Abstract: The embedded offline speech recognition system deploys a pre-trained end-to-end model on an embedded device. It maintains high accuracy while eliminating reliance on network connectivity and ...

Google launched a free offline AI dictation app on iOS, highlighting a shift toward private, on-device speech-to-text tools.

President Donald Trump speaks to the nation from the White House on April 1, 2026. Reporter In a speech marking just over a month since the U.S. and Israel launched attacks against Iran, Donald Trump ...

中文说明见 README.zh-CN.md. An Android app that executes selected text as Python code via the system Process Text menu and shows structured results in a dialog-style overlay. Some apps do not expose ...

Enterprise AI company Cohere on Thursday launched its first voice model: Transcribe is an open source automatic speech recognition model that can be used for tasks like note-taking and speech analysis ...

--conv-frontend=./sherpa-onnx-qwen3-asr-0.6B-int8-2026-03-25/conv_frontend.onnx \\ --encoder=./sherpa-onnx-qwen3-asr-0.6B-int8-2026-03-25/encoder.int8.onnx ...

Abstract: This paper introduces RAY, an offline multimodal desktop assistant designed to enhance human-computer interaction through the integration of voice commands, text input, and real-time ...