OpenVINO™ is an open source toolkit for optimizing and deploying AI inference

🎤 Enable seamless audio processing with "sherpa-onnx," supporting speech recognition, synthesis, and more across multiple platforms.

Port of OpenAI's Whisper model in C/C++

Local ML voice chat using high-end models.

Home automation suite using voice recognition and computer vision

Speech-to-text server framework with next-gen Kaldi

React Native binding of whisper.cpp.

OBS plugin for local speech recognition and captioning using AI

Speech Note Linux app. Note taking, reading and translating with offline Speech to Text, Text to Speech and Machine translation.

A cross platform (Android/iOS/MacOS) Bahasa Indonesia speech recognizer library, written in Flutter.

A speech recognition plugin for Unreal Engine 5. This is essentially a port of Pocketsphinx, to be used within an Unreal Engine project.

A 100% private AI voice transcription app that converts speech to text in 50+ languages. Built with Compose Multiplatform for Android & iOS using Whisper AI - no cloud uploads, all processing happens on-device for complete privacy.

Speech Processing Projects

Facebook AI Research's Automatic Speech Recognition Toolkit

Fully Local Push-to-Transcribe

Real-time speech recognition and voice activity detection (VAD) using next-gen Kaldi with ncnn without Internet connection. Support iOS, Android, Linux, macOS, Windows, Raspberry Pi, VisionFive2, LicheePi4A etc.

HMM-Speech-Recognition: A classic Hidden Markov Model (HMM) based speech recognition implementation in C/C++, featuring MFCC feature extraction, K-means clustering, and sequence decoding for automatic speech recognition (ASR).

Speech-to-Text based on SileroVAD + whisper.cpp (GGML Whisper) for ROS 2

Kroko ASR - Speech-to-text

Fork of Whisper.cpp, Much Speech Recognition.