Nuance Labs launches AI video persona Emma based on Nuplex 1.0
Nuance Labs has launched AI video persona Emma, whose response timing matches that of a human speaker at 89%. Emma runs on the full-duplex audio-visual model Nuplex 1.0, allowing it to speak while listening; her facial expressions begin reacting as users talk. Her appearance and voice come from a real actress who collaborated with Nuance Labs to record how she listens, reacts, and speaks. These recordings were fed into the Nuplex model to create distinct mannerisms for the character.
Continue looking at this topic
OpportunitiesTikTok AI product promotion with cumulative ten million views: how to find benchmarks, break down viral hits, and judge content direction ↗News and AnalysisGemini Omni supports multi-round video edits: how can you get closer to the final cut with each revision? ↗Open-source projectAfter an agent creates a vertical short video, how do you trace the facts in the narration back to their sources? ↗Hotly discussed viewsAI is tasked with creating educational videos based on implementation plans: how do we avoid scenarios where the visuals look great but the information is wrong? ↗Return to original text
A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.
Open AIHOT original