X Ambassadors: Adrenaline


In partnership with Microsoft and the platinum-selling band X Ambassadors, Listen created a voice-controlled interactive music video that takes you behind the scenes of the song "Adrenaline" – a wholly new kind of tech-driven music experience, featuring a "voice assistant" unlike any other.


Synthetic Voice Design, Voice AI, Text-to-Speech Translation


Interactive Audio Experience, Brand Activation


At Listen, we're interested in how the technology behind voice assistants and smart speakers could be used for audio storytelling. When audio content like a podcast can be listened to, but also interacted with, a whole new dimension opens up for engaging an audience and telling a story.

We've always imagined the end result being more than just a craftily designed voice assistant or novel podcast execution, but a truly new kind of interactive media with disruptive potential.


With X Ambassadors and Microsoft, we found partners similarly interested in combining music, storytelling, and interactive technology in a new way. On the band’s album The Beautiful Liar, lead singer Sam Harris is heard in short vignettes as the Shadow, a memorable character woven into the album’s narrative. We worked with Sam to record a list of 2,000 “utterances,” or syntactically varied sentences in the voice of the Shadow. We the used the recordings to train and build a comprehensive and highly realistic AI voice model using Microsoft’s Custom Neural Voice services.

Because the Shadow could say anything, we wanted to create an experience where fans could speak to it and get a response. Focusing on the single “Adrenaline” as a conversational meeting point for fans and the Shadow, we wrote an extensive branching-narrative script that customizes responses to the user’s natural-language inputs.

Sam Harris recording his voice to train the Custom Neural Voice
Custom Neural Voice reading back those same lines


The result? A truly new kind of audio experience combining elements of podcasting, behind-the-scenes rock documentary, and immersive voice app. Our browser-based experience appears at first like an X Ambassadors lyric video. But at key moments, the “tape” stops, the comically sinister eyes of the Shadow take over the screen, and the Shadow voice begins a conversation – facilitated by Azure Speech-to-Text technology – that teases out exclusive content covering the song’s themes and backstory.


The web experience gives fans the opportunity to directly interact with the band and the creative universe of The Beautiful Liar. And more broadly, it points to a future of voice technologies and narrative audio content pushing each other forward.

"Hearing it back," says Sam Harris, "I was so surprised at how accurately it captured the cadence. I like the idea of being able to use something like AI, because it’s still a bit of uncharted territory. We really hope fans get a chance to dive deeper into the song, and see a bit of the potential of what AI can bring to storytelling.”