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

Whisper Auto Transcribe

Whisper Auto Transcribe is a Python application based on OpenAI Whisper that converts audio or video into subtitles, can translate content into English, and provides a local web interface and a command-line mode.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Whisper Auto Transcribe — 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 to generate subtitle files from media on a local web interface or through documented command-line examples, including batch processing.

Who it is for

  • People who need subtitles generated from audio or video.
  • Users who want to translate transcribed material into English.
  • People processing individual media files or batches through a local CLI workflow.

Documented uses

  • Generate timed subtitles from audio or video.
  • Translate content into English.
  • Preview subtitles over video.
  • Process multiple media files through the CLI.
Before you choose

Requirements & limits

The project is public on GitHub and identifies an MIT license. The README documents a local web interface and CLI setup.

  • The documented web interface starts locally at http://127.0.0.1:7860.
  • The CLI examples include translation and batch processing, with SRT as a sample output format.
  • The README states support for 99 languages and English translation.
  • GPU acceleration requires additional CUDA, cuDNN, and GPU-enabled PyTorch setup.

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

Set up the local web interface

Install the project and open its local browser interface.

Before you start

  • Python 3
  • Git

Steps

  1. Clone the repository and change into its whisper-auto-transcribe directory.

  2. Open webui.bat.

  3. Check that the launch output reports the local URL http://127.0.0.1:7860.

  4. Open that URL in a browser.

Expected outcome

The README's documented local web interface is available in a browser at the indicated URL.

Guide limitations

  • The instructions use the Windows batch file webui.bat.
  • The repository advises choosing a working directory outside Program Files and Program Files (x86).
Documentation 1 ↗
Source-based practical guide

Run a CLI transcription or batch job

Use the documented CLI examples to produce an SRT output or process a folder.

Before you start

  • Python 3 and Git
  • The repository cloned locally
  • The README's CLI setup step: open enable_venv.bat

Steps

  1. Open enable_venv.bat to enable CLI mode.

  2. Run python .\cli.py -h to display help.

  3. For a single-file translation example, run python .\cli.py .\mp4\1min.mp4 --output .\tmp\123456.srt -lang ja --task translate --model large.

  4. For the documented batch example, run python .\cli.py .\mp4 --output .\batch\ --model small --model medium.

Expected outcome

The examples specify an SRT output path for a single video or an output directory for batch processing.

Guide limitations

  • The examples use Windows-style paths and refer to sample folders and files.
  • The README does not explain how to edit subtitles; subtitle editing is listed as a future feature.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
tomchang25/whisper-auto-transcribe · Official homepage title · retained in its source language
How we review sourcesSuggest a correction