we are very encouraged And with how quickly this can build. For restaurants, our smart ordering solution is beginning to solidify a strong subscription base.

Speaker 5

We have already closed with hundreds of brands including the White Castle expansion Kevan highlighted earlier. Aside from that, our current mix is predominantly SMB customers We are expanding in regional and middle market segments. Let me give you two quick examples of some of our traction. Naza Salal has nearly 30 locations spread mainly over the East Coast and Mid Atlantic region. A few months into onboarding 2 of their locations, Our products surpassed performance expectations and they have now signed up to roll out across the entire remaining fleet in the next few months.

Speaker 5

Hot Table is selling delicious panini sandwiches in the New England region. And after piloting one location, just last week, we have activated 4 new locations in just one day and are on rapid pace to scale across all of their locations. These are tangible examples and when you envision the opportunity across the 1,000,000 food establishments in the U. S. Alone, hopefully you can understand our excitement.

Speaker 5

In the U. S. Alone, hopefully, you can understand our excitement. Over time, we will provide more details of the key metrics we are watching here. But to give you a current sense of the near term opportunities, with solely the brands we have signed up to date, at scale And full deployment across these customers' groups, we would have over 1500 locations and well over $10,000,000 of ARR from this one specific business opportunity and our pipeline continues to strengthen.

Speaker 5

Let me now get specific on our financial results for the Q2. In Q2, we generated $8,800,000 in revenue, up 42% year over year, driven by strong growth primarily in automotive. The expansion is mainly driven by an increase in auto units overall as well as a slight increase in unit prices. And on a cumulative basis, we saw our IoT cloud units expand both sequentially and year over year. Additionally, a customer contract modification positively impacted product royalty revenue as the royalty increases from other international customers.

Speaker 5

These were partially offset by a decrease in customization services revenue versus the prior year Q2. In June, we finalized an agreement to modify the scope of an existing hosting services contract without changing the contract price. This modification involved the addition of new professional services in lieu of a tail support obligation beyond the contractual period ending twelvethirty onetwenty 23. Consequently, a portion of the professional services fee that was scheduled to be recognized after 2023 before the contract modification occurred Roughly $1,800,000 will be fully recognized in 2023. In Q2, our gross margin improved to 79%, up from 60% in the prior year quarter, which was largely driven by the Expanding scale of our business and increased data center efficiency.

Speaker 5

Also, this quarter was there was a positive impact from the previously mentioned contract modification. Cost of revenue for the quarter was $1,800,000 a decrease of 26% year over year. This improvement is due to the continued efficiency improvements From on premise activities to the cloud migration, helping us to drive further gross margin expansion as we scale the business. Additionally, in Q2 last year, our data center migration weighed on our gross margins. Operating expenses saw another step function reduction in Q2 compared to the previous quarter as we had our 1st full quarter after executing our announced corporate restructuring program in Q1.

Speaker 5

R and D expenses were $11,700,000 in Q2, a decrease of 38% year over year and 45% compared to Q4 last year. This decrease was largely due to the restructuring program we announced last quarter. However, our investment in key areas has not slowed and this level of R and D spend is where we need to be. We have the talent and expert engineering to support our growth while remaining at the forefront of innovation. Sales and marketing expenses were $5,100,000 in Q2, an increase of 16% year over year and a decrease of 25% compared to Q4 of last year.

Speaker 5

We saw a year over year increase since we went public in Q2 last year and we're still in the beginning stages of ramping up our sales and marketing efforts. We continue to streamline our focus in digital marketing, lead generation and customer acquisition, both direct and through channel partners. G and A expenses were $6,400,000 in Q2, a decrease of 32% year over year and a decrease of 12% compared to Q4 of last year. We experienced the majority of our going public costs in Q2 and Q3 last year and we saw this already start to taper off as we ended 2022. Across all operating expenses, non cash employee stock compensation was $5,600,000 in Q2, excluding the minimal expenses associated with restructuring as we finalize that program.

Speaker 5

As a result, our Q2 operating loss was $16,400,000 an improvement of 43% year over year. Interest expenses, which include ongoing amortization impacts and quarterly interest costs, were slightly lower than anticipated $5,600,000 in Q2. However, slightly higher than we expect going forward due to one time transaction related fees and other charges incurred as a result of our debt financing in Q2. Net loss was $21,900,000 in Q2, an improvement of 28% year over year. This led to a net loss per share in Q2 of $0.10 compared to $0.19 in the prior year.

Speaker 5

Adjusted EBITDA, which excludes non cash charges of stock compensation and depreciation and amortization, as well as other non operating activities, including restructuring, Was a loss of $9,900,000 which was a 50% year over year improvement. Net cash used in operating activities for the 1st 6 months With $33,700,000 improving roughly 28% year over year and a year over year improvement of 40% in the 2nd quarter. Now on to our capital structure. Our cash position at quarter end was approximately $130,000,000 up from $47,000,000 at the end of Q1. In Q2, we raised $100,000,000 of debt financing, which we partially used to pay off our existing debt of approximately $30,000,000 and eliminate the associated principal amortization payment.

Speaker 5

Our previously announced committed equity line of credit gave us additional access to capital Upon which we raised approximately $43,000,000 in Q2. In July, we filed a 3 year shelf registration under Form S-three, Which was not available to us previously. So this is just standard capital management and good housekeeping. Part of normal ongoing capital programs that companies should have in And we don't have any immediate needs to raise additional funding off of that shelf. That said, it does allow us to be opportunistic and agile if the right circumstances arise.

Speaker 5

Our capital position is now a source of strength and gives us the optionality we need to drive the business. With that, let me discuss our outlook for the remainder of the year. The first half in aggregate has landed pretty much in line with our Expectations despite massive organizational market shift. We are proud of this. As we look to the second half, there are a number of factors at play.

Speaker 5

There is tremendous interest in our solutions that are opening many new avenues that we did not fully foresee earlier this year, particularly in generative AI. That said, most of these are in large enterprise deals that can have longer deal cycles and can fluctuate. The pace and vastness of these deals Gives us greater conviction on the potential strength and momentum into 2024 and beyond, but we will comment on next year later in the year when we get closer to that time. Because of our unique market positioning, differentiated tech and massive addressable markets, we continue to believe over the longer term, We have the foundations to deliver strong, sustained and meaningfully disruptive growth. In the near term, there continues a nuanced macro picture and volatility in the markets in which we participate with uncertainties and green shoots growing together, mainly attributable to Timing of our large enterprise opportunities.

Speaker 5

Ultimately though, we believe the longer term tailwinds are largely in our favor. All that said, calibrating the puts and takes, we reiterate our 2023 revenue outlook of $43,000,000 to $50,000,000 As We noted last quarter our revenue builds throughout the year due to seasonality of Pillar 1 and the scaling of Pillar 2. And we continue to work towards becoming adjusted EBITDA positive in Before closing, I'd like to note that last week our auditor, Armenino LLP, Notified us that they have made a business decision to exit their public company SEC audit practice. As such, Our audit committee has launched a process to find a new auditor. This is a business decision by Armanino that affects dozens of their clients and is not at all a reflection of our financial position or any previously audited financials.

Speaker 5

To summarize, We are driving significant market differentiation, delivering on customer demand and catalyzing disruptive innovation with a high velocity. Each quarter on our journey brings its own unique dynamics, yet we are steadily piecing together the foundations for sustainable long term growth and profitability. Thank you. And we will now move to Q and A.

Operator

Thank you. One moment while we compile the Q and A roster. And our first question will come from the line of Mike Latimore with Northland Capital Markets. Your line is open.

Speaker 6

Great. Thanks. Yes, 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?

Speaker 5

Yes. Hey, Mike. Yes, I think it will come from Pillar 1 activity, a lot of backlog, but also some new deals potentials that I And 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 is those really end up being monthly recurring. So those will build and be consistent over time.

Speaker 5

But as we keep adding more and more 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 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.

Speaker 6

Yes. 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?

Speaker 5

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 Structuring 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.

Speaker 5

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 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.

Speaker 6

And just last one, great to see the White Castle expansion. Can you talk a little bit about the ROI they saw In their initial launch and then I guess it's going to roll out over a year and a half. I'm I'm assuming there's a good ROI here. So why wouldn't they roll out a little faster? I think you guys can kind of deploy faster than that.

Speaker 2

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 of the 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 rates, that is correct.

Speaker 2

And we, by far, exceeded The number that they were looking for and Vistar Pass their human order takers. So they're very happy with the partnership.

Speaker 5

And by the way, on return, Mike, there's obviously labor costs, benefits of utilizing AI. There's the opportunity to have upsell, which could generate revenue. There's consistency of service. I think in our press release, we commented it's 20 fourseven, so coverage over for a place that does operate 20 fourseven, that's meaningful. You don't get deterioration of performance because you're tired Your AI as an example.

Speaker 5

So multiple things from an ROI perspective, I think are very attractive to these restaurants.

Speaker 6

Great. Congrats.

Speaker 2

Thanks, Mike. Thank you.

Operator

And thank you. One moment for our next question. And that will come from the line of Brett Knoblauch with Cantor Fitzgerald. Your line is open.

Speaker 7

Hi, guys. Thanks for taking my questions. 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 the CapEx and 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?

Speaker 2

Well, we have been training models for over 10 years. So some of that has accumulated. So we have Voice 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 costs.

Speaker 2

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.

Speaker 5

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

Speaker 7

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 as this has historically been an area where you haven't invested much as you guys kind of been an R and D Product led companies, I guess, could you just maybe explain like what your vision is for what your go to market strategy would look like?

Speaker 5

Yes, certainly. So depends on the pillar. In 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 Pillar 1, I think we'll continue to grow. We leverage Channel Partnerships, we mentioned Qualcomm example is an opportunity to leverage it, a great partner, embed the voice AI with Snapdragon chip and Access, there's other partners.

Speaker 5

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 Kevan mentioned in the prepared remarks, when we get that out there, people see it, they're wowed, they really 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 1100 sales reps that we've been trained we've trained the sales reps before to kind of Showcase our technology, how we can integrate with them, and that just gives us greater reach.

Speaker 5

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, so we'll continue Look at both direct and indirect ways of accessing those customers.

Speaker 7

Got it. 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 reset midpoint or do you think that can come just from increased Usage or inquiries from product royalties?

Speaker 5

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 engagements. So that's all part of the contemplation. Don't know that I can break that up too much other than just scaling in units at the pace we're going.

Speaker 5

That gets you part of the way. But yes, I mean we need to Do some other deals and that but that's part of our overall motion as we work we 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 a rollout and some of it is we got to go do deals.

Speaker 5

We 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 timing is not always 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.

Speaker 7

Awesome. And then maybe if I could just ask one more.

Speaker 5

I

Speaker 7

guess you guys said 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 was $5,500,000 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 where you guys are at for this quarter's revenue.

Speaker 5

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 Mic 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 That's included in the prior year number. Last year, we announced sort of we had one particular customer in Europe, an auto customer 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.

Speaker 5

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 be that type of engineering The numbers that are playing out and not I don't want to say reeking, they're just changing the numbers. So that was a that's a reflection in our prior year numbers.

Speaker 7

Awesome. Thanks guys. Really appreciate it. Congrats on the quarter.

Speaker 5

Thanks Brett. Thank you.

Operator

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

Key Takeaways

  • SoundHound reported Q2 revenue of $8.8M (48% YoY growth), a 50% YoY improvement in adjusted EBITDA, and closed the quarter with $130M in cash and a $339M bookings backlog.
  • In Pillar 1, its voice AI powered over 2.8 billion annual interactions across automotive (60% YoY unit growth), TVs (80% usage increase) and IoT devices with partners such as Hyundai, Stellantis, Qualcomm and TOGG.
  • Pillar 2 smart ordering and SmartAnswering solutions now autonomously handle 93% of restaurant calls and have been deployed by hundreds of brands, including a White Castle expansion to 100 drive-thru lanes.
  • SoundHound launched Samhan Chat AI for Automotive, merging its proprietary voice AI with large language models, yielding pilot usage increases of 10× and expected customer rollouts this year.
  • The company is developing “Polaris,” a multimodal generative AI foundation model leveraging over two decades of voice and text data in dozens of languages to drive next-generation audio-text interfaces.
A.I. generated. May contain errors.
Earnings Conference Call
SoundHound AI Q2 2023
00:00 / 00:00