Earnings Call Transcript - SOUN Q4 2022

Operator, Operator

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 speakers’ presentation, there will be a question-and-answer session. 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, Sheri. Hi, everyone. Good afternoon, and thanks 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. 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 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 would like to turn the call over to our CEO, Keyvan Mohajer. Please go ahead, Keyvan.

Keyvan Mohajer, CEO

Thank you, Scott, and thank you to everyone for joining the call today. We're 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 and our full year 2022 revenue was 31.1 million. Both of these key values exceeded targets we communicated in 2021 before we went public and well before the challenging market conditions began. SoundHound user queries using cloud connectivity were highlighted as growing over 85% in 2022 compared to '21, resulting in an annual run rate of approximately 2.2 billion. In Q4, our bookings 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 would 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. And now we power tens of millions of devices and services around the world, enabling people to interact more seamlessly and exchange information in a more accessible, interconnected world. With the recent popularization of generative AI and large language models, we view 2023 as an inflection point for 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 on the field of conversational AI is similar to the impact of deep learning and deep neural networks on machine learning. Better quality models can be created faster and with fewer tedious engineering requirements. And 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 a text or voice interface to a large language model. Plus models persist 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 develop 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, GPT, and ChatGPT, among others. Ultimately, CAILAN controls and arbitrates the results to provide the best response to the user. Let me demonstrate. User: I work at SoundHound. SoundHound Chat AI: Okay, I will remember where your work is. User: Show me fancy restaurants near my work that accept reservations. SoundHound Chat AI: Here are several restaurants near SoundHound, sorted by highest price that accept reservations. User: Is it appropriate to bring a bottle of wine to a fancy restaurant? SoundHound Chat AI: 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. User: If there is a corkage fee, what is a typical charge? SoundHound Chat AI: The corkage fee can vary depending on the restaurant, but it typically ranges from $15 to $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. User: Okay. Sort the results by highest price and only show the ones that have more than four stars on Yelp and have outdoor seating. SoundHound Chat AI: Okay. Here are several restaurants with more than four stars sorted by highest price that have outdoor seating. User: So, the first one has parking? SoundHound Chat AI: Fleming's Prime Steakhouse & Wine Bar, The Wine Bar located at 2762 Augustine Drive in Santa Clara has parking. User: What kind of food does it have? SoundHound Chat AI: It is a wine bar, a steakhouse, and a seafood restaurant. User: I have a question. Is it bad for you to have that kind of food too often? SoundHound Chat AI: 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. User: How long does it take to drive from my work to there? SoundHound Chat AI: It will take approximately 7 minutes to drive 2.3 miles from Downtown to Fleming's Prime Steakhouse & Wine Bar, 2762 Augustine Drive, Santa Clara. User: When is sunset tonight, and will it be rainy tonight at 7 p.m. near my work? SoundHound Chat AI: 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. User: Send a message to 650-555-1212. We are on for dinner tonight at 7 p.m. I will book a fancy restaurant. See you then. SoundHound Chat AI: Sending your message. User: Can you recommend some gift ideas for a 10-year anniversary dinner? SoundHound Chat AI: You could consider creating a scrapbook of your favorite memories together. You could also write a heartfelt letter expressing your love and appreciation. User: Can you write me a four-line poem for a 10-year anniversary? SoundHound Chat AI: Sure. Here's a quick four-line poem. 10 years are coming on, but my love for you still hangs on. I'm grateful for every moment we've shared. I look forward to many more years to be paired. User: That was great. Thank you. SoundHound Chat AI: It is my pleasure. What you just heard was a sneak preview of a new product called SoundHound Chat AI. It ushers 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 digital assistant experience that users have been desiring for decades. Please stay tuned for our official launch announcement ready soon. Let's review our expected business impact of this change as it relates to our three-pillar strategy. In our pillar one, we will power devices and cars. More users will use their assistants more often. Users 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 translates into increased 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 our pillar two, more tasks can be automated, and in general customer service, an area of significant focus for SoundHound will be transformed with AI. AI is not just cheaper than humans but also better than humans. By incorporating the possibilities that are already proven with generative AI and large language models into customer service applications, we envision that end users will ultimately prefer to speak with AI agents rather than a human representative when talking to a business. We expect our expansion into new customer service verticals to accelerate, and 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 product, and existing customer base, we believe this cannot be done as a side project. It can't be achieved by simply integrating a few external APIs, and creating the technologies needed for winning conversational AI will 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. 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 awkward pauses or turn-taking. It ignores automatic speech recognition for unsolicited 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, similar to how Apple's multi-touch technology leapfrogged existing touch 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. Even with our unique positioning and strengths, the growing demand we see for our independent AI-powered products and services will only get stronger as we execute on more opportunities with more customers. In 2022, we made great progress importing and extending significant relationships and partnerships with several new brands with our vertical-agnostic technology. In the past year, SoundHound has announced several key partnerships and integrations, including an agreement with Qualcomm to bring SoundHound AI to the Snapdragon platform, 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 our commercial space, including with LG, HARMAN, DPCA, and DMI. In automotive, we now work with 20 brands—an impressive number given we went from 0 to 20 brands in just a few years. While we continue to add new brands to our portfolio, we're 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 with 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 this launch, we have added restaurant customers across North America and continue to pursue relationships with key partners including companies like Oracle, Square, and Toast, with more to come. Our SoundHound platform allows restaurants to automate the ordering process at drive-throughs, ordering kiosks, in-app, and over the phone, enabling restaurant customers to create efficiencies in order-taking at a time when many are facing rising food costs, staffing shortages, supply chain issues, and other headwinds. Most new restaurant audio interactions are particularly challenging, requiring specialized speech recognition and complex natural language understanding, which aligns 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. We are already voice-enabling meaningful cars, TVs, mobile apps, IoT devices, and restaurants on a global scale, thanks to our extensive set of languages. While we're excited about what we have built at SoundHound and the new opportunities we have realized, we're pleased to see that our success is also being recognized by the industry. We have been named a speech industry award winner, and we were also recognized as one of the world's top 10 disruptive AI companies by AI Magazine. Additionally, SoundHound for Restaurants has been named among the winners of the National Restaurant Association's Smartbrief Innovation Award for Foodservice shortly after its market launch. There is undoubtedly momentum building behind AI, our company, and our category. The convergence of heightened market demand for conversational AI with the technological readiness for our AI-powered solutions has positioned us at a critical and very exciting inflection point, one we are eager to take advantage of. In closing, since launching SoundHound's initial voice AI platform in 2016, we have radically evolved, globalized, reached 25 languages, been selected by 20 car brands, and created over 100 branded assistants across numerous brands and languages. There's tremendous opportunity in itself to expand within these existing customers, but we are also making meaningful progress in expanding into other submarkets, as demonstrated by our restaurant and customer service ventures. With recent product launches, such as Dynamic Interaction for customer service and generative AI, we're confident in our ability to both grow within our existing global additive 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're 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 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 drove investors towards value, and sentiment shifted away from disruptive high-growth technology companies such as ourselves. Nevertheless, we adjusted, fought harder, took aggressive actions, and set ourselves up to serve the rapidly increasing demand for our products on a much stronger financial footing. Artificial Intelligence is fundamentally about making technology more human-like. At SoundHound, we achieve this 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 continue to expand our voice-enabled ecosystem, have 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 outlook 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. Throughout 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. And then we bring pillars 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, and in 2022, we've 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 are constantly adding new ones. In automotive, for example, we saw more than 3x growth in 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, moving into pillar two voice-enabled services is a key focus area starting with AI-enabled customer services for restaurants. There's massive demand, and one advantage here is the pace at which we can scale because of a much shorter sales cycle and activation timeline. Just several months in, 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. Recent advances with large language models only accelerate 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. 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, which is 84% year-over-year growth. For the full year, our revenue was $31.1 million, largely driven by product royalties, with an increasing contribution from subscription services throughout the year. Our product loyalty 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 2 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 environment. We completed the migration of our cloud spend to Oracle in Q4 2022. As we look forward, there are some on-prem activities related to the cloud that will help 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, with over 260 filed and pending patents. 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 offering 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 two. We have increased our focus on 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 from 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, reflecting investments across global support functions such as 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 compensation expense to meaningfully reduce in 2023 post our recent restructuring. Our operating loss was $28.8 million in Q4, and adjusted EBITDA, which excludes non-cash charges of stock compensation and depreciation, 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. The full-year net loss per share was $0.83, compared to a net loss of $1.18 in the prior year. Under our 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. Additionally, as we announced concurrently with our preferred rates, we are in the process of refinancing our existing debt. Overall, our balance sheet has strengthened meaningfully, and we have a fully funded business plan through and beyond reaching profitability. Let me move on to guidance. Earlier this year, we announced restructuring actions that were necessary to right-size our cost structure, impacting both people and discretionary spending. Such decisions are never easy, but these 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 compared to 2022. We expect revenue to grow approximately 50% in 2023 and 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 elaborate a bit on these expectations. First, the $332 million of cumulative bookings backlog I noted earlier gives us high confidence in 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. In addition, 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 made only a minimal contribution to our revenue up to this point, but the underlying customer foundation and pipeline of activated stores is building rapidly. Also noteworthy is that this vertical has a very attractive financial profile, with more predictable revenue streams, better scalability, and faster conversion of initial customer contracts 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 revenue to be in the range of $43 million to $50 million. We expect this revenue to build throughout the year, with each quarter being larger than the last, due to the 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, and we expect to see a similar trend this year. To summarize, we have taken the important steps to set us up for long-term success. While 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, and customer traction is strong. We are extremely excited about our path forward. Thank you, and we will now move to Q&A.

Operator, Operator

And today's first question will come from Mike Latimore with Northland. Please go ahead.

Mike Latimore, Analyst

A lot of interesting developments. Obviously, I guess first on the restaurant vertical, you seem fairly positive about that vertical. I guess, can you just give a little bit more color there? I mean, how many restaurants are you currently deployed at? And when you talk about pipeline, is that business that's about to be deployed, or is that business that you still need to win? And then, I guess also it seems like this would be applicable to very large chains. Are there any large restaurant chains that are rolling soon?

Keyvan Mohajer, CEO

So, Mike, I think I'll start. So, a couple of points. Yes, when I alluded to the pipeline in my prepared remarks, I mean, generally, we—obviously, we have a lot of conversations going on, and we sort of have an initial pipeline, and then we venture into our CRM systems when it's in a more advanced stage. So the qualified leads that I'm referencing are ones where there are deep conversations occurring with decision makers at the restaurant, where there's clear line of sight to a significant opportunity. Whether it's small and medium enterprises, it could be one to single-digit location businesses on the enterprise side. They could be 10s or 100s, and we definitely have a suite of both small-medium mid-market and enterprise-level customers with hundreds of stores. We previously mentioned White Castle, as an example chain that has over 350 stores around the nation, and we're activating and live in several of those and scaling. I would say that, in terms of the number I mentioned, thousands of advanced-stage pipelines refer to those that are not yet paying us a monthly fee; they are still in the pipeline. This means they are late-stage conversations. In many cases, what happens is we gain traction in late-stage conversations with, let's say, a pizza restaurant where they have certain features they need, maybe they need customization for specific requests. So in many cases, there’s really active engagement, just requiring us to add some features and functionality. We have hundreds of restaurants signed up at this point, 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 can be very rapid, especially in restaurants that have multiple stores. Because once you ingest that menu upfront and custom-develop the capability and the voice, moving to restaurant number two or three is very fast. In some cases, if it involves additional drive-through features, there might be some acoustic challenges to figure out, but generally speaking, especially in quieter environments where outside noise isn't an issue, it could be much more rapid. I rambled a little bit there, so maybe I'll pause here.

Mike Latimore, Analyst

And then, on the Chat AI service, you mentioned that it is both a direct-to-consumer business enabler type of service. How do you think about the go-to-market there?

Nitesh Sharan, CFO

Yes, it will be both, to offer that to our existing customers, car makers, and other partners. SoundHound has historically had direct-to-consumer applications and products, and our existing applications have received over 300 million downloads. So that's something that is part of our DNA; we're really good at it, and it's good momentum to take advantage of that experience.

Mike Latimore, Analyst

Right, and just last one, can you provide a little more detail on your activities with Qualcomm? That seemed like an important partner that you announced last year. Maybe just a little bit more feel for how that partnership is going?

Keyvan Mohajer, CEO

Yes, we had a really good demonstration; we had a joint demo at the Snapdragon Summit a few months ago. They also showcased at CES. They are bundling our voice AI solution into their chipsets, and they can be our channel partners and sell it to our customers on our behalf. It's a combination of their chipsets and diverse technologies with our voice AI solutions, so it's a very meaningful partnership.

Operator, Operator

One moment for our next question, which comes from Brett Knoblauch with Cantor Fitzgerald. Your line is open.

Brett Knoblauch, Analyst

The first, I guess, is on the profitability guidance. You've taken a lot of action to kind of improve profitability over the last couple of months. What assumptions do you have to get to the positive adjusted EBITDA in the fourth quarter? What can we expect from the gross margin front, absolute off X basis? If we look at the run rate X into the quarter, should we expect that to decline by about $10 million on a run rate basis? Or what should we be considering for that?

Keyvan Mohajer, CEO

So, first of all, I'll start at the top. We guided for 50% growth, and I highlighted that is going to be back-end loaded. We are expecting to ramp throughout the year. Part of that is seasonality that comes with the pillar one and predominantly the auto business. But number two, I should say auto and devices. So there's seasonality associated with things like TV sales, etc. as well. But then also with our pillar two, which involves restaurants, as we continue to scale, getting traction there will build on a monthly subscription basis. That compounding will have a positive impact and that should grow throughout the year. There’s a bit of seasonal impact, and regarding margins, we're not really guiding on margins. But I'd say overall, our long-term goal is to maintain levels above 70%. The 70% plus level that we've been delivering this year is very achievable, given we go into a diversification of products from cloud to edge. I mentioned in my prepared remarks that, throughout the year, we have been migrating towards cloud, which has had a drag on 2022's margin, but that should be mostly completed now. Additionally, there are also actions we’re taking to drive efficiencies around margin, particularly as we scale, with respect to both cloud and edge solutions, since they tend to offer a more favorable gross margin profile. So as you put it all together, we expect the gross margin to stay positive vs. what it was in 2022. Regarding OpEx, I mentioned a full-year savings of $60 million. The first quarter will have some restructuring costs, but in the end, we should be largely through all restructuring activity by Q1, resulting in savings in OpEx. When you look at our OpEx items, our metrics for R&D, sales and marketing, and G&A were all subject to significant reductions on both headcount and discretionary expenses. You can do the math, and this will give us confidence in achieving adjusted EBITDA profitability in Q4.

Brett Knoblauch, Analyst

I have one follow-up. The new kind of generative AI chat product. Is this going to be more like a chatbot? Is it going to be more voice-driven? How do you plan on monetizing that solution and maybe what's your timeline for when you expect monetization to occur? Is this something that we should expect to contribute to revenues this year?

Keyvan Mohajer, CEO

The demo you heard was voice-based, so the user was talking to a mobile app, and it was responding. We believe voice absolutely unlocks the power of generative AI. Typing is not as compelling as voice because it can facilitate faster interaction and more freedom in conversation. So, it will involve text input, as well as voice; however, we think voice will be the dominant method. That's one of our differentiators—we bring our own ASR technology. I seriously believe this is the first time we can deliver a voice assistant to end users that they've wanted for more than a decade. You may remember when Apple launched Siri more than 10 years ago; there were all these ads on TV that made promises of opening up conversations with an assistant. Users loved the idea they rushed to it, but they quickly became disappointed because it could only handle a few things like asking questions about the weather or stock prices, setting timers, etc. It was still better than nothing, which meant users adopted it, but it wasn’t what they imagined. Now, more than a decade later, we can finally deliver that experience users have desired for so long. We know they want it because we have been in this business for a long time, and we know that users want it. Very few companies can utilize this opportunity because just having a voice interface to a large language model is not enough. A simple voice interface will typically fail to handle real-time search queries like asking for the weather or sports scores, setting timers, managing calendar events, or sending messages. To truly deliver this ultimate assistant experience, you need both the generative AI language model and existing assistant domains that users demand, with a voice interface on top of it. Only a handful of companies can take advantage of this situation, and SoundHound is very agile in this regard, allowing us to move quickly. Stay tuned for our announcement later this month regarding more details.

Nitesh Sharan, CFO

Just to add, generative AI is certainly the demonstration I provided, but we've also discussed Dynamic Interaction—our next-generation product for automotive—and there's significant interest there. In this space, we believe that voice is an important modality, but multimodal interaction is just as exciting. Sometimes using voice input and output makes the most sense, while other times, it could involve voice and touch input with visual output. Our Dynamic Interaction capability allows us to do that in real time. That's where the future is going—very rapidly. There are numerous applications and use cases we're excited about, and monetization will follow as we see them come to fruition in the near term.

Operator, Operator

Thank you 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, CEO

Thank you. When we founded SoundHound, we envisioned seeing voice-enabled AI in our lifetime. However, we couldn't have fully imagined the vibrant environment of AI innovation we find ourselves in today. Our conversational AI has gained prominence across industries, and we're confident that as the only independent cross-industry AI platform, we are in a strong position to deliver best-in-class technology to even more global brands. We continue to execute, and 2022 was a pivotal year for introducing new products and building new partnerships. We're excited about where we are and looking forward to a strong 2023. With that, I thank you for joining us on the call today. I look forward to speaking with you when we report our first quarter 2023 results. Thank you.

Operator, Operator

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