Versions:

  • 1.22.1
  • 1.21.0
  • 1.20.2
  • 1.20.1
  • 1.20.0
  • 1.19.1
  • 1.19.0
  • 1.18.1
  • 1.17.2
  • 1.17.1
  • 1.17.0
  • 1.16.1
  • 1.16.0
  • 1.15.2
  • 1.15.1
  • 1.15.0
  • 1.14.0
  • 1.13.5
  • 1.13.4
  • 1.13.3
  • 1.13.2
  • 1.12.0
  • 1.11.1

ByeType is a free, open-source, Markdown-driven AI voice input tool developed and published by ByeType, currently at version 1.22.1 with 23 versions recorded in the catalog. Its core purpose is speech-to-text transcription powered by multimodal large language models that process raw audio directly, rather than relying on conventional speech recognition pipelines. What distinguishes ByeType is its Markdown-based configuration approach: users edit Markdown prompt files to define custom recognition rules, proprietary vocabulary, and text optimization strategies, allowing transcription output to match industry-specific terminology and personal habits. Proper nouns, technical terms, filler words, and number formatting can be handled correctly in a single transcription pass, reducing the need for manual post-editing. In addition to voice input, ByeType includes a built-in AI image text extraction feature, also driven by Markdown prompts, which addresses the problem of copying AI-generated code from terminals where line numbers, split panes, and line breaks fragment the text and make direct copying impractical. The tool falls into the productivity and AI-assisted input software category, with use cases spanning dictation, transcription, technical writing, and developer workflows. ByeType itself does not charge fees and does not handle user data; instead, users supply their own API key, and audio or screenshots are sent directly to the AI provider of their choice, such as Google or Alibaba Cloud Bailian. Supported platforms include macOS and Windows desktop environments, as well as iPhone and iPad through iOS Shortcuts integration, making it usable across both desktop and mobile contexts. As an open-source project, it offers transparency into how prompts and data are processed while giving users full control over which AI service handles their content.

Tags: