A fully local and private Speech-To-Text app with cross-platform support, speaker diarization, Audio Notebook mode, LM Studio integration, and both longform and live transcription.
-
Updated
Apr 10, 2026 - Python
Whisper is an autoregressive language model developed by OpenAI. It is trained on a large corpus of text using a transformer architecture and is capable of generating high-quality natural language text. Whisper can be used for tasks such as language modeling, text completion, and text generation. It has shown impressive performance on various benchmarks and has been released by OpenAI to encourage research in the field of language modeling. Whisper is not yet available for public use, but it has the potential to transform the field of natural language processing and generate new opportunities for language-based applications.
A fully local and private Speech-To-Text app with cross-platform support, speaker diarization, Audio Notebook mode, LM Studio integration, and both longform and live transcription.
A JupyterLab extension for generating code and interacting with JupyterLab Notebooks via voice commands
jupyter notebooks to fine tune whisper models on Vietnamese using Colab and/or Kaggle and/or AWS EC2
Finetune Whisper at ease + Puntuation & Cap Restoration + Spoken to written
Automatic audio transcriber notebook based on Whisper
Turn a NotebookLM video export (MP4) into slides and per-slide transcripts, then optionally into a Google Vids project via Google Slides.
Google Colab notebook for video analysis tools
Jupyter notebook and Streamlit application for Whisper model from OpenAI
Demo repository for Kyutai Labs' STT-1B model: Real-time speech-to-text transcription with streaming inference, built-in VAD, and Jupyter notebook examples for audio processing and simulation.
🚀 Complete self-hosted AI stack with 40+ services: Transform YouTube videos & PDFs into AI podcasts (Open Notebook), local LLMs (Ollama CPU/GPU), workflow automation (n8n), AI agents (Flowise), vector databases (Qdrant), German TTS voice, and business tools. One-command Docker deployment. perfect for learning, development, and private teams.
A notebook series for learning multi model agentic evaluation systems, scenario design, and rubric calibration.
Free, privacy-aware startup interview transcription toolkit using Whisper on Google Colab, with Quickstart, Plus, and Advanced notebooks for different accuracy needs.
This repository contains notebook that shows how to fine-tune OpenAI's Whisper model on custom Hindi dataset.
Speakeasy GPT is a Jupyter notebook that utilizes several natural language processing utilities to provide a seamless and low-latency speech interface to ChatGPT and other large language models.
Local Linux CTI learning tool — Socratic sessions, voice interaction, and an I Don't Know notebook powered by Claude AI
A personal sandbox of Python scripts and notebooks spanning data engineering, AI/GenAI, speech processing, web scraping, and data analysis — with an Indonesian context.
The Ultimate AI-to-AI Hybrid Transcription Tool! A master-class Colab notebook for fully automated transcription that captures every technical term using Whisper and Gemini. / AI×AIのハイブリッド文字起こしの決定版! WhisperとGeminiを使って、専門用語も逃さず全自動で文字起こしする究極のColabノートブック
Created by OpenAI
Released August 2021
Latest release 10 months ago