All Voice AI Tools

Fully automated YouTube Shorts pipeline with a self-improving feedback loop....

A multi-project that contains UDP server, MQTT broker and a few sub-projects...

Voxtral is a state-of-the-art model developed to handle both speech...

基于pytorch-lighting框架搭建的端到端语音识别模型，目前还在实验中，性能在不断优化

List of open-source TTS, voice cloning, and music generation models

An alternative input module for Phosphorus Five, allowing you to use natural...

Python3智能语音助手

A macOS Tahoe app for transcribing audio/video files using Apple's on-device...

An AI Agent to work with Google Sheet using Natural Language

Ένα έξυπνο κουδούνι για το σχολείο μας - 1ο Επαγγελματικό Λύκειο Πύργου

保持原排版可选段的网页朗读神器

🗣️ Transcribe your voice to text easily on macOS. Just hold **Fn**, speak,...

AI Vtuber for Streaming on Youtube/Twitch

Code for my dissertation on "Distilling and Forgetting in Large Pre-Trained...

AI Vtuber for Streaming on Youtube/Twitch

An ONNX model for speech recognition of the Ukrainian language

Utilizando HTML5 SpeechRecognizer para Reconhecimento de Comandos.

🚀 Discover AI tools and resources to create faceless content for YouTube,...

A minimalistic yet powerful voice transcribing app that features precise and...

Speech recognition and synthesis app

Simple demo of client-side speech recognition

A TTS Trained on Universal Audio.

Audio Streaming for FreeSWITCH with backends powered by Azure, OpenAI, and Aristech

Easy-to-use Python library for converting English text into natural sounding...

Al MOM is an Al-powered meeting intelligence platform that delivers...

API that uses Tortoise and RVC to speed up text-to-speech generation.

Python tool for text-to-speech conversion with voice selection, usage...

🏃 💡 Talabat Hackathon 2022 API project

Java SDK for Palabra AI's real-time speech-to-speech translation API. Break...

A Bash script designed to make training sphinx4 and pocketsphinx acoustic...

An app that allows you to have voice conversations using the API of AI...

USING HTML , CSS AND JAVASCRIPT I HAVE BUILD A SIMPLE TEXT TO SPEECH CONVERTER.

macOS AI 翻译词典，基于 DeepSeek 提供智能翻译、词根助记、拼写纠正和语音朗读 | AI-powered dictionary app...

🎤 A real-time voice AI assistant built with Next.js and deployed on...

🐸💬 Coqui TTS Double Decoder Consistency samples

YouTube/audio transcription, image, video generation, AI voice (TTS) & OCR...

The speech recognition engine behind Speechnotes, based on the Webspeech-API

Local-first AI medical scribe running entirely in the browser using Chrome...

Voice Assistant — приложение на C# для управления компьютером голосом....

A gui to help make a text to speech dataset.

Privacy-first macOS transcription app with global hotkey recording. 100%...

A flexible Python tool for converting PDF documents to audio using various...

Reference architectures, cost models, and sales-engineering playbooks for...

PlayHT API client Go module

Java binding for Qwen3 ASR

Scripts e recursos para ASR em Português Brasileiro

🚗🤖 Agentic Connected Vehicle Platform — Agent orchestration 🤝, Model Context...

Myanmar Text-to-Speech with End-to-End Speech Synthesis

🏠 Turn any IP camera into a smart English tutor for your family. AI-powered,...

Official Swift API Client for the seven.io SMS Gateway

Consumer-grade voice cloning app using Coqui TTS - clone your voice from...

AI-powered summarizer for articles, PDFs, and Word documents with...

A screen reading accessibility tool

Neurovoz corpus of parkinosnian speech

Non-Human Identity Disclosure Standard for Healthcare Voice Workflows

Python project for Speech-to-Text and Sentiment Analysis. Supports English...

다양한 사용자를 위한 키오스크 개선 프로젝트 ✨

🎤 Integrate ElevenLabs Text-to-Speech and Speech-to-Text APIs seamlessly...

Voice controlled keyboard and mouse that is lightweight (minimal...

Python Text to Voice Package

A voice driven 3D chess game for learning Voice AI

🗣️ It's like Alexa, but for your computer. Highly modular, real-time voice...

Training notebook for Japanese TTS model with Tacotron 2

Library to reduce latency in voice generations from LLM chat completion streams.

Desktop based Personal Voice-Assistant Pi

Brief tutorial with code where you can automatically create a dictionary...

An Optical Character Recognition (OCR) System designed using Python to read...

Material for learning speech recognition, based on Microsoft teaching material on EdX

pico-tts-plugin

A functionless Android app that demonstrates a basic integration with the...

Its a Voice Controlled AI (Natural Language Processing) with some live face...

A repository for information related to the Data Analytics team's Advanced...

Simple, accessible Calendar for screenreader and blind users.

Parakeet MLX is a next-generation automatic speech recognition (ASR) engine...

Lots of miscellaneous scripts to work with Sphinx ASR files and other...

阿里云智能语音处理 Node 模块。

Uploading PDF files on Webpage, converting text present in PDF to speech and...

Parrot is a Talking Alarm App which allows the user to set up to 5 Alarm or...

bobby-snips-tts is an implementation of snips-tts written in Node.js with...

基于 Azure 文本转语音

Automatic video translator and dubber using Whisper, XTTS v2 for voice...

Persian Speech Recognition

Code and theory from Big Data Academy

Queries an API based on Edge-TTS and returns an audio file based on...

Voice cloning with 80+ emotions and multi-emotion mixing for ComfyUI

A repository for information related to the Data Analytics team's Data...

Bachelor's thesis carried at Universitat Politecnica de Catalunya in partial...

A Simple Voice Command Application powered by Java and Sphinx4 Speech...

Greeting PC, made with simple Visual Basic Script. Run file it will executes...

Voice Coding is all about writing code by voice commands.

Vector Quantizing speech representations

Automatic speech recognition (ASR) for Apple Silicon

Веб-сервис для озвучки текстов с использованием Microsoft Edge TTS

Converting Arabic text to speech in various languages with the versatile...

This repository is a collection of personal AutoHotkey v2 scripts designed...

Language Translator App - Translate text into multiple languages. Built with...

本项目是基于PaddlePaddle的语音合成项目，使用的是VITS，VITS是一种语音合成方法，这种时端到端的模型使用起来非常简单，不需要文本对齐等太复...

中文 vosk-android-demo

微软晓晓 语音合成接口

Fast C++ implementation of ESOLA using KFRLib, can be used for online...