All Voice AI Tools

GPU-accelerated Qwen3-TTS server for NVIDIA Jetson devices

Tacotron2 with BERT examples

Provides text2speech capabilities using ElevenLabs and Kokoro TTS

Ecommerce website with modern AI Chatbot feature

A simple voice AI bot on Discord

【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。

Community-built CLI for the ElevenLabs AI audio platform with TTS, STT,...

Point of Interest Error Rate (PIER) Metric for Code-Switching ASR: A...

A real-time Discord voice assistant powered by Llama 3, Whisper, and Web...

Vermeil is personal assistant just like Jarvis

NEMO (Naturally Evolving Model) is a voice controlled personal virtual...

PyroSpeak is a small Python wrapper library that uses big technologies like...

Fine-tune SpeechT5 for non-English text-to-speech task, implemented in PyTorch.

Text to Speech system for Hindi language

An AI-powered, voice-native chess platform built around real-time command...

Documented 6502 assembly code for the SAM voice synthesizer

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

An all-in-one GUI management toolkit built with PyQt6, offering a suite of...

Real-time translation of lectures on the get-go

Real-time AI-powered transcription and translation Chrome extension for live...

A cross-platform desktop app for instant text translation. Hover to...

Two-tier prosody + emotion analysis microservice: OpenAI-compatible Whisper...

A tool to slice your audio files into chunks using the Voice Activity...

Welcome to EchoCharm! This repository houses a dynamic text-to-speech...

Speech Recognition in python

An Urdu language voice assistant built with Python for speech recognition and TTS

Carina is a car assistant project to make driving simpler

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

Empowering your CLI agent with STT/TTS in VSCode.

A locally running Turkish text-to-speech application developed with Coqui...

Voice synthesis platform with TTS and STT. FastAPI backend, voice cloning,...

Elixir bindings to Kokoro-82M text-to-speech model

This is a voice assistant program for windows made of python language. No...

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

Qwen3-TTS Voice Cloning WebUI with automatic text chunking - Optimized for...

Implementation of FastSpeech 2

macOS menu bar app that reads text aloud using Deepgram TTS

豆包实时语音转文字桌面应用，按下快捷键或长按指定按键，语音识别结果自动输入到当前应用

Voice to text for macOS. Press a hotkey, speak, get instant transcription.

Push-to-talk voice transcription for macOS using MLX Whisper. Beautiful UI,...

FlowCue — native macOS teleprompter with real-time speech tracking, AI...

3D Mentor is an experimental AI-driven educational interface that combines...

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

This App is voice controlled and uses voice command for any task. It can...

Get started using Deepgram's Text-to-Speech with this Ruby demo app

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

Real-time transcription of Windows system audio to text via a floating,...

[시각장애인 버스 이용편의 개선 시스템] 영상으로 버스진입을 판단하여 음성안내하고, 버튼으로 탑승버스를 입력받아 LED 전광판으로 정차 유도 기능.

Clipboard monitor that converts copied text to speech (TTS) using...

Offline-native first speech-to-text engine built on whisper.cpp. Engine...

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

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

Interactive 3D exploration of insect morphology using real specimen–based...

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

📺 Making digital displays on kitchen appliances accessible for the blind.

Jarvis AI a program which respond to your commands with real voice and...

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

Proctoring using AI to automate the monitoring process using Audio and...

小説家になろうの読み上げ

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

Piattaforma web innovativa per il supporto dell'autismo e della...

AI Discord bot that acts as an insulting oracle. Ask questions by voice or...

AI Voice Assistant using Flutter , OpenAI and the bot supports four...

Free Speechify alternative - Stop paying $139/year. Listen to PDFs,...

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

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

SIP telephony automation toolkit — place calls via PJSIP, play WAV/TTS...

Convert markdown ections to audio files using multiple TTS providers - a...

Haz que tu navegador hable. Texto a Voz con JavaScript. 🔊

ConnectedRoom allows you to sync Home Assistant to Sports

CLI / Gradio app for the MLX (Mac M1-M4) implementation of KokoroTTS with...

Kokoro TTS - Ultimate Edition: A professional-grade Text-to-Speech system...

A TTS that runs natively on the browser using the kokoro.js library.

Any* to any to language voice translator built in python supported by google...

On-device Kokoro TTS for Flutter — high-quality text-to-speech using ONNX...

Kickstart your creative process with this convenient toolkit, integrating...

Yahboom Intelligent Voice Speech Recognition Module Voice Board 5V Power Supply

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

Using Snowboy and Google Cloud speech api in Electron for voice recognition

Vue Speech Input - Speech to text with Vue.js | Speech Recognition with Vue,js

マスター、お冷ショットで。

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

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

Craft expressive speech from text using a streamlined pipeline of voices,...

An introduction course on Speech Synthesis and Voice Cloning (Skoltech ISP'25)

Add sound to your TRUE friend and also co-worker

Electron app for sound file analysis with BirdNET.

Generate an accurate, timestamped transcript given an audio file and its...

Identifying individual speakers in an audio stream based on the unique...

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

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

🎥 Fully automated YouTube Shorts generator using Python, AI scripting,...

roberto but for telegram!

Google Meet Transcript Translator is a Chrome extension that translates live...

Vits based Mongolian (Khalkha) TTS language model

Portable multi-GPU text-to-speech server for Windows — 10 AI models, gateway...

A Streamlit-based web interface that converts text to speech using edge-tts...

Desktop speech-to-text app with 3D particle visualization, grammar...

Speech Recognition With Python | python语音识别

AI voice cloning and text-to-speech using XTTS — talk to historical figures...