SoTA open-source TTS

Voice Activity Detector (VAD) : low-latency, high-performance and lightweight

Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.

An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

On-device intelligence.

AI wearables. Put it on, speak, transcribe, automatically