W

whisper

System-wide voice-to-text for macOS. Hold a hotkey, speak, text appears at your cursor. Supports OpenAI, Gemini, Apple Speech & local models. No subscription — bring your own API keys.

A Node.js application for transcribing audio files into word-level and phrase-level subtitles in SRT format.

Multi-source RAG pipeline with hybrid vector + keyword retrieval, LLM-powered concept knowledge graph, adaptive search weighting, and evaluation framework.

No more typing. Use local-AI (whisper) to transcribe mic-Input (or files) into any textfield

Self-hosted Telegram bot that transcribes voice/audio/video using Whisper (Bun + Python).

Embedding of text and audio converted text

Audio transcription service built with FastAPI and OpenAI Whisper.

Ophelia - Voice Coding is a cross-platform experimental tool designed to help developers with disabilities by enabling hands-free coding through code dictation.

Application python permettant de transcrire un fichier audio, de générer une réponse à ce fichier avec un lightrag ou non puis de générer un fichier audio de la réponse en copiant une voix à l'aide d'un extrait.

(WIP) (shitty) interface for openai's whisper, including task system, use of yt-dl(p), and getting transcription data while processing

Adds timing to song lyrics when given the song and the lyrics using OpenAI Whisper.

Testing of the main ASR frameworks with reduced models for low-resource languages speech recognition