And now you can talk to AI systems like ChatGPT. Out loud.
AI, a company that provides artificial intelligence-based voice interfaces for cars and other devices, said it plans to add voice-enabled access to generative AI applications such as ChatGPT, the wildly popular chatbot launched last November by the start-up Open AI.
The news, disclosed Tuesday morning, is likely to add fuel to an already red-hot stock and sector, as investors continue to look for plays on the AI trend. SoundHound (ticker: SOUN) shares jumped 43% on Monday, and then added another 13% in after-hours trading, to hit $4.56.
The stock was trading at $1.28 when ChatGPT was launched in late November 2022. SoundHound went public via a SPAC merger in April 2022.
Other AI-related stocks—including BigBear.ai (BBAI) and
(AI) have likewise had torrid runs in recent sessions.
on Monday announced plans for an experimental conversational AI service of its own called Bard, which is based on the company’s project LaMDA, for Language Model for Dialogue Applications. CEO Sundar Pichai said that Bard will draw on information from the web, which is a point of differentiation with ChatGPT, which at this point relies on a vast but not unlimited training model that doesn’t include current events.
scheduled a press event in Seattle—expected to start at 10 a.m. Pacific time on Tuesday—with Open AI to announce expanded use of regenerative AI software, potentially including the software giant’s Bing internet search engine.
Wedbush analyst Dan Ives sees potential for Microsoft to become a more serious competitor in search.
“While Bing today only has roughly 9% of the search market, further integrating this unique ChatGPT tool and algorithms into the Microsoft search platform could result in major share shifts away from Google and towards Redmond down the road,” he wrote in a research note. “With OpenAI’s co-founder and CEO Sam Altman on the podium with Nadella … at this event is a clear signal that Microsoft is looking to win this AI battle between Big Tech giants over the coming years.”
SoundHound AI last fall unveiled a conversation AI platform called Dynamic Interaction, for restaurant ordering systems and other applications. “Now Dynamic Interaction will also offer effortless, voice-enabled access to generative AI, meaning users can unlock relevant information and ideas – just by speaking naturally,” it said Tuesday.
The company released a demo that specifically focused on in-vehicle applications for the automotive industry. SoundHound notes that since 2016 it has reached agreements with 17 automotive brands to use its conversational AI platform.
It’s worth noting that SoundHound isn’t specifically announcing an agreement to work with ChatGPT. “We’re actually planning a future announcement that will go into more details on where responses of the generative AI portion will come from, but they are similar to the responses that ChatGPT would provide,” the company said in response to a query from Barron’s.
The company offered an example of how the system would work.
Imagine you are planning a day in the Bay Area. In the example, the driver asks, “Can you help me plan a fun day of hiking in San Francisco for tomorrow?” And the app responds, not in text, but in audio, with a suggested itinerary.
“Start at Lands End trailhead. This trail offers amazing views of the Pacific Ocean and the Golden Gate Bridge. Then go to the Sutro Baths ruins, an old public bathhouse which has been converted to a park with trails and scenic views. Then finish your hike at the famous Seal Rocks, where you can enjoy the beautiful sunset over the ocean.”
As a point of comparison, Barron’s asked ChatGPT the exact same question. The first suggestion was “Lands End: a scenic coastal trail with stunning views of the Golden Gate Bridge, the Pacific Ocean, and the Marin Headlands.”
A nice hike, no matter which AI you ask.
Write to Eric J. Savitz at email@example.com