SoundHound AI - Q4 2022

Transcript

Operator (participant)

Good day, and welcome to the SoundHound Q4 2022 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. To ask a question during the session, you will need to press star one one on your telephone. You will then hear an automated message advising that your hand is raised.

To withdraw your question, press star one one again. 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. Please go ahead.

Scott Smith (Head of Investor Relations)

Great. Thank you, Cherie. Hi, everyone. Good afternoon. Thank you for joining our fourth quarter and full year 2022 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 those that qualify as forward-looking statements. 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.

Note that the forward-looking statements on this call are based on information available to us as of today's date. We disclaim any 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.

Keyvan Mohajer (President and CEO)

Thank you, Scott, thank you to everyone for joining the call today. We are happy to share with you the results and highlights of our first fiscal year as a public company, which we closed out with a strong fourth quarter. Our cumulative bookings backlog increased to $332 million at year-end, our full year 2022 revenue was $31.1 million.

Both of these key values exceeded targets we set and communicated in 2021 before we went public well before the challenging market conditions began. SoundHound user queries using cloud connectivity were also a highlight, growing over 85% in 2022 compared to 2021, resulting in an annual run rate of approximately $2.2 billion.

In Q4, our booking increased 10% quarter-over-quarter, and our revenue was $9.5 million, up 84% year-over-year. Before diving back in, I want to take a moment to reflect on how we got here and share our view of the latest trends and momentum in AI. We started SoundHound in a Stanford University dorm room with the vision that conversational AI will be the next major disruption in computing.

We knew our AI vision was long-term and worked for over a decade to build and own the entire technology stack that is transformative. We globalized our technology to over 25 languages and are starting the year with $332 million in bookings from our customers.

Now we power tens of millions of devices and services around the world, enabling people to more seamlessly interact and exchange in a more accessible, interconnected world. With the recent popularization of generative AI and large language models, we view 2023 as an inflection point of conversational AI, with a clear intersection between technology readiness and subsequent demand and adoption.

Such intersections are rare, and SoundHound is in a unique position to create tremendous value. We believe the impact of generative AI and large language models to the field of conversational AI is similar to the impact of deep learning, deep neural networks to machine learning.

Better quality models can be created faster and with fewer tedious engineering requirements. We view the market impact of this to be transformative, similar to the mobile ecosystem disruption of the last decade. Fast movers will create tremendous value.

Now, moving fast does not mean just opening the text or voice interface to a large language model. Such models possess the danger of providing unpredictable, stale, and incorrect responses, a phenomenon known as AI hallucinations. The underlying principles of SoundHound technology are addressing these shortcomings by combining software engineering and machine learning. For the first time, we are unveiling our novel approach using our proprietary technologies called CaiLAN and CaiNET.

CaiLAN, or Conversational AI Language, uses software engineering to efficiently build knowledge domains, while CaiNET, or Conversational AI Network, uses machine learning to augment and enhance the realm of possibilities. CaiNET can connect to SoundHound's internal generative AI models as well as external models such as OpenAI's GPT and ChatGPT, among others. Ultimately, CaiLAN controls and arbitrates the results to provide the best response to the user. Let me demonstrate.

Scott Smith (Head of Investor Relations)

I work at SoundHound.

Speaker 6

Okay, I will remember where your work is.

Scott Smith (Head of Investor Relations)

Show me fancy restaurants near my work that accept reservations.

Speaker 6

Here are several restaurants near SoundHound, sorted by highest price, that accept reservations.

Scott Smith (Head of Investor Relations)

Is it appropriate to bring a bottle of wine to a fancy restaurant?

Speaker 6

It depends on the restaurant's policy regarding bringing outside alcohol. Some restaurants allow customers to bring their own bottle of wine but charge a corkage fee, while others do not allow it at all. You may want to check the restaurant's website or call ahead to find out their policy.

Scott Smith (Head of Investor Relations)

If there is a corkage fee, what is a typical charge?

Speaker 6

The corkage fee can vary depending on the restaurant, but it typically ranges from $15-$50 per bottle. Some restaurants may have different fees depending on the size of the bottle or the type of wine. It's best to check with the restaurant beforehand to avoid any surprises on the bill.

Scott Smith (Head of Investor Relations)

Okay. Sort the results by highest price and only show the ones that have more than four stars on Yelp and have outdoor seating.

Speaker 6

Okay, here are several restaurants with more than four stars sorted by highest price and have outdoor seating.

Scott Smith (Head of Investor Relations)

Does the first one have parking?

Speaker 6

Fleming's Prime Steakhouse & Wine Bar, the wine bar located at 2762 Augustine Drive in Santa Clara has parking.

Scott Smith (Head of Investor Relations)

What kind of food does it have?

Speaker 6

It is a wine bar, a steakhouse, and a seafood restaurant.

Scott Smith (Head of Investor Relations)

I have a question. Is it bad for you to have that kind of food too often?

Speaker 6

Consuming high amounts of red meat or seafood can have negative health consequences if done on a regular basis. However, it is okay to indulge in these foods every once in a while as part of a balanced diet. It is important to consume a variety of foods in moderation to maintain a healthy lifestyle.

Scott Smith (Head of Investor Relations)

How long does it take to drive from my work to there?

Speaker 6

It will take approximately seven minutes to drive 2.3 miles from SoundHound to Fleming's Prime Steakhouse & Wine Bar, 2762 Augustine Drive, Santa Clara.

Scott Smith (Head of Investor Relations)

When is sunset tonight, and will it be raining tonight at 7 P.M. near my work?

Speaker 6

Sunset will be at 6:05 P.M. on Sunday, March 5, 2023. No, it isn't forecast to rain on March 5 near SoundHound.

Scott Smith (Head of Investor Relations)

Send a message to 650-555-1212. We are on for dinner tonight at 7:00 P.M. I will book a fancy restaurant. See you then.

Speaker 6

Sending your message.

Scott Smith (Head of Investor Relations)

Can you recommend some gift ideas for a 10-year anniversary dinner?

Speaker 6

You could consider creating a scrapbook of your favorite memories together. You could also write a heartfelt letter expressing your love and appreciation.

Scott Smith (Head of Investor Relations)

Can you write me a four-line poem for a 10-year anniversary?

Speaker 6

Sure, here's a quick four-line poem. Ten years have come and gone, but my love for you still shines on. I'm grateful for every moment we've shared and look forward to many more years to be paired.

Scott Smith (Head of Investor Relations)

That was great. Thank you.

Speaker 6

It is my pleasure.

Keyvan Mohajer (President and CEO)

What you just heard was a sneak preview of a new product called SoundHound Chat AI. It ushered in a new phase of voice-enabled conversational AI that used to only exist in science fiction. By combining the power of software engineering and machine learning with generative AI, we can finally deliver the visual assistant experience that users have been desiring for decades.

Please stay tuned for our official launch announcement later this month. Let's review our expected business impact of this change as it relates to our three-pillar strategy. In our pillar one, where we power devices and cars, more users will use their assistant more often.

Users will no longer limit their interactions to simple control commands, setting timers, and playing music. They can have lengthy, useful conversations with their assistants. This increasing usage should translate to an increasing revenue and licensing fees for SoundHound.

Combined with our breakthrough Dynamic Interaction, which I'll talk about shortly, this will further strengthen our position as a leader in voice interfaces by creating more interaction capabilities for users of our products. In addition, more product creators will demand this feature, and this increase in adoption will also increase the revenue for SoundHound AI.

In our pillar two, more tasks can be automated, and in general, customer service, an area of important focus for SoundHound AI, will be transformed, with AI being not just cheaper than humans, but also better than humans. By incorporating the possibilities that are already proven from generative AI and large language models into customer service applications, we envision that end users will ultimately prefer to speak to an AI agent rather than a human representative when talking to a business.

We expect our expansion to new customer service verticals to accelerate, ultimately, AI-enabled customer service will be as necessary to every business as electricity. SoundHound is in a unique position to take advantage of this rare moment due to our advanced and comprehensive technologies, mature products, and existing customer base.

In our view, this can't be done as a side project. It can't be achieved by simply interpreting a few external APIs. Creating the necessary technologies to winning conversational AI would be costly, inefficient, and slow. By owning all the core pieces of the engine, we have a distinct competitive advantage. Innovation has been a core part of our DNA. Last November, we unveiled a new technology called Dynamic Interaction.

SoundHound Dynamic Interaction is a multimodal full-duplex interface with real-time continuous audio-visual feedback in response to both audio and touch input, with no wait force, awkward pauses, or turn-taking. It ignores off-topic speech, makes proactive suggestions to the user, and intelligently decides when to use audio or visual output.

We believe Dynamic Interaction is a category-defining breakthrough that will raise the bar for human-computer interaction, just like how Apple's multi-touch technology leapfrogged existing touch inter-interfaces in 2007. By combining Dynamic Interaction with generative AI, we expect to achieve our ultimate vision of making computers better than humans in language understanding and more human in the way they interact and respond.

Given our unique positioning and strength, the growing demand we are seeing for our independent AI car products and services will only get stronger as we execute on more opportunities and with more customers.

In 2022, we made great progress in forging and extending significant relationships and partnerships with a number of new brands with our vertical agnostic technology. In the past year, SoundHound has announced a number of key partnerships and integrations, including an agreement with Qualcomm to bring SoundHound Voice AI to its Snapdragon platforms, new deals and integrations with VIZIO, Square, Toast, and Oracle, and an expanded partnership with Snap.

SoundHound also signed a multiyear agreement with Hyundai and announced an expansion of our Stellantis relationship in Europe, as well as a series of collaborations in automotive space, including with LG, Harman, EPCA, and DMI. In automotive, we now work with 20 brands, an impressive number given we went from zero to 20 brands in just a few years.

While we continue to add new brands in our portfolio, we are also able to expand with our existing brands globally by supporting new languages, new regions, adding edge and cloud, and new services. We are also working with many world-class device manufacturers, ranging from smart appliances to TVs and in multiple areas within the IoT space.

Here, we continue to expand within our existing customers, and we are excited about the companies in our pipeline. With more than 75 billion connected devices expected globally by 2025, we see a tremendous opportunity here for our voice AI-powered products and solutions. Last year, our voice AI technology was made generally available for customer service, starting with SoundHound for Restaurants, making our entry into this massive, rapidly evolving service industry.

Since launch, we have added restaurant customers across North America and continue to forge relationships with important partners, including companies like Oracle, Square, and Toast, with more to come. Our SoundHound for Restaurants voice AI assistant allows restaurants to automate the ordering process at drive-throughs, ordering kiosks, in-app, and over the phone, enabling restaurants to create efficiencies in order taking at a time when many are tackling rising food costs, staffing shortages, supply chain issues, and other headwinds.

Voice-enabled food ordering is particularly challenging, requiring specialized speech recognition and complex natural language understanding, which match perfectly with our key differentiators. We are excited as we move forward in 2023 because we expect to continue to add customers and partners and deliver voice AI technology to some of the most well-known brands in the world.

We aim to power billions of devices and services, and we already voice-enable millions of cars, TVs, mobile apps, IoT devices, and restaurants on a global scale, thanks to our expansive set of languages. While we are excited about what we have built at SoundHound and the new opportunities we have realized, it is nice to see that this success is also being recognized by the industry.

Recently, we have been named a Speech Industry Award winner, and we were also named as one of the world's top 10 disruptive AI companies by AI Magazine. In addition, SoundHound for Restaurants has been named among the winners of the National Restaurant Association SmartBrief Innovation Award for food service after only a short period since market launch. There is undoubtedly momentum building behind AI, our company, and our category.

The convergence of heightened market demand for conversational AI and the technological readiness for our AI-powered solutions has positioned us at a critical and a very exciting inflection point, one we are primed to take advantage of. In closing, since launching SoundHound's initial voice AI platform in 2016, we have radically evolved it, globalized it, its reach to 25 languages, been selected by 20 car brands, and created over 100 branded assistants across numerous brands and languages.

We continue to scale into major enterprises, including Hyundai, Kia, Genesis, Mercedes-Benz, Stellantis, Dodge, Chrysler, Harman, Toast, Square, LG, VIZIO, Snap, Pandora, and many others. There is tremendous opportunity in itself to expand within these existing customers, but we are also making meaningful progress in expanding our addressable market, as demonstrated with SoundHound for Restaurants in customer service.

With recent product launches, such as Dynamic Interaction for customer service and generative AI, we are confident in our ability to both grow within our existing global addressable market and expand into new ones. We are in a unique position to maintain our leadership in voice-enabled AI technology and solve extremely difficult problems with our breakthrough inventions for our customers and partners.

We are pleased to have ended the year at the high end of our guidance despite the macroeconomic conditions that worsened throughout the year. We remain agile and focused and are confident to grow the business at approximately 50% in 2023. With that, I will now turn the call over to Nitesh to talk about our financial performance for the quarter.

Nitesh Sharan (CFO)

Thank you, Keyvan, and good afternoon, everyone. 2022 was our first fiscal year in the public markets, a year when the IPO market stalled, higher interest rates steered investors towards value, and sentiment shifted away from disruptive, high-growth technology companies such as ourselves. Nevertheless, we adjusted, thought harder, progressively took actions, and set ourselves up to serve the rapidly increasing demand for our products and on much stronger financial footing.

Artificial intelligence is fundamentally about making technology more human-like. At SoundHound, we do that by making conversations with machines more natural and seamless, and the demand for that has never been stronger. Large language models, generative AI, and the pervasiveness of chatbots are unearthing entirely new use cases every day. The opportunity set and adoption curves will accelerate rapidly. As Keyvan indicated, our time is now. I'll dive deeper into expectations for 2023 shortly.

Let me first review our 2022 results. We continued to expand our voice-enabled ecosystem, had strong growth, and delivered full-year revenue at the high end of our guidance range. Despite the volatile macro backdrop, we have now outperformed our publicly stated full-year outlooks for the past two years. The foundation for this consistent overachievement versus our expectations is rooted in strong customer engagement and sound execution that should only further improve from here.

Our cumulative bookings backlog establishes that foundation. We closed the year with $332 million, representing a year-over-year growth of 59%. The contracts underlying our bookings backlog now range from one year to more than nine years, with a roughly 6.5 year weighted average contract length. Through the year, we saw meaningful lengthening in customer contracts, which demonstrates the deepening strategic partnerships and validates the value we continue to create.

Our business model is grounded in the three-pillar revenue framework. Pillar one represents voice-enabled products where we receive royalties. Pillar two represents voice-enabled services, generally under monthly subscription contracts. We bring pillar one and two together into pillar three monetization.

As we have discussed previously, the bulk of our current business and backlog is in pillar one. In 2022, we scaled into millions of new cars and devices. In this pillar, we are extending our offering across new units and adding more features to existing ones to expand revenue per unit. We can scale with existing customers, and we are constantly adding new ones. In automotive, for example, we saw more than 3x growth in in-year new unit production in 2022 and unit price expansion of more than 20%. In Q4, we added another three brands to our ever-growing list.

As we have discussed previously, growing our pillar two voice-enabled services is a key focus area, starting with AI-enabled customer services for restaurant. There's massive demand, and one advantage here is the pace at which we can scale because of the much shorter sales cycles and activation timeline. Just several months in, and our qualified advanced pipeline of stores is now well into the thousands, and we are rapidly enhancing product features to extend our reach to even more brands and locations.

The recent advances with large language models only accelerates our excitement around the broader customer service opportunity in this pillar. Our packaged offerings and technologically advanced business inquiry voice AI solutions are perfectly suited to extend our reach to a multitude of businesses and industries. There is tremendous value to unlock for customers.

Let me now get specific on our financial results for the fourth quarter and full year. In Q4, we generated $9.5 million in revenue, up 84% year-over-year. For the full year, our revenue was $31.1 million and was predominantly driven by product royalties with an increasing contribution from subscription services throughout the year.

Our product royalty revenue increased primarily due to strong customer momentum and a number of large edge deals where we received multiyear minimum guarantee commitments. Our edge solutions operate without internet connectivity or hosting requirements, so our performance obligations are fulfilled when we deliver the software. Our long-term commitments demonstrate the continued strong partnerships we've developed and the continued share gains we are experiencing. Foreign exchange also had an impact on our revenue.

Our full-year revenue growth rate would have been roughly two percentage points higher without this impact. In Q4, our gross margin improved to 71%, up from 67% in the prior year quarter, which was largely driven by the expanding scale of our business. Cost of revenue for the quarter was $2.8 million, up 61% from the prior year.

The majority of our cost of revenue includes data center costs supporting our customer production environments. We completed the migration of our cloud spend to Oracle in Q4 2022. As we look forward, there are some on-prem activities that we migrate to the cloud, helping us continue to drive gross margin expansion along with the anticipated benefits of further scale. Moving on to operating expenses.

R&D has been the key pillar of this company as we built our voice AI platform and deep patent portfolio of over 260 filed and pending. In Q4, R&D was $21.5 million, up 32% year-over-year. We continue to invest in R&D to ensure we remain at the forefront of innovation in AI and machine learning, while also helping to develop and scale our cloud offerings and other products and services.

In 2022, we ramped up our sales and marketing investments in both people and technology to accelerate growth, particularly in pillar 2. We have increased focus in digital marketing, lead generation, and customer acquisition, both direct and through channel partners. In Q4, sales and marketing expenses were $6.7 million, up 587% year-over-year off a small prior year base.

With our organizational shifts in 2023, we expect this expense item to benefit from greater focus. G&A expenses were $7.2 million in Q4, up 41% year-over-year, which reflects investments across the global support functions of finance, legal, facilities, and human resources. The increases were largely a result of ensuring our G&A functions delivered on the requirements of a newly public company.

Across all operating expenses, non-cash employee stock compensation was $9.3 million in Q4. We expect the ongoing quarterly stock comp expense to meaningfully reduce in 2023 post our recent restructuring. Our operating loss is $28.8 million in Q4. Adjusted EBITDA, which excludes the non-cash charges of stock compensation and depreciation and amortization and other non-operating activities, was a loss of $18.6 million.

Net loss per share in Q4 was $0.15 compared to a net loss of $0.32 in the prior year period. For the full year, net loss per share was $0.83 compared to a net loss of $1.18 in the prior year. On to the capital structure. Our cash position at year-end was $9.2 million. In January, we successfully raised $25 million in preferred equity.

Our previously announced committed equity line of credit also became effective, giving us additional access to capital. In addition, as we announced concurrently with our preferred raise, we are in process of refinancing our existing debt. All in, our balance sheet has strengthened meaningfully, and we have a fully funded business plan through and beyond the point of our becoming profitable. With that, I'll move on to guidance.

Earlier this year, we announced restructuring actions that were necessary to rightsize our cost structure, impacting both people and discretionary spend. Such decisions are never easy, but the actions have enabled us to accelerate our path to profitability without materially impacting our ability to execute our business plan effectively.

We expect these cost reductions to result in operating cost savings of approximately $60 million in 2023 as compared to 2022. We expect revenue to grow approximately 50% in 2023, and we now expect to be adjusted EBITDA positive in Q4 of this year, setting the stage for sustained long-term profitable growth as we enter 2024. Let me double-click a bit on these expectations.

The $332 million of cumulative bookings backlog that I noted earlier gives us high confidence on revenue that will either automatically roll into the P&L in accordance with software revenue recognition guidance or as a result of expected customer unit volumes upon which we generate royalty revenue streams.

We expect that SoundHound for Restaurants will provide a meaningful contribution to revenue and grow at an accelerated rate as we move through the year. It is important to note that SoundHound for Restaurants has had only a minimal contribution to our revenue up to this point, but the underlying customer foundation, pipeline, and activation of stores is building rapidly.

It's also important to note that this vertical has a very attractive financial profile with more predictable revenue streams, better scalability leading to more favorable operating margins, and a fast conversion of initial customer contacts to cash flow. We are enthusiastic about the momentum we continue to see from customers and how our team is capitalizing on this tremendous opportunity.

Therefore, overall in 2023, we expect that revenue will be in the range of $43 million-$50 million. We expect this revenue will build through the year, with each quarter larger than the last due to seasonality of pillar one businesses and the scaling of restaurants. Our Q1 results will also be impacted by the restructuring efforts that we continue to finalize.

Last year, approximately two-thirds of our revenue was recognized in the second half of the year. We expect to see a similar trend for this year. To summarize, we have taken the important steps to set us up for long-term success. While the progress will not always be linear, we are building a strong and sustainable business model and driving growth with a clear path to profitability. Market momentum is real, customer traction is strong. We are extremely excited about our path forward. Thank you. We will now move to Q&A.

Operator (participant)

Thank you. As a reminder to ask a question, please press star one one on your telephone and wait for your name to be announced. To withdraw your question, please press star one one again. One moment while we compile the Q&A roster. Today's first question will come from the line of Mike Latimore with Northland. Please go ahead.

Michael Latimore (Managing Director and Senior Research Analyst)

All right, great. Thank you. Yeah, congrats on the excellent results this year.

Nitesh Sharan (CFO)

Thanks, Mike.

Michael Latimore (Managing Director and Senior Research Analyst)

A lot of interesting developments, obviously. I guess first on the restaurant vertical, you seem, you know, fairly positive about that vertical. I guess, can you just give a little more color there? You know, I mean, how many restaurants are you currently deployed at?

When you, when you talk about pipeline, is that business that's about to be deployed or is that business that you know, still need to win? Then I guess also it just seems like, you know, this would be applicable to very large chains. Are there any large restaurant chains that are rolling this out?

Nitesh Sharan (CFO)

Sure, Mike. I could start. A couple of points. Yeah, when I alluded to the the the pipeline in my prepared remarks, I mean, generally we, you know, obviously we have a lot of conversations going on, and we sort of have an initial pipeline, and then we kind of enter it into our CRM systems when it's in a more advanced stage.

Qualified leads that we really characterize in what I was referencing are ones where there are deep conversations going on with decision-makers at the restaurants, where there's clear line of sight to to a significant opportunity, whether as it's small and medium enterprises, it could be, you know, one to a single digit level locations. In the enterprise side, they could be tens, hundreds+.

We definitely have a suite of both small, medium, mid-market and enterprise-level customers that have hundreds of stores. We've previously mentioned White Castle as an example. You know, a chain that has over 350 stores around the nation. We're activating and live in several of those and scaling. You know, I would say that, you know, in terms of the number, I mentioned thousands of advanced stage pipeline. Those are ones that are not yet paying us monthly fee. Those are pipeline. That means they're not yet in, but those are late-stage conversations.

In many cases, what happens is we kind of get a late-stage conversation with a let's say a pizza restaurant. There are certain features or facets that they need. You know, maybe they need a customization of doing half this, half that, and that's a feature that we developed. In a lot of cases, there's really active engagement.

We may just need to add some features and functionality. We have hundreds of restaurants signed up already, so beyond the pipeline stage that are operating, and we're quickly scaling those. As I mentioned in the prepared remarks, the time from sort of initial conversation to cash flow or monthly recurring revenue in the case for us can be very rapid.

Especially when you get into restaurants that have multiple stores. Once you ingest that menu upfront and you custom sort of develop the capability and the voice, moving to restaurant number two or three is very, very fast. In some cases, if it's more on the drive-thru feature, you might have some acoustic things that you have to figure out, but generally, especially for full ordering, you don't have any of those complexities of traffic or outside noise, and so it could be much more rapid. I rambled a little bit there, so maybe I'll pause and see if that kinda hits the question.

Michael Latimore (Managing Director and Senior Research Analyst)

Yeah, no. That's good context. On the SoundHound Chat AI service you mentioned, is that both a direct to consumer and, you know, business enabler type of service? Or how are you thinking about kind of the go-to-market there?

Keyvan Mohajer (President and CEO)

Yeah. It will be both. We'll offer that to our existing customers, like car makers and IoT makers and so on. You know, SoundHound, historically, we've had direct to consumer applications and products. You know, our existing applications have received over 300 million downloads. That's something that is part of our DNA. We are really good at it, and it's a good moment to take advantage of that experience.

Michael Latimore (Managing Director and Senior Research Analyst)

Great. Just last one, can you provide a little more color on your activities with Qualcomm? That seemed like a, you know, important partner that you announced last year. Maybe just a little bit more feel for how that partnership's going.

Keyvan Mohajer (President and CEO)

Yeah, absolutely. We had a really good demonstration. We had a joint demo at their Snapdragon Summit a few months ago. They also showcased it at CES. They are basically bundling our Voice AI solution into their chipsets, and they can basically be our channel partner and sell it to their customers on our behalf. It's a combination of their chipsets and their voice technologies, voice recognition technologies, and our Voice AI solutions. It's a very meaningful partnership.

Michael Latimore (Managing Director and Senior Research Analyst)

Okay. Great. Thank you.

Nitesh Sharan (CFO)

Thanks, Mike.

Operator (participant)

Thank you. As a reminder, if you would like to ask a question, please press star one one. One moment for our next question. That will come from the line of Brett Knoblauch with Cantor Fitzgerald. Your line is open.

Brett Knoblauch (Managing Director)

Hi, guys. Thanks for taking my question. The first I guess is on the profitability guide. I know you guys have taken a lot of action to kind of, you know, improve profitability over the last couple of months. What assumptions do you have to get to kind of, you know, positive adjusted EBITDA in the fourth quarter?

I guess, what should we be expecting from the gross margin front, absolute OpEx basis? You know, if we look at the run rate exiting the quarter, should we expect, you know, that to decline by, call it, you know, $10 million on a run rate basis, or what should we be thinking for that?

Nitesh Sharan (CFO)

Sure, Brett. First I'll start at the top. We guided, you know, 50% growth and sort of highlighted that that is going to be back-end loaded. You know, we are expecting to ramp through the year. Part of that is the just seasonality that comes with the pillar 1 and predominantly auto business.

Number 2, well, I should say auto and devices. There is seasonality associated with like TV sales and so forth as well. Also with our pillar 2 in restaurants, as we continue to scale, gain traction, and that builds on a monthly subscription basis that'll compound in a positive way that should build through the year. There's a bit of that seasonality.

Then with margins, you know, we're not really guiding margins, but I'd say that just overall profile and long term, we definitely think the levels, you know, the 70% plus level that we've been delivering this year is very achievable and very scalable. As you go into, you know, our diversification of products from cloud to edge, that we've seen this year, that does have favorable elements to gross margin. I mentioned in my prepared remark, well, you know, through the year, we were migrating cloud, and we had that sort of impact a little bit of a, you know, a bit of a drag, in 2022's margin that is now kinda completed.

Also there's some other actions we're taking to drive efficiencies and margin just with scale. With respect to cloud versus edge, some of the edge solutions, they tend to have favorable gross margin profiles. As you put it all together, you know, we expect gross margin to continue to be in the zone and positive to what it was in 2022.

On the OpEx line, I mentioned, you know, on a full year basis, $60 million of savings. The first quarter will have some of the restructuring cost impact in it, but on an ongoing, and we're still, for some of our international countries, it just takes, you know, time to kinda work through that.

Certainly by the end of the year, you know, we'll have worked through entirely. In fact, in Q1, by the time we're done with Q1, we should be largely through all the restructuring activities. We should start to realize those savings in OpEx. Yeah, I mean, as you get to the full year, Q4E estimation.

I think when you look at our OpEx items, R&D, sales and marketing, G&A, where we're taking and when the actions we took were north of 40+% reductions on, you know, both headcount and discretionary, you can kind of do the math.

The other thing I'd say we, and I mentioned this in the prepared remarks in passing as well, around the stock comp elements, although that doesn't affect the adjusted EBITDA, that also we expect to come down. So that is kind of the composition of what gives us confidence that we'll achieve adjusted EBITDA profitability in Q4.

Brett Knoblauch (Managing Director)

Got it. No, that's helpful. Then I guess on the cumulative kind of bookings backlog, I guess the, you know, grew 10% sequentially. Can you talk about what kind of specific relationships or customers really drove the kind of, you know, quarter-over-quarter growth there?

Keyvan Mohajer (President and CEO)

Yeah. I think they've announced they have over 70,000 restaurants. One thing that's very unique about our kind of a restaurant is that we could work with single location restaurants. There are a few players that are in the space because of the huge amount of onboarding requirements. It could take them months to train a model for a new menu.

They can only go after the brands that have, like, hundreds of locations, for example. We could actually work with a restaurant that has a single location because our onboarding is automated. We can ingest the menu and even if they have custom vocabulary on their menu, our feature recognition automatically gets trained and enhanced to recognize those when they have complex menu structure. All of that can be automated.

That's a very green area for us to go after the long tail. The Toast partnership is very key because they have, you know, they open the door to tens of thousands of restaurants for us. We partnered with their sales team as well. They have a large number of salespeople that can sell our solution on our behalf.

Brett Knoblauch (Managing Director)

Perfect. That makes sense. I guess I could have one follow-up. The new kind of, generative AI chat product, is this gonna be more like a chatbot? Is it gonna be more voice driven? How do you plan on, I guess, monetizing that solution and maybe the timeline for when you expect monetization to occur? Is this something that we should expect to contribute to revenues this year?

Keyvan Mohajer (President and CEO)

The demo you heard was voice-based, the user was talking to a mobile app and hear the response. We believe voice really unlocks the power of generative AI. Typing is not as compelling as voice because you can speak faster and interact more freely. It will be voice-based.

There will be a text-based text input as well, but voice, we think, will be the dominant way. That's one of our differentiators. We bring our own ASR. You know, I really think this is the first time we can deliver a voice assistant to the end users that they have been wanting for more than a decade.

If you remember when Apple launched Siri more than 10 years ago, there were all these ads on TV that made a big promise that you can go and have it open up a conversation with an assistant. Users loved the idea. They rushed to it, and they quickly became disappointed because it was able to only handle a few things, like answer questions about weather and maybe stock prices and play music and set timers.

It was still better than not having it. People used it and adopted it, but it wasn't what they had imagined. Now more than a decade later, we are finally able to deliver that experience that users have wanted. We know they want it because we've been in this business for a long time, for many years, and we know that's what the users want.

Very few companies can take advantage of this moment because just having a voice interface to a large language model is not enough because maybe you can ask them some questions to write you a poem or, you know, some long tail questions. If you ask them questions about real-time search queries, like how's the weather or sports scores or stock prices or setting a timer or calling contacts or sending messages or setting calendar, navigating to restaurants or addresses, they fail at those.

To really deliver this ultimate assistant experience, you need to have both. You need to have the generative AI large language models, and you need to have the existing assistant domains that people demand with a voice interface on top of it. There's only a handful of companies that can take advantage of this situation.

SoundHound is the most agile 'cause we are able to move really fast. Stay tuned for our announcement later this month. The questions, the rest of the questions you asked, we will answer those in our announcement.

Nitesh Sharan (CFO)

Brett, the other thing, just that, you know, for us, the generative AI is certainly, the, like the demo we shared, but we also talked about Dynamic Interaction, and we previously announced a Dynamic Interaction sort of next generation for auto. There's a ton of interest there. You know, in the space, we think certainly voice is an important modality, but sort of the multimodal is just as exciting.

You know, sometimes voice input, voice output makes a lot of sense. Sometimes it's voice and touch input and audio and visual output, and that's sort of what our Dynamic Interaction capability allows us to do real-time. That's really where the future is going. It's just going very rapidly. So there's a ton of application use cases that we're very excited about.

The monetization will come with those near term.

Brett Knoblauch (Managing Director)

Perfect. Thanks, guys. Really appreciate it.

Nitesh Sharan (CFO)

Thanks, Brett.

Operator (participant)

Thank you all for participating in today's question and answer session. I would now like to turn the call back over to Mr. Keyvan Mohajer for any closing remarks.

Keyvan Mohajer (President and CEO)

Thank you. When we founded SoundHound, we had a vision to see Voice AI in our lifetime, but we couldn't have fully imagined the vibrant environment of AI innovation we find ourselves in today. As conversational AI comes to prominence across industries, we are confident that as the only independent cross-industry Voice AI platform, we are in a strong position to deliver SoundHound's best-in-class technology to even more global brands.

We continue to execute, 2022 was a pivotal year for introducing new products and building new partnerships, We are excited about where we are and where we are looking forward to a strong 2023. With that, I thank you for joining us on the call today and look forward to speaking with you when we report our first quarter 2023 results. Thank you.

Operator (participant)

Thank you all for participating. This concludes today's program. You may now disconnect.