A real-time transcription project using React and socketio

Offline Voice Recognition Module for MagicMirror²

BOT WHATSAPP

Voice2voice ChatGPT Assistant built through OpenAI Whisper (speech2text) + OpenAI ChatGPT API + Google Text2Speech Service (text2speech)

This is an OpenAI Whisper automatic speech recognition microservice

Example python scripts to evaluate various ASR methods

Transcription of any large audio/video files.

(incubation) Provides ability to transform speech to text in a Streams application

Word-cloud project implementation in angular

Jupyter notebook and Streamlit application for Whisper model from OpenAI

Speech to text

Transcribe long audio, process output text.

convert Fuji X voice recordings to EXIF description

TER system focused to Spanish with multilanguage speech-to-text

This minimalistic React-based project not only excels at speech-to-text translation but also seamlessly enables users to copy the transcribed text with ease, enhancing convenience and functionality.

This project provides a Speech-to-Text API service using FastAPI and SpeechRecognition. It converts various audio formats to text, supports multiple languages, and offers both file upload and base64 encoded audio input options.