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

Livetranslate

LiveTranslate is a Windows application that captures system audio and optional microphone input, performs speech recognition, sends recognized content to an LLM translation API, and displays the translation in a transparent overlay.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Livetranslate — 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 translated text from audio playing on Windows without modifying the video, livestream or voice-chat player.

Who it is for

  • Viewers following foreign-language videos or livestreams
  • Livestreamers seeking translated captions
  • People who want translated text over voice chat

Documented uses

  • Translate audio playing on a Windows computer into streaming on-screen text.
  • Combine microphone input with system audio for speech recognition.
  • Display translated speech in an always-on-top overlay.
Before you choose

Requirements & limits

The project is open source under the MIT license. The README documents Windows 10/11 support and a portable build; source installation requires Python 3.10–3.12. Network access to a translation API is required.

  • Translation depends on a compatible LLM API; the README lists API base, key and model settings.
  • The initial setup downloads Silero VAD and SenseVoice models, about 1 GB.
  • An NVIDIA GPU is recommended for accelerated speech recognition, while CPU PyTorch is also an installer choice.
  • The documented portable build avoids a separate Python installation.

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 prepare LiveTranslate from source

Set up the Windows application and complete its first-launch model setup.

Before you start

  • Windows 10 or 11
  • Python 3.10–3.12, or an installer that can obtain Python via winget
  • Network access to download dependencies and speech models

Steps

  1. Clone the LiveTranslate repository and open its folder.

  2. Run install.bat to create a virtual environment, select CUDA or CPU PyTorch, and install dependencies.

  3. Run start.bat to open the application.

  4. In the setup wizard, choose ModelScope or Hugging Face and a cache path; allow Silero VAD and SenseVoice models to download.

Expected outcome

The application opens after its initial speech-model setup.

Guide limitations

  • The setup downloads about 1 GB of models.
  • This guide covers installation and first-launch setup; translation requires separate API settings.
Documentation 1 ↗
Evidence and transparency

Sources & review

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