Ellis is an AI notetaker specifically designed for in-person meetings, catering to individuals who need to capture and recall information from face-to-face interactions. Its primary purpose is to provide a seamless and intelligent way to document conversations without the need for laptops or additional hardware, relying solely on an iPhone or Apple Watch.
The challenge Ellis addresses is the difficulty of accurately capturing and recalling details from in-person meetings, especially when multiple people are speaking. Traditional note-taking methods can be time-consuming and prone to errors, while digital solutions often focus on online calls. Ellis aims to bridge this gap by offering a dedicated tool for physical interactions, ensuring that valuable information is not lost.
One of Ellis's key features is its ability to accurately identify speakers within a conversation. This is achieved through voice enrollment and advanced diarization techniques, which distinguish between different voices even when they are recorded by the same microphone. The platform also provides a user-friendly interface for tagging oneself and other participants, ensuring clarity in the transcript.
Another significant capability is the ability to ask questions about any recorded conversation. Users can retrieve specific information, decisions made, or any details they wish to revisit simply by posing a question. This interactive feature transforms static transcripts into dynamic knowledge bases.
Ellis also offers a unique search functionality based on location. If a user forgets a name or a specific detail, they can query the system using a place, such as "what did we agree on during our walk in Fort Greene?" This allows for context-aware retrieval of information.
Privacy is a core consideration for Ellis. Recordings are automatically deleted once the transcription process is complete, ensuring that sensitive information is not stored unnecessarily. This default privacy setting aims to build user trust and confidence in the application.
Ellis operates by recording audio from in-person meetings using an iPhone or Apple Watch. The audio is then processed to generate a clean transcript with speaker identification. Users can interact with the transcript by asking questions or searching by location. The system utilizes voice enrollment for personalized speaker recognition and provides tools for manual speaker tagging.
The benefits for users include improved recall of meeting details, enhanced productivity by reducing manual note-taking, and the ability to consolidate information from various personal and professional contexts into a single, searchable repository. This allows for a more comprehensive understanding of conversations and their outcomes.
Ellis is suitable for a wide range of use cases, including coffee meetups, on-site sales meetings, therapy sessions, doctor visits, interviews, and teacher-parent conferences. It is designed for individuals who need to capture information from any in-person interaction where accurate recall is important.
The product is available for iPhone and Apple Watch, indicating its mobile-first approach. It leverages technologies like AssemblyAI for speaker diarization and Pyannote for speaker embeddings, with user voice enrollment for personalized reference. The product is offered for free, with a focus on consumer use.
In summary, Ellis provides a privacy-conscious, AI-powered solution for capturing and recalling information from in-person meetings, empowering individuals to stay organized and informed without the need for traditional note-taking tools.