All Voice AI Tools

A project for the toxic commentator sitting next to you, commenting on your game.

Text To Speech (Georgian, English, Russian)

In short, a voice-based app that detects signs of depression by your voice....

Voice Replay lovelace card

Allows you to have an engaging and safely emotive spoken / CLI conversation...

🎙 Yet another python script that speech your text

A small HTTP API wrapper for piper's texttospeech

This demo shows how to integrate the Webix UI library with the OpenAI...

Distributed, GPU-aware workload scheduler for heterogeneous clusters:...

Proyecto que reconoce la voz, la transcribe, la interpreta con IA y responde por voz.

AI Voice Agent for Techfest IIT Bombay Hackathon - Built using Murf Falcon...

Development of an embedded AI assistant fully operating locally on a Raspberry Pi 5.

A straightforward deep learning pipeline for audio classification using a...

Fast, local neural text-to-speech CLI. No cloud. No latency. Just speak.

A modern random quote generator featuring ZenQuotes API integration,...

Python-based chatbot with speech recognition and voice responses

Swift library for Voice Activity Detection (VAD) using NVIDIA NeMo MarbleNet...

Voice-controlled AI assistant with real-time transcription, natural language...

Robot Mood Announcer is a small but delightful script that gives your Python...

Local AI voice cloning with Coqui TTS XTTS-v2 - Docker-ready, GPU-accelerated

VoxPen Desktop (語墨) — System-tray voice-to-text app. Global hotkey → dictate...

Always-listening voice agent pipeline (wake word, barge-in, streaming STT/TTS)

Suomalainen uutislukija - Lukee Helsingin Sanomien ja YLE:n uutiset ääneen....

A Chrome extension to interact with your Udemy AWS certification prep exams....

Claude Code plugin for voice notifications and TTS using ElevenLabs v3 -...

CLI text-to-speech tool with LLM summarization and translation. Reads text...

Learning vocabulary with text-to-speech and Anki

A Cross-Platform Voice-Activated Grading Interface, Unity-based application...

Speech Assessment API in FastAPI with HuggingFace 🤗

Dub audiobooks into any language using AI. Transcribe → Translate →...

A small collection of helper scripts for working with Google Text-to-Speech...

Takes an input text and transcribes it using zonos-v0.1-hybrid

Web Speech Recognition API turned into a React component -...

A Simple python tool to convert PDF documents into audiobooks.

📱 Flutter demo app for Arabic TTS 🎙️ — ONNX-based offline speech synthesis 🚀

A simple, lightweight web app that converts your voice into text in...

🎙️ Record and transcribe audio effortlessly using AI technologies for clear...

A collection of small, self-contained JS, HTML, CSS projects.

A sample application for on-device offline mobile voice inference using deep...

AI-powered radio DJ display for Plex and Spotify. Shows artist info, album...

PyCaptchaGenerator is a Python file that generates image and audio CAPTCHAs...

[YSC 2024] S2IGAN: Speech to Image Generative Adversarial Networks

Empathy Engine is an AI voice synthesis system that detects emotions in text...

A voice assistant for general applications focused on RPG setting

4 voices x 80 transcripts = 320 audio recordings

voxta unofficial docs for weirdo power users and creators, no affiliated...

Convert wsws.org articles to speech

Real-time, on-device speech-to-text for Mac. 22+ languages, live...

Multilingual input assistant for real-time chat. Type in your language, send...

AI-powered mock interview platform with real-time voice interviews and...

Generates audio for Anki flashcards using the Kokoro TTS engine with direct...

Grounded Sequence-to-Sequence Transduction Team at JSALT 2018

NeuraVoice is an AI-powered voice assistant that combines speech...

Python tool to download Rutube videos + generate AI subtitles. Features rate...

A Python-based voice assistant that uses OpenAI Whisper for speech...

A Flutter-based AI-powered voice assistant, powered by Gemini.

Provides a Dockerfile and instructions in order to facilitate the process of...

🎤 AI-powered Emotion Recognition from Speech. Detects human emotions from...

Super fast Multilingual TTS supporting 54 voices across 8 languages.

A voice-based language learning companion that helps you practice speaking...

It is a comprehensive real-time voice modification suite that allows users...

End-to-end speech intelligence pipeline — CNN speaker identification,...

#IT: This is the Mentally front-end application to help people with aphasia...

AI-powered farming assistant built with React + Flask that helps farmers...

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

Simple graphical front‑end for F5‑TTS

FlowTTS BYOK Replicate model wrapper - Tencent Cloud TTS with bring-your-own-key

This is a small app that takes your voice to a tts app, I made it to...

Real-time AI-powered translation for vernacular, slang, and regional...

🎙️ Terry: Local voice assistant for macOS with Alexa-style UX and superior...

PyVidNote is a mobile application built using Python that transcribes and...

Guides, phonetic tools, and speaking exercises to achieve clear and natural...

声ボタン - 文字を打つだけで話してくれるアプリ / Voice Button - Text-to-Speech App for Japanese

Soundforge is a modular, open-source pipeline for transforming emotionally...

ROOT is a Personal Voice Assistant, A friendly assistant you can talk to and...

A private, offline-capable Voice AI Assistant that runs locally on your...

The Moment | 片刻即永恒

For The Visually Impaired.

UTAUTAI(Unrestricted Tune Automated Technology Artificial Interigence)

🌐 Interact with PDFs using chat or voice in multiple languages, powered by...

Развертывание демостенда Yandex SpeechKit Hybrid с помощью Terraform.

🎧 Convert text notes to audio easily with Study Vault, a serverless AWS...

Repository for "LLM-based speaker diarization correction: A generalizable...

📊 Create engaging polls on Discord with admin-only access, advanced...

A pure Swift implementation for Kokoro TTS (Text-to-Speech) using local ONNX...

Misaki is a lightweight offline desktop voice assistant built in Python that...

On-device AI starter app showing how to use runanywhere-react-native to run...

This is a summary of Expressive speech synthesis papers. Now update: 13 May.

Deliver high-quality text-to-speech in the browser with 28 voices, no...

Mimicry is a complete, self-hosted zero-shot voice cloning system. Built on...

HOW TO RUN MICROSOFT VIBEVOICE LOCALLY

Qwen3 TTS Demo

🎙️ AI live stream co-host — real-time STT, LLM conversation & TTS with an...

A workflow to create a dataset of all TTS voices/languages available on...

🤖 Build a robust AI Doctor Assistant app with a Rust backend, Next.js...

BreathySync is an AI-powered respiratory health platform that uses 6-second...

This is a text-to-speech synthesizer that uses Piper TTS engine to read text...

A hybrid quantum-classical machine learning approach to speech recognition...

Simplified scripts for fine-tuning VibeVoice speech synthesis models with...

Docker image to make index tts run with Home Assistant