Repolode
Submit
Sharrnah

Sharrnah/whispering-ui

Native Go/Fyne desktop UI for Whispering Tiger, a Windows and Linux app for live speech transcription, translation, text-to-speech and OCR.

View on GitHubWebsite
Stars
332
Forks
25
Open issues
10
Last commit
22 days ago

What is it?

Whispering Tiger UI is the desktop front end for Whispering Tiger, a free, open-source application for Windows and Linux. It transcribes microphone or desktop audio, translates speech and text, reads text aloud, and extracts text from images with OCR.

The AI models run locally after they are downloaded, so the core features work offline. Results can be sent to VRChat via OSC or shown in browser overlays via WebSockets. Online services are optional plugins. This repository holds the native Go/Fyne UI, while the Python backend runs the models.

Profiles store audio devices, models and compute settings, and can be saved, loaded and switched. A plugin system adds features such as subtitles, additional TTS voices and LLM-based processing.

Key features

  • 01Live transcription and translation of microphone or desktop audio.
  • 02Text translation, text-to-speech and OCR from images.
  • 03Output to VRChat via OSC or browser overlays via WebSockets.
  • 04Desktop audio capture via WASAPI loopback on Windows and PulseAudio/PipeWire on Linux.
  • 05Profiles that save and load configurations, plus a plugin system.

Use cases

  • Adding live subtitles or translated captions to streams and videos.
  • Translating in-game dialogue or on-screen text while playing.
  • Showing speech transcripts in VRChat or a browser overlay.
  • Running speech and translation models locally without sending audio to a cloud service.

Quick start

  1. 1

    Download the latest release ZIP for your platform from the Releases page

  2. 2

    Extract the ZIP to a writable local folder, then run Whispering Tiger.exe on Windows

  3. 3

    On Linux, make the binary executable inside the extracted folder

    chmod +x whispering-tiger-linux-amd64
  4. 4

    On Linux, start the application from the extracted folder

    ./whispering-tiger-linux-amd64

Things to know

  • Supports only Windows and Linux; macOS is not supported.
  • The Linux build needs x86-64, glibc 2.36 or newer, and an X11/XWayland desktop with PulseAudio or PipeWire.
  • NVIDIA CUDA acceleration requires a compatible NVIDIA driver, and AMD or Intel acceleration relies on Vulkan via audio.cpp.

In collections

PDF, OCR & document toolsAI video & audio toolsDesktop GUI apps & toolkits

Topics

#speech-recognition#transcription#translation#text-to-speech#ocr#whisper#desktop-app#live-captions#ai#transcribe

FAQ

What is whispering-ui?
Native Go/Fyne desktop UI for Whispering Tiger, a Windows and Linux app for live speech transcription, translation, text-to-speech and OCR. Whispering Tiger UI is the desktop front end for Whispering Tiger, a free, open-source application for Windows and Linux. It transcribes microphone or desktop audio, translates speech and text, reads text aloud, and extracts text from images with OCR.
Is whispering-ui free to use? What license does it have?
whispering-ui is open source under the MIT license. Check the license terms before using it in commercial products.
Is whispering-ui still maintained?
Actively maintained. The last commit to whispering-ui was on Oct 1, 2026.
What can I use whispering-ui for?
Adding live subtitles or translated captions to streams and videos. Translating in-game dialogue or on-screen text while playing. Showing speech transcripts in VRChat or a browser overlay. Running speech and translation models locally without sending audio to a cloud service.
How do I install whispering-ui?
Download the latest release ZIP for your platform from the Releases page Extract the ZIP to a writable local folder, then run Whispering Tiger.exe on Windows On Linux, make the binary executable inside the extracted folder: chmod +x whispering-tiger-linux-amd64 On Linux, start the application from the extracted folder: ./whispering-tiger-linux-amd64
Where can I get whispering-ui?
The source code and installation instructions are on GitHub: https://github.com/Sharrnah/whispering-ui

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects