projects.md

Awesome Whisper Apps

A curated collection of applications, tools, and resources built with OpenAI Whisper - a robust automatic speech recognition (ASR) system trained on 680,000 hours of multilingual and multitask supervised data.

Table of Contents

• Quick Start Guide
• Popular Picks
• Getting Started
• By Use Case
• By Platform
• For Developers
• Resources

Quick Start Guide

Looking for something specific?

• Voice typing on Linux? → Linux System Integration or try nerd-dictation
• Voice typing on Mac? → macOS Apps or try SuperWhisper
• Voice typing on Windows? → Windows Apps or try WinWhisper
• Cross-platform desktop app? → Try Buzz or whisper-writer
• Generate video subtitles? → Subtitles & Captioning
• Real-time transcription? → Real-Time & Streaming
• Meeting transcription? → Meeting & Productivity
• Cloud/SaaS solution? → SaaS Platforms
• Self-hosted web interface? → Web UI
• Mobile app? → Android or iOS
• Developer integration? → Libraries & APIs or Model Variants

Popular Picks

Top projects by community engagement and activity:

Desktop Applications

Project	Platform	Stars	Description
Buzz	Cross-platform		Feature-rich desktop transcription app
whisper-writer	Cross-platform		Voice-to-text for system-wide input
SuperWhisper	macOS	N/A	Premium Mac app for voice-to-text
WinWhisper	Windows		System-wide hotkey support for Windows

Model Variants & Performance

Project	Stars	Description
whisper.cpp		High-performance C/C++ implementation
faster-whisper		Faster implementation using CTranslate2
WhisperX		Word-level timestamps + speaker diarization
insanely-fast-whisper		Speed-optimized implementation

Developer Tools

Project	Stars	Description
WhisperLive		Real-time transcription server
whisper_streaming		Long-form streaming transcription
Whisper-WebUI		Self-hosted web interface

Getting Started

Official Whisper & Models

Official Repository: openai/whisper

Hugging Face Collection: Whisper Model Release

Official Paper: Robust Speech Recognition via Large-Scale Weak Supervision

Official Model Sizes

Choose based on your accuracy/speed requirements:

Model	Parameters	English-only	Multilingual	Relative Speed	Use Case
tiny	39M	✓	✓	Fastest	Minimal resource usage, real-time apps
base	74M	✓	✓	Very Fast	Resource-constrained environments
small	244M	✓	✓	Fast	Good balance for most use cases
medium	769M	✓	✓	Moderate	Better accuracy, moderate speed
large	1550M	-	✓	Slower	Best accuracy, research use

---

By Use Case

Voice Typing & Dictation

Cross-Platform:

• Buzz - Feature-rich desktop app
• whisper-writer - System-wide voice-to-text
• whisper-dictation - Dictation application

Linux:

• nerd-dictation - Hackable offline speech-to-text
• BlahST - Linux speech-to-text integration
• whisper-to-input - Convert transcription to keyboard input
• voice-typing-linux - Voice typing integration

macOS:

• SuperWhisper - Premium Mac voice-to-text app
• OpenSuperWhisper - Open-source Mac app
• WhisperKit - Native macOS implementation

Windows:

• WinWhisper - System-wide hotkey support
• Whisper Typing for Windows - Desktop voice typing

Mobile:

• whisperIME (Android) - Input method editor
• Whisperboard (iOS) - Keyboard with Whisper

SaaS Platforms & Cloud Services

• Whisper Transcribe - Online transcription platform
• WhisperAI - Cloud-based transcription service
• Whisper Typing - Online typing and transcription
• Wisprflow - Workflow automation with transcription
• CleverType - Smart typing assistant
• SpeechPulse - Cross-platform speech-to-text
• Blabby.ai - Browser-based transcription

Subtitles & Captioning

Generate subtitles and captions for videos:

• auto-subs - Automatic subtitle generation
• TeroSubtitler - Professional subtitle editor
• whisper-youtube - YouTube subtitle generation
• yt-whisper - YouTube transcription tool
• whisper-subs - CLI for adding subtitles to videos
• whisply - Automatic subtitle generation (Linux)
• template-tiktok - TikTok-style captioning with Remotion

Meeting & Productivity

Tools for transcribing meetings and generating notes:

• meeting-minutes - Generate meeting minutes
• ScribeWizard - AI-powered note-taking

Web Interfaces

Self-Hosted:

• Whisper-WebUI - Web interface for transcription
• NeuroSandboxWebUI - Comprehensive web UI for AI models

---

By Platform

Cross-Platform Desktop Applications

Applications that work on Linux, macOS, and Windows:

Project	Stars	Description
Buzz		Feature-rich transcription app
whisper-writer		Voice-to-text application
faster-whisper-GUI		GUI for faster-whisper
SoftWhisper		User-friendly GUI
speech-assistant		Speech assistant GUI
whisper-dictation		Dictation application
whisper-realtime-gui		Real-time transcription GUI
whisper-ui		Cross-platform desktop UI
whisper_dictation		Voice dictation tool
WhisperGUI		Simple GUI

Linux

Desktop Applications

• froshine - Linux desktop app
• speak-to-ai - Voice interaction app
• Whisper-Notepad-For-Linux - Notepad-style transcription
• WhisperNow - Desktop application

CLI Tools

• whisper.cpp-cli - CLI for whisper.cpp
• blurt - Command-line transcription tool

System Integration

• nerd-dictation - Hackable offline STT (VOSK-API)
• BlahST - Speech-to-text integration
• Linux-Dictation-Project - Dictation system
• linux-stt-input - STT input method
• linux-voice-to-text-ai - Voice-to-text AI
• LinuxWhisper - Linux implementation
• voice-typing-linux - Voice typing integration
• Whisper-Dictation - Dictation system
• whisper-flow-linux - Workflow integration
• whisper-hotkey-linux - Hotkey-based integration
• whispertrigger - System integration
• whisprd - Whisper daemon
• whisper-to-input - Transcription to keyboard input
• whispy - Integration tool
• dicti - Dictation tool
• sonori - Voice input system
• hushnote - Private note-taking
• Local-Voice - Local voice processing
• s2t - Speech-to-text
• Whisper-Notepad-Simple - Simple notepad app
• Linux-AI-Assistant-scripts - AI assistant scripts

macOS

Desktop Applications

• SuperWhisper - Premium Mac voice-to-text app
• OpenSuperWhisper - Open-source Mac app
• WhisperKit - Native macOS implementation
• Careless Whisper - Lightweight transcription app

System Integration

• ollama-voice-mac - Voice interface for Ollama
• whisperanywhere-js - System-wide transcription

---

Windows

Desktop Applications

• AI Transcription - Microsoft Store app
• Whisper Typing for Windows - Desktop voice typing

System Integration

• WinWhisper - System-wide hotkey support

---

Android

• whisperIME - Input method editor
• WhisperInput - Input app
• WhisperKitAndroid - WhisperKit for Android
• RTranslator - Real-time translation app
• Dictate - Voice dictation app
• whisper_android - Android integration

---

iOS

• Whisperboard - iOS keyboard with Whisper integration

---

Embedded / Raspberry Pi

• Local-Voice - Local voice processing for embedded systems

---

For Developers

Model Variants & Performance Optimizations

pyannote-whisper

Integration of Whisper with pyannote for speaker diarization

Repository: https://github.com/yinruiqing/pyannote-whisper

---

WhisperChain

Pipeline framework for Whisper-based workflows

Repository: https://github.com/chrischoy/WhisperChain

---

IDE & Editor Integrations

VS Code

Whisper Assistant

Whisper voice-to-text integration for VS Code

Repository: https://marketplace.visualstudio.com/items?itemName=MartinOpenSky.whisper-assistant

---

Yap - Cursor Extension

Voice input extension for VS Code and Cursor editor

Repository: https://marketplace.visualstudio.com/items?itemName=rishabhsai.yap-cursor-extension

---

WhisperX Assistant

WhisperX integration for VS Code with enhanced features

Repository: https://marketplace.visualstudio.com/items?itemName=mwhesse.whisperx-assistant

---

Obsidian

whisper-obsidian-plugin

Whisper integration for Obsidian note-taking app

Repository: https://github.com/nikdanilov/whisper-obsidian-plugin

---

Note-Taking & Productivity

ScribeWizard

AI-powered note-taking with Whisper transcription

Repository: https://github.com/Bklieger/ScribeWizard

---

Game Engines & Development Platforms

Unity

whisper.unity

Whisper integration for Unity game engine

Repository: https://github.com/Macoron/whisper.unity

---

Playgrounds & Demos

whisper-playground

Interactive playground for experimenting with Whisper

Repository: https://github.com/saharmor/whisper-playground

---

SRT / Subtitles & Captioning

auto-subs

Automatic subtitle generation with Whisper

Repository: https://github.com/tmoroney/auto-subs

---

template-tiktok

TikTok-style captioning with Whisper integration using Remotion

Repository: https://github.com/remotion-dev/template-tiktok

---

TeroSubtitler

Professional subtitle editor with Whisper integration

Repository: https://github.com/URUWorks/TeroSubtitler

---

whisper-subs

CLI tool for adding subtitles to videos using Whisper

Repository: https://github.com/GhostNaN/whisper-subs

---

whisper-youtube

Generate subtitles from YouTube videos using Whisper

Repository: https://github.com/ArthurFDLR/whisper-youtube

---

whisply

Linux tool for automatic subtitle generation

Repository: https://github.com/tsmdt/whisply

---

yt-whisper

YouTube subtitle generation with Whisper

Repository: https://github.com/m1guelpf/yt-whisper

---

Deployment & Containers

cog-whisper

Cog container for deploying Whisper models

Repository: https://github.com/replicate/cog-whisper

---

Meeting & Productivity

meeting-minutes

Generate meeting minutes using Whisper transcription

Repository: https://github.com/Zackriya-Solutions/meeting-minutes

---

Miscellaneous

whisper-turbo

High-performance Whisper implementation

Repository: https://github.com/FL33TW00D/whisper-turbo

---

Resources

Official

• OpenAI Whisper Paper

Tutorials & Guides

Model Variants

CrisperWhisper

Enhanced Whisper variant for improved accuracy

Repository: https://github.com/nyrahealth/CrisperWhisper

---

distil-whisper

Distilled Whisper models from Hugging Face

Repository: https://github.com/huggingface/distil-whisper

---

faster-whisper

Faster Whisper implementation using CTranslate2

Repository: https://github.com/SYSTRAN/faster-whisper

---

insanely-fast-whisper

Optimized Whisper implementation for speed

Repository: https://github.com/Vaibhavs10/insanely-fast-whisper

---

whisper.cpp

High-performance C/C++ implementation

Repository: https://github.com/ggerganov/whisper.cpp

---

whisper.net

.NET implementation of Whisper

Repository: https://github.com/sandrohanea/whisper.net

---

WhisperX

Whisper with word-level timestamps and speaker diarization

Repository: https://github.com/m-bain/whisperX

---

Real-Time & Streaming

whisper-flow

Real-time Whisper transcription flow

Repository: https://github.com/dimastatz/whisper-flow

---

whisper_real_time

Real-time Whisper transcription implementation

Repository: https://github.com/davabase/whisper_real_time

---

whisper_streaming

Whisper for long-form streaming transcription

Repository: https://github.com/ufal/whisper_streaming

---

WhisperLive

Real-time transcription using Whisper

Repository: https://github.com/collabora/WhisperLive

---

Diarization & Timestamps

cog-whisper-diarization

Cog-wrapped Whisper with diarization

Repository: https://github.com/thomasmol/cog-whisper-diarization

---

whisper-diarization

Whisper with speaker diarization

Repository: https://github.com/MahmoudAshraf97/whisper-diarization

---

whisper-timestamped

Word-level timestamps for Whisper

Repository: https://github.com/linto-ai/whisper-timestamped

---

WhisperTimeSync

Time synchronization and diarization for Whisper

Repository: https://github.com/EtienneAb3d/WhisperTimeSync

---

Fine-Tuning

Whisper-Finetune

Utilities for fine-tuning Whisper models

Repository: https://github.com/yeyupiaoling/Whisper-Finetune

---

whisper-finetuning

Fine-tuning framework for Whisper models

Repository: https://github.com/jumon/whisper-finetuning

---

Awesome Lists

• awesome-openai-whisper (ancs21)
• awesome-whisper (saharmor)
• awesome-whisper (oenu)