azure-speech

The virtual secretary, Lisa, is designed to interact naturally with users through text, voice, emotion, and a real-time animated avatar.

Text-to-speech for Zotero 10: more voices, word and sentence highlighting at once in your own colors, speed and navigation shortcuts, one voice across documents, settings backup and reading-position sync through WebDAV.

A fascinating demo website built with Node.js and Azure OpenAI o series/gpt4o-realtime/gpt4o series model. This project serves as a great starting point for developers who are interested in developing chatbot applications using JavaScript and Azure OpenAI API.

开源本地版 Language Reactor + ELSA：把任意视频变成听力 / 跟读 / 发音训练 · Open-source local alternative — turn any video into listening, shadowing & pronunciation practice

A self-hosted app that turns RSS feeds into conversational podcasts for commutes. 将 RSS 转成对话式播客，让通勤成为轻松获取信息的时刻。

Enhancing Patient Care with OpenAI: A Blazor and Azure Speech AI Medical Assistant Web App

🎙️ Voice-to-text typing application powered by Azure Speech Services. Supports multiple languages with automatic language detection, mixed-language recognition, and real-time speech-to-text conversion. Perfect for multilingual users and accessibility needs.

芯语伴 SprechMate：和 AI 用 23 种语言聊天 → 一键生成母语原声 → 录音跟读 → Azure 发音打分。纯静态 PWA，数据全在本地。| Chat with AI in 23 languages → one-tap native audio → record & shadow → Azure pronunciation scoring. Static PWA, all data stays local.

Real-time AI voice conversation platform with WebSocket, supporting streaming STT/LLM/TTS

Turn highlighted text into natural speech with Amazon Polly, Azure, Google Cloud TTS, OpenAI, or any OpenAI-compatible server: one browser extension, your own keys.

Copilot ASR benchmark for Azure Speech accuracy testing, command recognition, realtime transcription, and speech error analysis.

Hold a key, speak, get context-aware AI-polished text typed at your cursor. Windows native, BYO Azure/OpenAI keys, MIT.

AI-powered DSA practice platform with Socratic hint-based problem solving and voice mock interviews — Node.js/Express/MongoDB backend, React frontend, Google Gemini for hints/feedback, Azure Speech for voice interviews.

Developer playground for Azure Voice Live, Azure Speech, real-time voice agents, STT, TTS, and browser audio experiments.

Create narrated radial vocabulary and word-root videos with customizable layouts and multilingual TTS. 词根与词缀放射视频制作工具，支持自定义布局、多语言朗读和 MP4 导出。

SpeakRight pronunciation practice: Windows Desktop and cross-platform Browser Edition

Azure Voice Live car assistant demo for automotive AI voice agents and real-time in-car speech interaction.

Real-time AI voice interpreter demo with Azure Voice Live, Azure Speech, and speech translation.

Local meeting screen recording and speech-to-text for Windows. (Foundry Local & Azure Speech)

Internship project at WizeCare: Developing an automated video translation system that extracts speech from video, translates it into multiple languages, and regenerates dubbed audio in the target language – beyond simple subtitles, using a fully programmatic pipeline.