speech-synthesis

A mobile web application that helps you convert spoken words to sharable/editable text 🎊

This project is a conversational AI program that uses speech recognition, text-to-speech, and the OpenAI API to generate responses to user prompts, allowing for a natural conversation flow.

Speech-to-Speech conversational AI using Azure OpenAI Service and Azure Speech Services

a simple speech recognition app using the Web Speech API Interfaces

Continuous Dictation Speech Recognition and Speech Synthesis in Win32

Arabic-first expressive zero-shot speech synthesis — Audar-TTS-V1 (Flash + Turbo + Pro). Voice cloning, expression tags, benchmarks, technical report & inference.

🎙️ CosyVoice LoRA 微调框架：LLM+Flow 联合训练，实现无 Prompt 语音合成