Yasa-1 is available via APIs and as docker containers for on-premise or VPC deployment. It can understand not only words and phrases but also images, audio, and short video clips. The assistant can be prompted with the image of a product to generate a social media post promoting it, or it could be used to detect a particular sound or the source that made it. However, the company also emphasized that the assistant is still very new and has some limitations.
Key takeaways:
- AI startup Reka has announced Yasa-1, a multimodal AI assistant that can understand images, short videos, and audio snippets, and supports 20 different languages.
- Yasa-1 can be customized on private datasets of any modality, allowing enterprises to build new experiences for a myriad of use cases. It also has the ability to provide answers with context from the internet, process long context documents and execute code.
- Yasa-1's multimodal capabilities allow users to combine traditional text-based prompts with multimedia files to get more specific answers. However, the company acknowledges that the assistant is still new and has some limitations.
- Reka plans to give more enterprises access to Yasa-1 and work towards improving the capabilities of the assistant. The company, which came out of stealth just three months ago, is competing against deep-pocketed players, including Microsoft-backed OpenAI and Amazon-backed Anthropic.