A voice-powered AI built with Whisper, ChatGPT, and ElevenLabs
VAD->STT web client based on guillaumekln/faster-whisper & ricky0123/vad
This is a web application that performs speech recognition on audio files. It allows you to upload an audio file (in .wav, .mp3, or .ogg format) and transcribes the speech content using an AI speech recognition model.
Simple User Interface: Enter text and generate speech with a single click.
This project uses RSelenium webscraping, Google Colab, and OpenAI’s Whisper Transcription to analyze sentiment in US political ads on Google platforms. The goal is to explore the difference between Trump and Biden ads using GPT-3.5 Turbo as the sentiment analyzer.
An innovative application that records audio, transcribes it using OpenAI Wisper, and provides a feature to translate the transcribed text directly into English. The output is automatically copied to your clipboard, offering a seamless and efficient user experience. Ideal to automate and optimize your workflow.
Add a description, image, and links to the whisper-ai topic page so that developers can more easily learn about it.
To associate your repository with the whisper-ai topic, visit your repo's landing page and select "manage topics."