🐧 Linux Native

RocketWhisper Linux Edition

Fully Offline, One-Time Purchase
AI Speech Recognition & Transcription

🔒 Privacy Protected
CUDA Accelerated
🌐 Works Offline
Supported Platforms:
🟠 Ubuntu 🔴 Debian 🔵 Fedora 🟢 Arch
RocketWhisper
Converting speech to text...

💭 Sound Familiar?

🔐

Worried About Confidential Data

Cloud-based speech recognition is convenient, but sending sensitive data to external servers is a concern...

🌐

No Internet Available

Need voice input on air-gapped environments or development servers with network restrictions...

⌨️

Tired of Typing

Writing documentation while working in the terminal. If only you could just speak and type...

🐧

Few Linux Options

Plenty of options for Windows/Mac, but hard to find a quality speech recognition app for Linux...

RocketWhisper Solves It All!

🚀

Fully Local Processing

Runs OpenAI Whisper locally.
Your voice data never leaves your machine.
Safe to use even in air-gapped environments.

No internet connection required
Confidential data stays safe
No server outage impact
Zero monthly fees
CUDA Accelerated

Blazing Fast Recognition with GPU

On machines with NVIDIA GPUs, CUDA hardware acceleration delivers incredible processing speed.

DGX Spark ✅ Optimized
Jetson AGX Orin ✅ Supported
Jetson Orin NX/Nano ✅ Supported

💡 Works on CPU too when no GPU is available (auto-detected)

🎮
10x Faster*
128GB VRAM Support

*Compared to CPU with large-v3-turbo model

🆕 NEW in v1.2.0

🤖 Even More Powerful with AI

Works with local LLMs (Ollama, etc.).
Completely offline and free AI features.
No API key required. No cloud communication. Full privacy protection.

🎯

AI Command Mode

Simply give voice instructions on selected text. "Translate to Japanese", "Summarize this", "Make it formal", etc.
Powered by local LLM — works offline

1 Select text
2 Press hotkey
3 Speak command
4 AI processes it!
🔍

Voice Search

Just say "Search for ..." and it automatically opens a browser search. Research made effortless.

"Search for Docker Compose"
"Look up Rust ownership"
"What is systemd?"

17 Premium Features

🎙️

High-Accuracy Recognition

State-of-the-art speech recognition powered by OpenAI Whisper. Excellent for both Japanese and English.

⌨️

Global Hotkey

Start recording with a single hotkey from any app. No need to interrupt your workflow.

📋

Auto Paste

Recognition results are automatically typed into the active window. No copy-paste needed.

🎯

Per-App Processing Modes

Automatically apply different settings for each app. Separate configs for VSCode, Slack, and more.

🤖

AI Processing

Auto-format recognized text with local LLMs (Ollama, etc.). Grammar correction, formalization, and more. Completely offline and free.

📝

Correction Rules

Automatically fix common misrecognitions. Regular expressions supported.

💬

Voice Commands

Edit text with voice commands like "new line", "period", and more.

🔍

Voice Search

Say "Search for ..." to automatically open a browser search.

🚀

Voice Launcher

Launch apps by voice. Say "Open VS Code" and it starts.

🎯

AI Command Mode

Give voice instructions on selected text. Translation, summarization, and more via local AI. No API key required.

📖

Custom Dictionary

Register technical terms and proper nouns to improve recognition accuracy.

🔊

Notification Sounds

Audio cues for recording start/stop. Stay informed even when looking away.

📁

Batch Processing

Transcribe multiple audio and video files at once. Supports MP4, MKV, and more. SRT/VTT subtitle export available.

Custom Instructions

Register frequently used AI tasks to dedicated hotkeys. Translation, formal language, summarization — up to 20 custom instructions, each triggered with a single key.

📜

Recognition History

All recognition results are automatically saved. Search, copy, and reuse anytime.

🔴

Recording Indicator

Floating indicator at the bottom of the screen during recording. Real-time audio level waveform display.

🌙

Dark Theme

Easy-on-the-eyes dark mode built in. Comfortable for extended use.

📚 Get Started in 3 Steps

1

Install Dependencies

sudo apt install pulseaudio-utils xdotool xclip ffmpeg

For Ubuntu/Debian. Use dnf for Fedora, pacman for Arch.

2

Download & Run the AppImage

chmod +x RocketWhisper-*.AppImage
./RocketWhisper-*.AppImage

No installation required. Just download and run.

3

Start Recording with a Hotkey!

F8 Start/Stop Recording

Press to talk. Press again to recognize. That's it.

🖥️ System Requirements

📦 Supported Distributions

Ubuntu 20.04 LTS or later
Debian 11 (Bullseye) or later
Fedora 35 or later
Linux Mint 20 or later
Pop!_OS 20.04 or later
Arch Linux Rolling

💻 Architecture

ARM64 (aarch64) ✅ Recommended (DGX Spark, etc.)
x86_64 (AMD64) ✅ Supported

📋 Required Packages

pulseaudio-utils Microphone recording (parec)
xdotool Keyboard automation
xclip Clipboard access
ffmpeg Audio conversion (optional)

🎮 CUDA-Compatible GPUs

DGX Spark Blackwell ✅ Optimized
Jetson AGX Orin Ampere ✅
Jetson Orin NX/Nano Ampere ✅
Falls back to CPU when no GPU is present

⚠️ Display Server

X11 ✅ Fully supported (recommended)
Wayland ⚠️ Limited support
Some features are limited under Wayland

💾 Memory Requirements

small/medium model 8GB or more
large-v3-turbo 8GB or more recommended
large-v3 16GB or more recommended
⚠️

For Wayland Users

The following features are limited under Wayland:

  • Global hotkeys (ydotool required, may need root privileges)
  • Auto paste (wl-clipboard required)
  • AI Command Mode (affected by clipboard restrictions)
  • Per-app processing (limited window detection)
Additional packages: sudo apt install ydotool wl-clipboard

💡 Log in with an X11 session for full functionality

📥 Download

💻

x86_64

AMD64 / x86_64

For standard Linux PCs
and servers

~196MB
Download
⚠️

Before You Download

Running RocketWhisper requires installing dependency packages.
Please install the required system packages for microphone recording and keyboard automation beforehand.

sudo apt install pulseaudio-utils xdotool xclip ffmpeg

For detailed installation instructions, see Help: Installation.
Package lists and commands for each distribution are available at Help: Required Packages.

📌 Latest version: v1.2.0
📋 AI model is automatically downloaded on first launch
🔒 License: Commercial (30-day free trial)

💰 Licensing

Personal License

¥4,800 (excl. tax)
  • ✅ All features included
  • ✅ Valid for 1 PC
  • ✅ Perpetual license
  • ✅ Free updates
Purchase

Free Trial

¥0 30 days
  • ✅ All features included
  • ✅ No credit card required
  • ✅ No automatic billing
Try Now

👥 Perfect For

👨‍💻

Linux Developers

Write documentation while working in the terminal. Input text without leaving the keyboard.

🔒

Security-Conscious Users

Safe to use even in environments handling confidential data. No data is ever sent externally.

🖥️

System Administrators

Works in air-gapped and network-restricted environments.

🎮

GPU Developers

Leverage DGX Spark and Jetson hardware. Blazing-fast recognition with CUDA acceleration.

Frequently Asked Questions

Q Is the license shared with the Windows version?
A Yes, the license is universal. A license purchased for the Windows version works on the Linux version as well.
Q Can I use it without a GPU?
A Yes, it works on CPU as well. CUDA acceleration is automatically enabled when a GPU is available, but the app works fine without one.
Q Does everything work on Wayland?
A Some features are limited under Wayland. For full functionality, please log in with an X11 session.
Q Do I need to extract the AppImage?
A No, you can run it directly. Just grant execute permission with chmod +x. On systems without FUSE, you can extract it with --appimage-extract.
Q Can I use it for meeting transcription?
A Yes, you can transcribe meetings in real-time or from recorded audio/video files via batch processing. AI processing can automatically summarize and format the results.
Q Can it create subtitles from video files?
A Yes, RocketWhisper can transcribe video files (MP4, MKV, AVI, MOV, WebM) and export subtitles in SRT and VTT formats.