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

Vid2Cleantxt

Vid2Cleantxt is an open-source Python API and command-line tool that transcribes speech-heavy video files into text using a pretrained transformer pipeline, with post-processing options for spelling, sentence boundaries and keyword extraction.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Vid2Cleantxt — 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 Vid2Cleantxt when you want a Python- or CLI-based workflow for turning a directory of speech-heavy videos into text that can be searched, reviewed or analyzed.

Who it is for

  • People who need searchable text from speech-heavy videos.
  • Python users building video transcription into scripts.
  • Command-line users processing directories of video files.
  • Researchers and analysts who want transcript text for later review or text analysis.

Documented uses

  • Transcribe speech from video files into text files.
  • Process transcripts with spelling correction and inferred sentence boundaries.
  • Extract keywords from corrected transcripts and export them to an Excel workbook.
  • Collect transcript outputs and runtime metadata from a directory-based job.
Before you choose

Requirements & limits

The repository is public and licensed under Apache-2.0. A Google Colab demo notebook is linked in the README.

  • FFmpeg is required for video and audio processing.
  • A spaCy English model may need to be downloaded for post-processing.
  • The README recommends a 30-second chunk length for Whisper models until further tests are completed.
  • The project describes transcript cleanup and keyword extraction as pipeline stages; transcription output may still need review.

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 Vid2Cleantxt as a Python package

Prepare the package for use in a Python script.

Before you start

  • Python 3
  • FFmpeg as a system dependency for video and audio processing
  • A spaCy English model may be needed for post-processing

Steps

  1. Create a virtual environment with the command below and activate it.

    Documented command
    python3 -m venv venv

  2. Install the repository with the command below.

    Documented command
    pip install git+https://github.com/pszemraj/vid2cleantxt.git

  3. If needed for post-processing, download the spaCy model with spacy download en_core_web_sm.

Expected outcome

The package is installed for use in Python scripts; video transcription can then be invoked through the `transcribe` module.

Guide limitations

  • FFmpeg is required to process video or audio.
  • The spaCy model may be required for post-processing.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
pszemraj/vid2cleantxt · Official homepage title · retained in its source language
How we review sourcesSuggest a correction