All Voice AI Tools

Trainer and Evaluation scripts for fine-tuning Whisper models for the...

Deliver natural English speech with an ultra-lightweight, end-to-end...

Local Voice AI Assistant — faster-whisper STT + Ollama LLM + pyttsx3 TTS

🗣️ Elevate your workflow with NeuraVoice, an AI desktop assistant that...

Build real-time, low-latency voice assistants supporting 23 Indian languages...

NeuralMate 🤖 is your smart AI personal assistant 🧠, built to help you work...

Real-time bidirectional translation between speech and Namibian Sign...

Coach structured answers in real time during mock interviews with question...

Meet Vi, a modular, voice-activated AI assistant built in Python. It...

Voice & face-based secure payment and authentication platform with real-time...

Talk2Hire is an AI-powered hiring platform for secure online interviews with...

🎙️ Darmowy system Text-to-Speech dla polskich streamerów Kick.com. Łatwa...

🎧 Manage your audiobooks efficiently with this toolkit that converts Audible...

Use ChatGpt (openAi) by Voice i.e. using text to speech and speech to text....

Voice-enabled dog chatbot for emotional therapy. 🐶

SPARK — a Claude-powered robot companion for a neurodivergent kid. Built on...

Democratizing speech technology: the simplest way to create custom TTS and...

Example code to call Deepgram APIs on Amazon SageMaker

Real-time courtroom transcription

Voice cloning pipeline for AI agents — F5-TTS zero-shot inference, Whisper...

My City Speaks is an innovative web application that combines AI-powered...

Analyze any YouTube track's audio to extract key, BPM, chords, time...

Simple GUI application to emulate voice assistant workflow [just for fun]

Developed a Python-based virtual assistant that performs voice-controlled...

A Python-based system for real-time two-way translation between sign...

Kiswahili text normalization utilities for speech datasets (ASR/TTS)

👁️🗨️ Empower vision with SeeSense-AI, a browser-based tool that enhances...

VoxLibri: The Ultimate AI-Powered eBook to Audiobook Converter. 🎧📚 Transform...

A simple Anki add-on to globally disable all Text-to-Speech (TTS) playback

✨ Streamline your travel with DesiYatra, an AI system that negotiates local...

A web-based voice assistant that empowers visually impaired users to perform...

AI-powered TTS that detects emotion and modulates voice — speed, pitch — to...

Create voice overs with radio effects for DCS

Enterprise AI platform that transforms audio meetings into structured...

A simple React component to deal with browser SpeechRecognition

Made Silero Hostable for api requests

Fine-tuning the openai/whisper-small model on the 250h dataset for...

Personal Voice Assistant: Easy to change the code and making it suitable for...

Voxis is an intelligent voice assistant powered by Groq's AI models,...

Convert voice/text to animated avatar video

Production-grade on-device AI meeting assistant featuring real-time...

Post-training quantization on Nvidia Nemo ASR model

Murf AI's 30 Days of AI Voice Agents Challenge

🎤 Effortlessly integrate speech recognition capabilities into your React...

An audio recorder and speech to text with commands recognition created using...

AI-powered audio creation platform offering TTS, Voice Cloning, Voice...

Simple overlay for Windows, that listens for background sound and translates...

Real-time voice noise reduction app for macOS with virtual microphone support

This project demonstrates how to use Azure Cognitive Services with a...

An AI-powered web application that converts articles and URLs into...

An Android app written in Kotlin that performs OCR on Simplified Chinese...

🎧 Convert various document formats into high-quality audiobooks with Qwen3...

SpeakLow — a lightweight macOS menu bar app for voice-to-text input. Press a...

Data Pipeline for Text to Speech Project

Projeto MVP com processamento de áudio com IA local

🎙️ German TTS (FastPitch) with Thorsten voice / emotional

an interface for nerd-dictation in gtk

Using voice to keep a journal.

Local implementation for voxtral

HearPapers allows you to listen to PDFs (by converting them to audiobooks,...

Chat TTS for your streams.

A versatile app that converts images into short stories and lifelike audio...

🎤 Transform text into natural-sounding speech with Gemini-Live-TTS, offering...

Consume random jokes APIs and make them as a speech

Transcribe local files and browser streams (Canvas, YouTube, and more) using...

future - image based answer , UI Improvements , youtube link based summary

AI-powered audio source separation using Meta Demucs - Split songs into...

🎤 Generate and customize voices with ComfyUI HAIGC Qwen3TTS, integrating...

The application is deployed on the web of the ASL_Pytorch project, with...

Official repo for "Audio-Visual Speech Recognition In-the-Wild: Multi-Angle...

Automatic Speech Recognition for Low-Resourced Middle Eastern Languages -...

In this repo, I developed a step-by-step pipeline for a standard...

Twitch TTS бот с клонированием голоса через XTTS v2. Озвучивание сообщений...

Unreal Metahuman Conversation Speech to Speech backend and frontend.

End-to-end IPA-based phoneme recognition pipeline using Wav2Vec2, featuring...

An indie singing synthesizer

Transcribe offline audio recordings quickly with AI-powered, privacy-focused...

A Basic But Useful Online Text to Speech Converter with a male voice...

This projects aims to show how whisper model can be fine-tuned on language...

A free of cost Triage Assistant, this is the HealSpeak app.

Official repo for the paper "An Effective Training Framework for...

A console application for converting long-form plain-text files into speech...

Voice-based AI system helping farmers access agricultural guidance via phone...

Raw waveform adaptation with SincNet

An Api for testing covid using cough sound

A Nim client for the Google Cloud Text to Speech API.

Project used to illustrate how to use a RDK3 to interact with EnOcean BLE...

🎤 Convert spoken Chinese into pinyin with this simple voice recognition...

Play with voices. Speak any language. Clone your vibe.

Implementation of Automatic Speech Recognition inspired by "Listen, Attend...

FullStack App - NextJs 14 - Nest JS - Deployment

FitVoice/Speech2Diet is an application that allows people to track their...

A corpus that can be used to train English-to-Italian End-to-End...

Audio transcription app using Whisper AI for accurate speech-to-text...

Headless RVC voice cloning & training pipeline - Train and run voice...

This project focuses on real-time Speech Emotion Recognition (SER) using the...

Capturing the Rhythm of your words. Real-time AI transcription with a...

A real-time audio transcription web application designed to make...

Ko taqaku konqamatuqa mo nqaaqaku meqa.

ParsiGoo is a Persian multispeaker dataset for text-to-speech purposes. It...