All Voice AI Tools

AI-powered daily audio news digests for accessibility. Generates...

Node.js module that provides bindings for the DecTalk Text-To-Speech library

Google text to speech translation using php.

Voice cloning demo page using ElevenLabs text-to-speech API — Node.js + Express

A locally-hosted AI Desktop Assistant capable of OS control, neural speech,...

Voice Assistant powered by Google Gemini AI, with speech recognition and...

made as a capstone project | powered by safaricom gebeya

Crimean Tatar-russian dictionary app for Android with offline text-to-speech...

iOS example app demonstrating on-device speaker diarization using FluidAudio...

A Flutter widget that provides a simple button for speech-to-text...

Virtual Assistant like Alexa and Google Dot

Tsundere Japanese maid AI with voice chat, bilingual dialogue, and emotion...

A futuristic, Siri-inspired AI voice assistant with real-time fluid visualization

An AI-powered voice librarian that listens to a user, finds relevant books...

AI-powered bilingual doctor assistant using Groq (Whisper + LLM) and...

For evaluating speech recognition system using the Corpus of Spontaneous...

Vits based Mongolian (Khalkha) TTS language model

PowerShell modules for text-to-speech (TTS) and speech-to-text (STT) across...

A Python-based AI desktop assistant designed to perform various tasks like...

Cross-platform .NET MAUI desktop client for the Sound Board voice engine.

Text-to-speech for AI coding assistants. Give your AI a voice with emotional...

Real-time VRM avatar lipsync MVP — Godot 4 + FFT visemes + OpenSeeFace

Voxtral Codec : Combining Semantic VQ and Acoustic FSQ for Ultra-Low Bitrate...

Privacy-First Neural Text-to-Speech for Linux (Wayland & X11).

テキストファイルからランダムに1行を選び、一定間隔でmacOSの音声で読み上げる学習用CLIツール

ブラウザで動く汎用暗記カードアプリ「AnkiFlow」。自動読み上げ（TTS）機能を搭載し、画面を見ない「聞き流し学習」にも対応しています。

CLI tool to generate spoken vocabulary study audio from a JSON deck....

Desktop app for PocketTTS with voice cloning audiobook creation,...

Python tool using Selenium and Chrome’s Web Speech API for speech-to-text in...

Javascript leveraging browser-native Web Speech API to convert any PDF to...

An asynchronous Python desktop application that extracts text from PDFs and...

Automatically generate Shorts Video using AI, stock video, and TTS

Converts Markdown and PowerPoint files into AI-generated video presentations...

idk if this is accurate. This was done in an afternoon. Used gemini 3 pro...

Multiple AI personas inside Foundry VTT with chat + ElevenLabs TTS. Create...

PodcastAgent uses advanced text-to-speech technology to create...

A command-line interface for generating high-quality speech using the...

Python Voice Synthesis - TTS/STT web app with voice cloning using Qwen3-TTS

【新人エンジニア向け】Mac環境でQwen3-TTSを使って音声合成環境を構築する手順ガイド。環境構築から日本語音声生成までステップバイステップで解説。

GPU-accelerated Qwen3-TTS server for NVIDIA Jetson devices

เว็บแอปพลิเคชันสำหรับแปลงข้อความเป็นเสียง (TTS) และแปลงเสียงเป็นข้อความ...

An intelligent AI companion system for Twitch streaming with VTube Studio integration

Open-source screen reader for Windows 11 — built in C#/.NET 9 with UI...

Mojo audio library: FFI-enabled, pure Mojo DSP.

Automated pipeline: Obsidian markdown → AI podcast scripts → TTS audio → RSS...

Finetuning Whisper ASR model for Belarusian language

A voice-based AI agent designed for a car dealership. This agent can...

Production-grade Python virtual assistant with full asynchronous support....

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

responsive voice TTS plugin for mycroft

Using app to control Voice Kit(smart speaker)

A streamlit based UI for editing speech

this repository concedes my project work done in my bachelors

A minimal tool that helps transforming fixed grammars into compiled Finite...

Voice Controlled Turtlebot 2i - ROS 🤖

*AFT is an audio translator nano framework* based on python who transcribe...

AI-Video-Transcriber is an intelligent, open-source tool that automatically...

JavaScript/Node.js SDK for TTS.ai API — text-to-speech, voice cloning, speech-to-text

Python SDK for the TTS.ai text-to-speech API

💻 Fale por mim is a web application in which the user can type their text or...

Learn Communication Language Effectively with Pictorial Story.

A notebook created for training StableTTS models in Google Colab easily!

Android Application for smart classroom, uses voice-based commands to...

Gemini-powered Chrome extension for smart translations. Features...

A Promise tts api, it depend on browser api window.speechSynthesis

UDP Client that listens for text messages and converts it to speech.

Automatic Speech Recognition ASR / Speech To Text STT demonstration using...

Offline desktop application for generating accurate subtitles (SRT) from...

Tencent TTS for Legado Reader 基于腾讯语音合成API的Legado(开源阅读)TTS服务.

A simple chatbot written in python which takes in user audio input, displays...

This code is designed to read chat messages from YouTube and Hearing from...

using Win SpVoice Interface (SAPI) with python to generate audio files with...

Natural Reader is a professional text to speech program that converts any...

A command line program to loudly tell time (in chunks of 5 minutes).

A Python Script that uses Cohere Language API and Elevenlabs Speech API to...

The ~MASTER-GIFT~ All-in-One Speech AI-Chatbot Nexus is an interactive...

The project introduces Maya, Multimodal AI Assistant with Face Recognition,...

台語語音轉文字訓練資料集，資料來源：教育部《臺灣閩南語常用詞辭典》。

Udacity Natural Language Processing Nanodegree.

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

TTS that can "speak as you type" using google translate (via simplytranslate.org)

Pika TTS is a small, local text to speech voice synthesizer package based on...

demo for web speech-recognition api

Tutorial on Speech Recognition using Convolutional Neural Network

A voice-driven project capturing emotional echoes from the heart —...

🗣️ Transcription (speech to text) d’échanges téléphoniques adressés au...

Convert audio to text using JavaScript, Speech To Text.

Czech diphone database for Festival: voice "ph"

A powerful, local speech-to-text transcription system that combines OpenAI's...

How to use Vatis Tech with HTML & JavaScript.

A voice-activated virtual assistant using Python and OpenAI.

The Praximedes project was developed to control LED lights (HappyLighting),...

Asistente personal web con entrada por voz (STT), salida por voz (TTS) y...

An Virtual Elderly Chatbot App Using Unity 5.6.2f1

Python Colab for speech recognition with wav2vec2. Since wav2vec2 requires...

TTS for local usage that works for all OS's, with a simple interface,...

Standalone application that allows users to keep track of their Vocal...

Lego ev3 brick automation

Caderno de Colab para síntese de voz (TTS) en galego usando o modelo ONNX de Celtia

A TensorFlow Implementation of DC-TTS: yet another text-to-speech model