Researchers at Amazon have trained what they are calling the largest text-to-speech model ever created, which they claim is exhibiting “emergent” qualities — the ability to inherently improve itself at speaking complex sentences naturally. Called BASE TTS, for Big Adaptive Streamable TTS with Emergent abilities, the new model could pave the way for more human-like interactions with AI, reports suggest. Trained on 100,000 hours of public domain speech data, BASE TTS offers “state-of-the-art naturalness” in English as well as some German, Dutch and Spanish. Text-to-speech models are used in developing voice assistants for smart devices and apps and accessibility. Read more

OpenAI has debuted a generative video model called Sora that could be a game changer. In OpenAI’s demonstration clips, Sora depicts both fantasy and natural scenes with photorealistic intensity that makes the images appear to be photographed. Although Sora is said to be currently limited to one-minute clips, it is only a matter of time until that expands, which suggests the technology could have a significant impact on all aspects of production — from entertainment to advertising to education. Concerned about Sora’s disinformation potential, OpenAI is proceeding cautiously, and initially making it available only to a select group to help it troubleshoot. Read more

Global streamer Cineverse has launched an AI-powered search and discovery tool called cineSearch. Developed using the Vertex AI platform from Google Cloud, cineSearch will be released in public beta this spring. A waitlist has already been started, and Cineverse says it will be made more widely available in partnership with OEM and third-party streaming platform partners in the coming months. Simultaneously, the Los Angeles-based firm is rolling out a new ad platform called Cineverse 360, or C360 for short, that will connect brands across omnichannel services reaching 82 million monthly viewers at launch. Read more

MoviePass says it has sold more than 1 million tickets since relaunching last spring, and has also announced the first profitable year in the company’s 13-year history. Co-founder and CEO Stacy Spikes, who purchased the company out of bankruptcy in 2021, is giving artificial intelligence much of the credit for the turnaround. The MoviePass Cinematic Marketplace is an aggregator for the theatrical industry that uses AI and machine learning to improve attendance engagement and ticket sales. Spikes says hitting the milestones “highlights the powerful impact” the technology enhancements have had “from the previous business model.” Read more

Apple has taken a novel approach to animation with Keyframer, using large language models to add motion to static images through natural language prompts. “The application of LLMs to animation is underexplored,” Apple researchers say in a paper that describes Keyframer as an “animation prototyping tool.” Based on input from animators and engineers, Keyframer lets users refine their work through “a combination of prompting and direct editing,” the paper explains. The LLM can generate CSS animation code. Users can also use natural language to request design variations. Read more