OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Audio & Voice AI

Whispering Tiger UI

Whispering Tiger UI is a native Go/Fyne desktop interface for the Whispering Tiger Python backend, which runs AI models for audio transcription and translation, text translation, text-to-speech, and OCR. It supports Windows and Linux, local processing after model downloads, and text output to VRChat or browser overlays.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Whispering Tiger UI — OpenViST project profile in Audio & Voice AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want a desktop workflow for live audio transcription or translation, text-to-speech, or image OCR, especially when local processing or caption output to VRChat or a browser overlay is useful.

Who it is for

  • People who need live transcription or translation of microphone or computer audio.
  • Users who want local speech and text processing after downloading models.
  • VRChat users or browser-overlay setups that display recognized text.

Documented uses

  • Transcribe microphone speech or desktop audio.
  • Translate audio streams or written text.
  • Read text aloud with text-to-speech.
  • Extract text from images using OCR.
  • Send recognized text to VRChat through OSC or browser overlays through WebSockets.
Before you choose

Requirements & limits

The project describes the application as free and open source, and publishes Windows and Linux desktop releases.

  • The UI and model-running backend are separate components; the backend is downloaded during setup.
  • Selected models download on first use, so local offline processing depends on completing that download.
  • Compute support varies by task and model: CPU and compatible NVIDIA CUDA are supported, with Vulkan for audio.cpp STT/TTS.
  • Linux has specific architecture, glibc, desktop-display, and audio-service requirements.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install and configure Whispering Tiger UI

Prepare a desktop profile with selected audio devices, models, and compute devices.

Before you start

  • A Windows or Linux desktop and the matching release ZIP.
  • A writable local folder with space for the backend and models.
  • For Linux: x86-64, glibc 2.36 or newer, an OpenGL-capable X11/XWayland desktop, and PulseAudio or PipeWire's PulseAudio compatibility service.

Steps

  1. Download the matching Windows or Linux ZIP and extract it to a writable local folder; do not run the application from inside the ZIP.

  2. Launch the Windows executable or, on Linux, run chmod +x whispering-tiger-linux-amd64 followed by ./whispering-tiger-linux-amd64 in the extracted folder.

  3. Accept the backend download when prompted, create a profile, and select audio devices, models, and compute devices.

  4. Start the profile; selected models download on first use.

Expected outcome

A configured profile with its selected models downloaded for use.

Guide limitations

  • Linux desktop audio capture requires choosing a PulseAudio or PipeWire monitor source.
  • CUDA acceleration requires compatible NVIDIA hardware and driver support; the documented audio.cpp path uses CPU or Vulkan on Linux.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
Sharrnah/whispering-ui · Official homepage title · retained in its source language
How we review sourcesSuggest a correction