EdgeTTS Sharp is a library that provides an easy-to-use, realtime-streaming, multi-platform interface for text-to-speech (TTS) synthesis using Microsoft's Edge voices.
-
Updated
Nov 16, 2025 - C#
#
edgetts
Here are 18 public repositories matching this topic...
Language: All
Filter by language
Sort: Most stars
Sort options
🎬 Nano Cinema: An all-in-one local AI video production studio. Automatically orchestrates Llama-3 (Script), SDXL-Turbo (Visuals), EdgeTTS (Audio), and LTX-Video (Motion) into a seamless Python workflow. Create cinematic short films with no API fees, full privacy, and professional-grade editing logic included!!! 🚀
python automation ffmpeg gradio short-film text-to-video gradio-interface ai-video-generator local-ai text-to-video-generation sdxl-turbo llama-3 edgetts local-ai-development ltx-video local-ai-llm ai-video-generator-tool
-
Updated
Feb 5, 2026 - Jupyter Notebook
把微软 Edge 的神经网络语音合成能力,包装成 OpenAI TTS API 兼容格式,部署在 Cloudflare Workers 上。免费、快速、无需服务器!
-
Updated
Dec 23, 2025 - JavaScript
🤖A Voice-First Agentic AI for Government Schemes in Hindi. Built with LangGraph (State Machine), Groq (Llama-3), and EdgeTTS for low-latency, CPU-optimized inference without GPUs.
voice edge statemachine voice-first groq llama2 langgraph groq-api groq-integration llama3 agentic-workflow agentic-ai edgetts langgraph-agents
-
Updated
Jan 2, 2026 - Python
A TypeScript port of edge-tts. Small, fast, and easy text-to-speech using Microsoft Edge's online service.
-
Updated
Jan 5, 2026 - TypeScript
Text-to-speech conversion of Twitch chat messages using EdgeTTS
-
Updated
Jun 22, 2025 - TypeScript
A real-time (<500ms) voice AI concierge built with Next.js, FastAPI, and Gemini 2.5 Flash Lite. Features local RAG (ChromaDB) for policy retrieval, Tool Calling for live booking, and event-driven CRM logging to Google Sheets.
nextjs gemini-api crm-integration rag fastapi voice-agent generative-ai chromadb edgetts realtime-ai
-
Updated
Jan 9, 2026 - TypeScript
Virtual Operation eXecutor
-
Updated
Dec 22, 2025 - C
A Streamlit-based web interface that converts text to speech using edge-tts and transforms it into custom voices via RVC.
-
Updated
Apr 30, 2026 - Python
AI-powered video platform that lets users create short, engaging videos. With intelligent caption styling, customizable transitions, and background audio support, it empowers anyone to turn text into visually appealing videos with ease.
-
Updated
Jun 14, 2025 - TypeScript
AI-powered assistant using LLMs as backend(Hybrid-intelligence) , React Native, and FastAPI
react-native cross-platform tts low-latency stt web-search livestreaming interrupt-handling llm hybrid-ai animated-object edgetts presistent-memory
-
Updated
May 29, 2026 - TypeScript
Automatic Scenes and Short length video generator
-
Updated
Mar 11, 2026 - Python
Content Factory is a "Zero-Cost" local video automation pipeline designed to turn raw assets (Images, Videos, Script) into polished, high-retention short-form content.
content automation youtube video pipeline script nextjs edge tts texttospeech remotion remotion-video edgetts
-
Updated
Jun 15, 2026 - TypeScript
Alan is an Ai voice assistant With RAG and heavy LLM models and hybrid-intelligence
python nlp api streaming tts gemini sqlite3 streaming-audio gemini-api rag fastapi groq memmory ai-assistant llm hybrid-intelligence generative-ai groq-api ai-voice-assistant edgetts
-
Updated
May 29, 2026 - Python
This is a small app that takes your voice to a tts app, I made it to function as a proxy between my voice and streaming, bcs shyness.
desktop-app text-to-speech streaming tool tts speech-recognition speech-to-text stts speech-to-text-to-speech edgetts
-
Updated
Dec 8, 2025 - Python
Repository for the FLVM prototype.
flask imagemagick ffmpeg video-processing flask-application videos video-editing moviepy gemini-api openai-api ollama edgetts
-
Updated
May 25, 2026 - Python
DoublyDoo is a LangChain-based children's app that creates personalized stories based on a child's chosen genre and age. The app not only generates engaging stories but also reads them aloud and creates AI-generated images to bring the stories to life. Designed to spark creativity and make storytelling interactive and fun! 🚀✨
-
Updated
Feb 15, 2025 - Python
Tafsiri is an AI-powered speech-to-speech translation app that uses seamlessM4T and Edge TTS models. It is build using NodeJS, PostgreSQL, FastAPI, React (+ Vite), Nginx, and Tailwind CSS
-
Updated
Feb 12, 2026 - JavaScript
Improve this page
Add a description, image, and links to the edgetts topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the edgetts topic, visit your repo's landing page and select "manage topics."