AI Is Reshaping Sports Broadcasting, From Synthetic Voices to Real-Time Analysis
ESPN, NBC, Amazon, the NBA, IBM, and Telemundo are using AI for personalized programming, synthetic voices, live analytics, animation, and new production formats as broadcasters test how far automation can extend into the sports media experience.
Artificial intelligence is moving deeper into sports broadcasting, with major media companies and leagues using the technology to generate personalized shows, recreate recognizable voices, analyze live action, automate production, and develop programming that would be difficult to produce through traditional workflows.
The applications now extend across nearly every layer of a broadcast, from pregame production and graphics to commentary, highlights, analytics, and digital programming. At the same time, broadcasters are drawing different lines around how much of the sports viewing experience should remain distinctly human.
ESPN AI In Action
ESPN is using AI-generated commentary in SC For You, a personalized version of SportsCenter that delivers highlights, news, and video based on each fan’s favorite teams, leagues, and sports. The product uses AI-generated commentary derived from the voices of Hannah Storm, Gary Striewski, Christine Williamson, and Omar Raja and is available through the ESPN mobile app, ESPN.com, and connected TV devices.
Instead of having anchors record narration for hundreds of personalized combinations each day, the system allows ESPN to create individualized programs at scale.
“It really is helping us be able to reach fans and serve them at scale.” – Kaitee Daley, Senior Vice President, Digital, Social and Streaming Content, ESPN
ESPN plans to expand the personalized product beyond its original daily format into an always-on experience that can update throughout the day.
NBC Sports AI In Action
NBC Sports has taken a different approach to synthetic voice technology with its NBA coverage. The network worked with the family of former NBC narrator Jim Fagan, who died in 2017, to recreate his voice using AI. Fagan’s voice, closely associated with NBC’s NBA coverage from 1990 through 2002, is being used for select title sequences, show opens, and promotional material.
The AI voice supplements rather than replaces traditional voiceover artists working on NBC’s basketball coverage.
“Knowing that his voice will once again be part of the game he loved — and that a new generation of fans will get to experience it — is incredibly special for our family.” – Jana Silvia Joyce and Risa Silvia-Koonin, Daughters of Jim Fagan
The technology could eventually extend to broadcasters who are still actively working. Jim Nantz, CBS Sports’ lead voice for the NFL and the Masters, said he first experienced the accuracy of generative voice technology through an AI-created version of himself that someone sent him several years ago.
“I still have it in my phone. I was so blown away by it; it sounds exactly like me.” – Jim Nantz, Broadcaster, CBS Sports
Nantz said he is considering participating in an AI-related project that could allow his voice to continue being used beyond his lifetime.
“It’s a from-the-grave kind of a deal. Who knows where this AI is going, but it has the chance to call certain things for as long as somebody wanted to use it … It’s just extraordinary to think about the possibilities.” – Jim Nantz, Broadcaster, CBS Sports
The ability to license and preserve a broadcaster’s digital likeness is also creating a new rights category around sports talent.
“We, from the very beginning, had this vision that two things would be true as the space developed. Number one, that the need for protections and guardrails would only grow in importance, and number two, that over time the commercial opportunity would be astronomical.” – Alex Shannon, Head of Strategic Development, CAA
Amazon Prime Video AI In Action
AI is also becoming part of live game analysis. Amazon Prime Video has developed a growing collection of AI-powered Prime Insights for Thursday Night Football, using machine learning and computer vision to interpret plays in real time.
Defensive Alerts uses a predictive model to analyze defenders before the snap and identify players most likely to blitz. Coverage ID identifies defensive schemes in real time. Pressure Alert identifies defenders attacking the offensive backfield, while Prime Targets tracks open receivers as routes develop.
A newer feature, Pocket Health, analyzes tens of thousands of data points across the offensive line during a play to visualize threats to quarterback protection.
“We had this idea, and we didn’t really know how we’d get it done. And then somebody much smarter than us hopped in and said, ‘Let’s try something crazy.’” – Alex Strand, Senior Coordinating Producer, Prime Video
AI is also enabling sports organizations to produce programming for smaller audience segments that previously would have been difficult to support economically.
NBA + WSC Sports AI In Action
The NBA, working with WSC Sports, introduced The Alley & Oop Show, an animated series built around characters Alley, Oop, and Buzzer traveling to NBA cities and interacting with stories around players including Nikola Jokić and Victor Wembanyama.
Human voice actors provide the baseline performances, while generative AI assists the production team with scripting, narration, and animation. The NBA identifies episodes as containing AI-generated elements.
“Humans still build the show, but the generative AI engine is now doing all this heavy lifting at every step. What would normally have taken weeks or months can now be done in a day or two.” – Bob Carney, Senior Vice President, Digital and Social Content, NBA
WSC Studios describes its model as combining human creative development with AI scale and is also developing sports entertainment formats around other properties, including LaLiga and EA Sports.
During World Cup coverage, Telemundo, HeyGen, and CAA pushed generative AI further into live television production.
The partners created four AI-powered segments for Telemundo’s knockout-stage coverage that placed commentators in environments including Times Square, a private beach in Miami, and the midfield of Dallas Stadium without requiring those presenters to physically travel to the locations.
The segments ran 20 to 30 seconds during pregame programming from the quarterfinals through the World Cup Final and represented HeyGen’s first major live-broadcast partnership.
Individual generations took approximately five to 10 minutes, allowing producers to create about 20 candidate performances per hour. Dialogue revisions could often be completed within 15 minutes as matchups and scripts changed during the tournament.
The production used CAA Vault to manage the capture, storage, and licensing of the commentators’ digital likenesses and voices. Participating talent retained control over how they appeared and what they said.
IBM AI In Action
IBM has been developing another branch of AI-powered sports media around automated commentary, data analysis, and editorial scale.
Beginning in 2023, IBM introduced AI-generated spoken commentary for Masters and Wimbledon highlight packages, providing narration for moments that otherwise might not have received traditional commentary.
The company has subsequently shifted more attention toward AI-generated analytics and content discovery. At the Masters, IBM has made decades of historical video searchable. At Wimbledon, AI supports digital match analysis and app experiences.
For the 2026 U.S. Open, IBM and the USTA launched Serve Quality, an AI-powered metric that uses computer vision to evaluate multiple components of a player’s serve. The system tracks 21 body and racquet data points 50 times per second and is expected to process roughly 1.2 billion data points during the tournament.
AI also allows small editorial staffs to cover significantly more competition. At the U.S. Open, an editorial team of five can use AI-assisted workflows to produce written recaps across all 254 matches, including periods when as many as 17 matches are occurring simultaneously.
“There are ways that people think AI is scary. But being able to show the real-world value of how we can actually help people scale their productivity is what’s so meaningful in these partnerships.” – Kameryn Stanhouse, Vice President, Sports and Entertainment Partnerships, IBM
Fan adoption of AI is increasing, although trust has not grown at the same rate.
An IBM study conducted by Morning Consult in June 2026 surveyed 20,589 sports fans across 12 countries and found that AI use increased from 52% to 69% year over year. At the same time, the percentage of respondents who said they trust AI-generated sports content declined from 63% to 59%.
Among fans already using AI, 74% said they trust AI-generated sports content, compared with 27% among respondents who do not use AI. Accuracy was cited as the leading driver of trust in AI-powered sports information, with 45% identifying it as the most important factor.
NASCAR AI In Action
Not every experiment has produced a path toward broader automation. NASCAR used AI to provide live Spanish-language coverage of its 2025 Mexico City race but later said the organization would approach the experiment differently despite the technology performing as intended.
“One of the few things that brings everyone together is sports. It’s a really personal experience, and for us to automate that to a disconnected voice, I just don’t think is the right thing for our fans.” – Tim Clark, Chief Brand Officer, NASCAR
The emerging sports broadcast model increasingly combines human talent with machine-generated production. AI is being used to create programming that would otherwise be too expensive or time-consuming, personalize coverage for individual fans, surface live insights faster, and extend the voices and likenesses of established broadcasters.
For now, the largest media companies and sports properties are generally using AI to augment human-produced coverage rather than replace the central voices and personalities around live games. The technology is expanding the amount, speed, and variety of sports programming that can be produced while creating new questions around consent, licensing, authenticity, and how fans respond when parts of a broadcast are generated rather than performed live.
ESPN: SC For You and the Enhanced ESPN App
NBC Sports: AI-Generated Voice of Jim Fagan for NBA Coverage
Amazon: AI-Powered Prime Insights for Thursday Night Football
HeyGen: How Telemundo Reimagined World Cup Storytelling
