Awesome GitHub RepositoriesStreaming Audio Generators

F5-TTS is a text-to-speech system that utilizes a flow matching engine and diffusion transformers to generate fluent synthetic speech. It functions as a multilingual speech synthesizer and neural training framework, providing tools for voice cloning and high-performance inference serving. The project distinguishes itself through a voice cloning toolkit capable of mimicking specific speaker characteristics and tones from reference audio clips. It supports cross-lingual generation, allowing for the synthesis of audio across various global languages or the mixing of multiple languages within a s

MeloTTS is an open-source text-to-speech library that generates natural-sounding speech across six languages, with the ability to mix two languages within a single utterance. Its architecture combines a token-based text frontend with a language-agnostic acoustic model, enabling it to handle bilingual code-switching and produce streaming audio output in real time. The system is designed to run efficiently on standard CPU hardware without requiring a dedicated GPU, using a lightweight neural network for real-time inference. It supports English, Spanish, French, Chinese, Japanese, and Korean, an

Orpheus-TTS is an open-source text-to-speech system that generates human-like audio with controllable emotional tone and the ability to clone voices from short audio samples. It is built on an architecture that treats speech generation as a language modeling task, using a large language model trained on text-speech pairs to produce audio tokens autoregressively. The system distinguishes itself through several key capabilities. It supports emotion-controllable speech synthesis by embedding emotional and intonation markers directly into text prompts, allowing the model to condition its output o

Neutts is a neural text-to-speech engine designed for real-time streaming output on edge devices such as phones and laptops. It supports voice cloning from short audio references, enabling zero-shot reproduction of a target speaker's voice, and can be fine-tuned or retrained from scratch for custom voices and styles. The system distinguishes itself through a decoder-only architecture that halves memory and accelerates generation on constrained hardware, combined with quantized model inference for reduced memory footprint. Its streaming decoder loop interleaves synthesis with playback, deliver

mlx-audio is an audio processing toolkit built on Apple MLX that provides speech transcription, text-to-speech synthesis, voice cloning, and audio source separation using local models. It offers an OpenAI-compatible REST API and web interface for running audio generation and transcription tasks, enabling drop-in integration with existing tools that follow that endpoint structure. The toolkit supports text-prompted audio source separation, allowing specific sounds to be isolated from mixed recordings based on natural language descriptions. It also provides voice cloning from a short reference

Urho3D is a cross-platform 3D game engine written in C++. It uses a component-based scene graph to compose game objects from nodes and attached components, separating transforms from behaviors for modular design. The engine integrates AngelScript and Lua scripting for game logic, uses the Bullet library for physics simulation, and renders scenes with OpenGL or Direct3D through forward, deferred, or light pre-pass pipelines with customizable render passes and shadow mapping. The engine distinguishes itself with a built-in visual scene and UI editor for composing 3D worlds and interface layouts

Oboe एक नेटिव C++ लाइब्रेरी है जिसे एंड्रॉइड पर उच्च-प्रदर्शन, कम-विलंबता (low-latency) वाले ऑडियो एप्लिकेशन बनाने के लिए डिज़ाइन किया गया है। यह विभिन्न एंड्रॉइड ऑपरेटिंग सिस्टम वर्जन्स में ऑडियो स्ट्रीम्स, सैंपल रेट्स और हार्डवेयर रूटिंग को मैनेज करने के लिए एक एकीकृत रैपर और नेटिव API के रूप में कार्य करता है। यह लाइब्रेरी रनटाइम पर सबसे कुशल ऑडियो बैकएंड को स्वचालित रूप से चुनकर एक सुसंगत इंटरफेस प्रदान करती है, जो सबसे कम संभव विलंबता सुनिश्चित करने के लिए AAudio और OpenSL ES के बीच स्विच करती है। यह सिस्टम मिक्सर को बायपास करने के लिए एक्सक्लूसिव-मोड हार्डवेयर एक्सेस को सक्षम बनाती है और ऑडियो प्रोसेसिंग के लिए एक उच्च-प्राथमिकता वाले एसिंक्रोनस पुल मॉडल का उपयोग करती है। Oboe ऑडियो इंजीनियरिंग क्षमताओं की एक विस्तृत श्रृंखला को कवर करती है, जिसमें वास्तविक समय सिग्नल प्रोसेसिंग, प्रोग्रामेटिक वेवफॉर्म सिंथेसिस, और फुल-डुप्लेक्स ऑडियो रूटिंग शामिल है। इसमें ऑडियो फॉर्मेट कन्वर्जन, इफेक्ट्स पाइपलाइन मैनेजमेंट, और डिवाइस डिस्कनेक्शन को संभालने के लिए हार्डवेयर रूटिंग चेंज डिटेक्शन के लिए सिस्टम शामिल हैं। इस प्रोजेक्ट में ऑडियो विलंबता को मापने और प्लेबैक ग्लिच का पता लगाने के लिए डायग्नोस्टिक टूल्स, साथ ही ऑटोमेटेड परफॉरमेंस टेस्टिंग यूटिलिटीज भी शामिल हैं।

This project is a neural text-to-speech system and voice trainer that converts written text into spoken audio across a variety of global languages and regional dialects. It functions as an ONNX-based engine capable of performing fast offline inference and uses a phoneme-based controller to manage precise pronunciation. The system distinguishes itself through a comprehensive toolkit for neural voice training, allowing for the creation of custom single-speaker or multi-speaker models. It supports the export of these models to a standardized open format and provides hardware acceleration via gra

This Python SDK provides a comprehensive toolkit for synthetic audio generation, voice cloning, and the development of conversational AI agents. It enables the creation of lifelike spoken audio from text, the replication of human voices through custom cloning, and the deployment of real-time voice agents capable of interacting with external large language models. The library distinguishes itself through deep integration of conversational AI capabilities, including the design of agent personas and the execution of real-time actions via APIs. It supports professional-grade audio production thro