Speech Processing Flow Graph
-
Updated
Mar 23, 2026 - TypeScript
Speech Processing Flow Graph
Sybapse : Low-Latency Hybrid Edge Computing
Voice to Text service with text processing, including translation and summary. Chat service for local group projects, or (experimentally) online
Blueprint by Mozilla.ai for generating podcasts from documents using local AI
Awesome AI Tools for Game Development: A curated collection of the best AI tools, libraries, and resources to enhance game development workflows. From procedural content generation to NPC behavior, this repository gathers state-of-the-art AI solutions for game developers.
Moshi: open-source speech-text foundation model for real-time full-duplex voice dialogue. Uses Mimi neural audio codec. PyTorch, MLX (Apple Silicon) and Rust backends. Moshika & Moshiko voices.
Unofficial PyTorch implementation of VALL-E: zero-shot text-to-speech and voice cloning using neural codec language models. Train and synthesize speech from text with a single reference audio.
A Scalable Architecture for Text Correction and Normalization
Text Humanizer Pro is a Python-based project with a Streamlit frontend that transforms raw AI-generated text into natural, human-like writing.
JVM library for text generation, written in Kotlin and based on the C++ library llama.cpp
Gradio Template to make your AI app look prettier and to help in deplyoment by reducing the time, it serves as a template of sorts and also does more than look pretty there are some added functionality to help take things to worry about off your mind
A real-time multilingual translation application where users can speak or type to get instant translations along with audio outcome. Built using Flask, Streamlit, and used OpenAI API for translation, it supports 20+ languages and follows an standard server design to handle translation and speech as modular tools.
A Discord bot capable of fulfilling your artificial intelligence needs.
Fission AI is a multimodal AI platform that transforms text into images, videos, research reports, and rewritten content using state-of-the-art generative models—all through a single unified interface.
AI company, product, and tool collection.
This project demonstrates the use of Transformers for text generation using the T5 model. The project includes the necessary code for training the model on a custom dataset and generating new text.
Collaborate with your favorite LLM directly inside of your Jupyter Notebooks
The code for AAAI 2025 “Large Language Models Are Read/Write Policy-Makers for Simultaneous Generation”
Llama-3.1-Nemotron-70B-Instruct is a large language model customized by NVIDIA in order to improve the helpfulness of LLM generated responses.
Extract the most viral clips from a random youtube video.
Add a description, image, and links to the text-to-text topic page so that developers can more easily learn about it.
To associate your repository with the text-to-text topic, visit your repo's landing page and select "manage topics."