Local voice (English) to text app

A Next.js front-end to the tiny-whisper Python Flask app.

Video transcription, speaker diarization, and face detection in Python.

'SpeechGrade' is an innovative educational platform designed to streamline speech assessment and enhance teaching by integrating the MERN stack, machine learning models, large language models (LLMs), and Google's Generative AI.

Tool for transforming lengthy video and audio content into concise, digestible summaries.

OpenAI ChatGPT Assistants in Discord

Speech Recognition applied to transcribe amateur radio traffic experiments

A micro service that provides isolated and single-purpose NLP functions to the Genau! app

Speech-to-Text using OpenAI's Whisper model

translate/transcribe spotify songs using urls or audio files

LifeCoach is a full-stack demo project created by me, developed to mimic conversations with a Life Coach. On the Backend, it is implemented on fastAPI and features a REST API, and runs on OpenAI's Chat Completions and Audio Transcriptions API. It utilises ElevenLabs for voicing.

Developed an audio transcription and translation system using OpenAI’s Whisper to convert speech into translated text accurately.

OpenAI golang library that will support, ChatGPT, GPT-3, GPT-4, DALL·E, Whisper API. This is a golang wrapper library

🎥 Python tool that automatically generates and translates video subtitles using OpenAI's Whisper model. Supports multiple languages and custom configurations.

Voice (en) to Text using openai-whisper (works offline). FYI: Apple has dictation already

Digital competition in 2024

An AI Subtitle maker using OpenAI Whisper model

Learn how to turn audio into text.

LLM Experiment - context assisted subtitle generation