speech-to-text

An editor for speech-to-text transcripts such as AWS Transcribe and Mozilla DeepSpeech

Tensorflow implementation of "Listen, Attend and Spell" authored by William Chan. This project utilizes input pipeline and estimator API of Tensorflow, which makes the training and evaluation truly end-to-end.

Voice-driven writing, input, and cross-app work for your desktop.

Official Go SDK for Deepgram.

GSoC'2021 | TensorFlow implementation of Wav2Vec2

Free offline voice-to-text for macOS. Push-to-talk, works in any app.

Tutorials and my solutions to the Udacity NLP Nanodegree

一个中文语音转文字项目，封装自FireRedASR

ChatGPT 安卓版 - 私人定制 AI，只需要本地设置 API Key 就可以使用，聊天历史本地存储，如果想体验语音版本可以下载商用版，或是 自己集成 Azure Speech SDK（付费，现有免费额度送）。

openai/whisper + extra features

B.E.N.J.I.- The Impossible Missions Force's digital assistant

An autonomous, context-aware AI desktop companion. Built with Python, featuring real-time screen vision, custom ONNX voice synthesis, active window tracking, and a dynamic floating UI with reactive facial expressions.

A wayland overlay providing speech-to-text functionality for any application via a global push-to-talk hotkey

GPT-3 client for Windows and Unix with memories management that supports both text and speech in any language. Includes a free text2image

NOVA is a customizable voice assistant made with Node.js.

A multilingual ASR model that can recognize ten Turkic languages—Azerbaijani, Bashkir, Chuvash, Kazakh, Kyrgyz, Sakha, Tatar, Turkish, Uyghur, and Uzbek.

Privacy-conscious, open-source AI voice typing for Windows.

This repository outlines the procedures and general information for the Speech Translator project.

AskTube - An AI-powered YouTube video summarizer and QA assistant powered by Retrieval Augmented Generation (RAG) 🤖. Run it entirely on your local machine with Ollama, or cloud-based models like Claude, OpenAI, Gemini, Mistral, and more.

极简语音输入法，利用豆包 Web 语音识别实现全局听写。支持 macOS 、Windows 与 Linux/SteamOS（Steam Deck 手柄一键语音输入）