Real-time transcription using faster-whisper

Web UI for OpenAI Whisper API

A voice-powered AI built with Whisper, ChatGPT, and ElevenLabs

whisper-cpp-serve Real-time speech recognition and c+ of OpenAI's Whisper model in C/C++

Automatically filter, censor, and replace profanity, swear words, curse words, or custom terms in audio and video with a beep or bleep sound effect.

Blazor Server playground for OpenAI using Cledev.OpenAI .NET library

Summarization web service via the use of OpenAI Whisper and GPT-3 models

Scrape and transcribe thousands of audio files for free using Python, OpenAI's Whisper, and GitHub Actions

Distil whisper on web

A web ui application that utilizes the stream-translator-gpt

Simple User Interface: Enter text and generate speech with a single click.

State of Art AI models you can run locally.

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

A voice-powered AI built with Whisper, ChatGPT, and ElevenLabs

VideoWise is a video transcription and AI-powered analysis tool that helps users easily upload, transcribe, and interact with video content. Using WhisperX for high-quality transcriptions and Ollama for AI-driven insights, VideoWise makes it easy to search, analyze, and export video data.

Use LLM and Whisper to summarize long text and audio/video

FastAPI server for locally serving Gemma 3 270M & OpenAI Whisper with batched inference and streaming support.

A multilingual automatic speech recognition and video captioning tool using faster whisper. Supports real-time translation to english. Runs on consumer grade cpu.

AI-powered audio transcription tool using OpenAI Whisper. Convert speech to text with support for 8+ formats, batch processing, and multilingual transcription. Python CLI tool for developers.

Secrets app using Node.js/Express/EJS, MongoDB-Atlas/Mongoose, Heroku, Bootstrap. minimalist app where you can share your secrets anonymously.