Simple virtual assistant using Ollama3 + PiperVoice

Ahh, it's music to my eyes.

Fullstack AI Korean language learning system

🤖 Empower your documents with a local AI assistant for PDF, DOCX, and TXT files, ensuring privacy by keeping data off the cloud.

Transcribe speech in browser

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

Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free. Twitter: @khojdev

An electron os x app to practice Chinese

Backend voice recognition using MediaRecorder API in front and Python Flask at backend. For recognition use Google's SpeechRecognition

upload an MP3 file, convert the speech to text using OpenAI's Whisper API, generate an intelligent answer using OpenAI GPT, and finally convert the generated answer back into speech for playback.

A tool to name audio recordings by analyzing the slate at the start of a file

This is a demo Speech to Text service using GO-Lang. It uses Google STT API to transcribe video/audios into text format.

VAD->STT web client based on guillaumekln/faster-whisper & ricky0123/vad

Docker, 음성인식 AI, FastAPI 기반 한국어 발음 교정 시스템