All Voice AI Tools

Small project with the help of javascript and speech synthesis web API.

Vocaloid-style Arabic TTS desktop editor built with Electron + BayanSynthTTS

Examples showing how to build lip-synced voice agents using AvatarKit by SpatialReal

A lightweight, high-performance voice cloning TTS system based on Coqui TTS...

Create deepfake video by just uploading the original video and specifying...

Audio samples from "Zero-Shot Long-Form Voice Cloning with Dynamic...

Turkish Speech Recognition Project / Türkçe Konuşma Tanıma Projesi

Fluid dialogue manager plugin for Godot 4.x built on RiveScript

Get the text from your video/audio with a simple Telegram bot — fast and easy

A simple speech assistance in python made with the help of pyttsx3,...

Nhận dạng giọng nói Tiếng Việt sử dụng model Quartznet (Nvidia) + flask demo

Demonstração do acionamento de dispositivos IoT através de comandos de voz,...

An AI Recieptionist Flask App with STT, TTS, FaceRecognition,...

This Python script creates a voice-controlled desktop assistant capable of...

Transcribe audio with whisper in zig

Sonori is a fully local STT app for linux (wayland).

This repository includes all the essential scripts and notebooks required...

A tool for crawling and creating audio dataset

Free version of: Whisper Flow, Aqua Voice, Willow Voice, SuperWhisper MacWhisper

An AR+AR TTS attempt.

Simple TTS tool made with Fresh

A Raspberry Pi is useful in all kinds of ways, even if you are looking to...

Clock with TTS for WaveShare ESP32-S3 Touch LCD 1.85"

A front-end for Dr. Sbaitso done in Zig and Raylib.

My first repository on github. Interactive CLI-based RoboSpeaker in Python....

🔊 Clone voices easily with this lightweight Python app that synthesizes...

🎤 Voice Studio - 语音识别与合成工具箱，支持实时流式转写、CPU推理、离线模式、桌面悬浮话筒 | ASR & TTS toolkit...

A Speech Recognition web app that converts speech to text in real time.

python tryout projects

AI-powered PDF to audiobook converter with LangGraph workflow orchestration....

A voice-controlled spin on "Who Wants to Be a Millionaire?", made with Unity

This is a web application that performs speech recognition on audio files....

A straightforward way to convert text to speech.

🏘 Vehicle 🏩 Speed 🏫 Detection 🏦 System 🕍 is 🚋 an 🚃 intelligent 🚟 computer 🚠...

Offline-first AI voice input for macOS. Hold-to-speak or tap-to-toggle,...

Ai project work about NAO robot strips planner.

Speech recognition using DNNs, script to create features, use kaldi for...

Build your own AI personal assistant using Python (Alexa and Jarvis both are...

It will convert our voice into text using Google speech API

Intent and Entity Extraction and Classification from audio files

Simple Speech Recognition Program Run on Raspberry Pi

Speech NLP Bootcamp

This repository contains a Python implementation of the paper "Iterative...

This project transfert the self supervised Wav2vec2 representation to low...

Libra.AI is a women's safety-focused voice-activated A.I. assistant android...

CampusSync — a modern MERN-based campus platform featuring lost & found, a...

AI-powered automatic video dubbing and transcription extension for VLC....

Offline speech-to-text system using Whisper AI with React and Node.js.

微信小程序全栈项目 语音识别 图片识别

Convert any PDF into a podcast episode using Gemini and Elevenlabs!

A professional todolist that stores information in local storage and uses...

A Project that gets you up and running with using speech recognition and...

Explainable WebAudio Klatt formant synthesizer with declarative TTS frontend...

Application to try out Google Text to Speech API

A smart text-to-speech (TTS) web tool with the feature of downloading...

A WebGL demo that combines virtual reality, speech recognition and synthetic...

Open-source voice AI evaluation workbench for dev teams

Ambient AI for macOS that works without the need to prompt. Uses local...

🎙 Headless real-time voice pipeline for LibreChat — LiveKit WebRTC +...

Live voice chat with LLM through discord

Text To Speech in regional languages like English, Hindi and Marathi using python

Simple Automated Voice Controlled Email Sender using SMTP in python

This is a Python3 based virtual assistant developed for Computer Science...

Speech Recognition 、Speech Synthesis 、Intelligent Dialogue

视频/音频一键转文字 + AI 总结 | CLI / Web UI / Telegram Bot 三合一

Recognize human emotion and affective states from speech

VOSKを使ったスピーカーやヘッドフォンから出力される音声のオフライン文字起こし

Simple HMM implementation

Simple Telegram bot for transcribing voice messages into text (STT) in...

Custom Built AI Chatbot using Huggingface's ai, enhanced with features such...

Converts image to speech to text using python and it's GUI feature

This is a proof of concept that generates speech based on parameters...

Notification Bot that calls user via teams or phone number and plays a...

For tieto hackathon 2018 to improve Finnish people financial well-being

Microsoft Speech SDK 11 - C# .Net 4 - Urdu Text-to-Speech System

A REST API that converts a text image to an mp3 file. The text image can...

Text-to-Speech & AI Bot With OSC Integration

speech recognition system to transcribe ATC voice data

a ASR(automatic speech recognition) model for Persian language based on...

Converts epub e-book files to mp3 audiobook files.

An application that allows you to read facts. It includes voice interaction...

An HTTP microservice using OpenAI to generate text-to-speech.

Concept of a multi-content sharing and reading social platform. In app...

A Simple Text To Speech Converter in java

Implemented a Desktop PC Assistant Application in Java. The Application can...

Aplicação de notas de áudio que se convertem em texto.

This is a android application that serves as simple digital signage...

Audiollect is a Notes to AudioBook Web App built with MERN stack , where...

🎵 Create and manage local-first AI-powered music with a fast, self-hosted...

I recorded 10 voices with the same words from myself and compared them with...

A smart clock which understands voice command and performs tasks accordingy

NaverTTS with C#

ICASSP 2020

Voice Assistant

A basic but fun virtual assistant made using Python

Notes App is an application to record notes and store them in the cloud in...

TensorFlow Speech Recognition Challenge -...

AI and AR-based digital memory lane and cognitive stimulation for dementia patients

Final Year Project on Speech Emotion Recognition with CNN and LSTM.

its a smart assistant that can answer any question