Whisper is an open-source AI-powered speech recognition system developed by OpenAI

Contents

• Official
• Model variants
• Apps
• Web apps
• CLI tools
• Playgrounds
• Packages
• Articles
• Videos
• Community
• Third-party APIs
• Related lists

Official

• Introduction
• Source code
• White paper

Model variants

• Whisper.cpp - Port of Whisper in C++.
  • Bindings for many languages
• WhisperX - Adds fast automatic speaker recognition with word-level timestamps and speaker diarization.
• faster-whisper - Faster reimplementation of Whisper using CTranslate2.
• Whisper JAX - JAX implementation of Whisper for up to 70x speed-up on TPU.
• whisper-timestamped - Adds word-level timestamps and confidence scores.
• whisper-openvino - Whisper running on OpenVINO.
• whisper.tflite - Whisper running on TensorFlow Lite.
• Whisper variants - Various Whisper variants on Hugging Faces.

Apps

• Aiko - Audio transcription iOS and macOS app.
• MacWhisper - Audio transcription macOS app. (Freemium)
• Whisper Memos - Audio transcription iOS app. (Freemium)
• FourYou - Audio journal iOS app.
• Jojo Transcribe - Audio transcription macOS app.
• Buzz - Audio transcription and translation macOS app.
• WhisperScript - Audio transcription macOS app. (Freemium · Electron)

Web apps

Hosted

• bigWav - Audio transcription and annotation tool.
• Free Podcast Transcription - Runs locally in your browser.
• Gladia - Transcription with real-time processing.

Self-hosted

• Subs AI - Subtitle generation.
• WaaS - GUI and API for Whisper.

CLI tools

• yt-whisper - YouTube subtitle generation.
• phonix - Generate captions for videos.

Playgrounds

• Hugging Faces - Whisper demo running on Hugging Faces. (Source)
• Monster API - Whisper demo running on Monster API. (Source)
• Web Whisper - Whisper demo by Pluja. (Source)
• YouTube Video Transcription - Running on Colab.

Packages

JavaScript

• use-whisper - React hook.

Articles

• Whispers of A.I.'s Modular Future - The future of machine learning lies in adaptable and accessible open-source speech-transcription programs.
• How to Run Whisper Speech Recognition Model - Explains how to install and run the model, as well as providing a performance analysis comparing Whisper to other models.
• Create your own speech to text app using Flask - The tutorial demonstrates Whisper's speech-to-text model, with a demo on running it in a Gradient Notebook and a guide for setting up a Flask app with Gradient Deployments.
• Convert Podcasts to Text - Tutorial on the Whisper API with Python for speech-to-text transcription, showcasing GPU's faster transcription and advanced technology.

Videos

• Open AI's Whisper is Amazing! - Introduction to Whisper.
• How to do Free Speech-to-Text Transcription Better Than Google Premium API - Tutorial.
• Multilingual AI Speech Recognition Live App - Tutorial.

Community

• Discussions
• Discord

Third-party APIs

APIs that use Whisper.

• Whisper+ - Extension of the Whisper model which adds powerful features such as speaker identification custom vocabulary, summarization, and chapter generation.
• Replicate - Use Whisper running on Replicate.

Related lists

• awesome-chatgpt - ChatGPT resources.