An Demonstration of PocketSphinx on RaspberryPi3

Python UI application that transcribes speech output from your soundcard. Helpful for hearing impaired people or to create the minutes of meeting. Can be used for dictations, too.

Microservices with HTTP, Triton Inference Server, FastApi and Docker-compose

AI-powered Avatar-assistant specialized in tourism and city infrastructure

Realtime-subtitles captures input audio in Google Chrome and translating from any to any language.

A wake-word activated voice assistant that can recognize content from webcam captures, screenshots, and clipboard. Built with Llama 3 via Groq.

AI Assistant bot that helps people to do actions with comunications.

A Home Assistant custom component that integrates Parasail for STT.

Local Voice Dictation for MacOS

Notes on STT processing chain (for future voice projects)

Personalized voice assistant 'Alice' with Language classification, Speech Recognition, Machine Translation, Restoring Punctuation, Conversational and Speech Synthesis.

Реализация серверной части STT на Python для сервера Orienta для игры SS14

Robot berbasis AI LLM OpenAI yang dapat melihat menggunakan kamera, mendeteksi wajah/contour, menggerakkan roda, dan berinteraksi dengan percakapan suara secara realtime.

Local voice-to-text transcription tool 🗣️📢🖮

Audio tts using nextjs and fastapi. ( DEPLOYED ON RENDER)

한국어 관련 모임, 행사 그리고 오픈 소스나 해결 방법에 관한 정보를 공유하는 저장소입니다.

A choose your own adventure game based on Jack and the beanstalk.

This is my Foss setup to replace Gboard, Google Voice input, Gboard IME (STT Keyboard), Google TTS, Gboard with spell checker (right now extra keyboard is used here)

A simple Whisper Dictation MVP app.

A whisper-based, lightweight transcription pipeline for processing audio and video files in batch mode, generating accurate transcriptions with color-coded confidence scores to indicate the reliability of each transcribed segment.