OpenAI Whisper

Open-source OCR engine first built at HP, later developed by Google

Overview

Tesseract is the most widely used open-source OCR engine. It was developed at Hewlett-Packard Laboratories in Bristol and at HP in Greeley, Colorado, between 1985 and 1994, released as open source by HP in 2005, and developed by Google from 2006 until August 2017; it is now maintained by a community of contributors[16]. The code is released under the Apache License 2.0[16].

Version 4 added a neural-network OCR engine based on LSTM line recognition, and version 5, whose first release 5.0.0 appeared on 30 November 2021, is the current stable line[16]. Tesseract recognises more than 100 languages out of the box and outputs plain text, hOCR, PDF and other formats; it is used as a command-line tool or through its C++ API and many third-party wrappers. The repository had about 77,500 GitHub stars when fetched[16].

Tesseract is free and runs offline, which makes it the default choice for developers who cannot send documents to a cloud service. It has no graphical interface of its own, performs best on clean, well-segmented printed text, and leaves layout analysis, table extraction and handwriting to other tools or custom training.

What OpenAI Whisper does

  • YAML workflows triggered by repository events
  • GitHub-hosted Linux, Windows and macOS runners
  • Self-hosted runners and Actions Runner Controller
  • Larger and Arm runners
  • Marketplace of reusable actions
  • Free standard runners for public repositories
  • Git hosting and code review
  • GitHub Actions CI/CD minutes

OpenAI Whisper pricing

Included compute per month: GitHub Free and Free for organizations US$12; GitHub Pro and Team US$18; Enterprise Cloud US$300. Per-minute rates include Linux 2-core US$0.006, Linux 1-core US$0.002, Linux Arm 2-core US$0.005 and Windows 2-core US$0.010. Plans: Free US$0; Team US$4 per user per month; Enterprise US$21 per user per month.

OpenAI Whisper strengths and limitations

Strengths

  • No separate tool for GitHub users
  • Large marketplace of reusable actions
  • Free for public repositories on standard runners
  • Hosted and self-hosted runners
  • Largest developer community
  • Low per-seat entry price

Limitations

  • Tied to GitHub as the code host
  • macOS and Windows minutes cost more
  • Limited deployment orchestration features
  • YAML workflows can become hard to maintain at scale
  • Advanced Security costs extra
  • Enterprise features need US$21 plan

Appears in

OpenAI Whisper alternatives and competitors

Alternatives to OpenAI Whisper: companies ranked in the same lists.

Is this your company?

Update the description, logo, image and link through the submission form. Editors review every change.

Update this listing

Is your company missing from a list?

Send your logo, description and link. Editors review every submission, and approved listings are clearly labelled.

Add your company