Speech

At Menlo, we’re reimagining how AI systems process and understand speech. Our approach focuses on creating unified models that handle both speech and text natively, eliminating the need for separate processing pipelines and enabling more natural human-AI interactions.

Research Projects

Ichigo (Aug 2024)

🍓 Ichigo: Rethinking Speech and Language Processing

Ichigo is a unified model that processes voice and text in a shared token space—eliminating the need for separate automatic speech recognition (ASR) or text to speech (TTS) pipelines. Ichigo handles speech natively to deliver seamless, real-time interactions.