跳到正文
Diktavo 返回首页
版本 更新日志
English
Englishen Deutschde Françaisfr Españoles Italianoit Nederlandsnl Polskipl Portuguêspt Svenskasv Türkçetr Русскийru Українськаuk العربيةar हिन्दीhi Bahasa Indonesiaid 日本語ja 한국어ko ไทยth Tiếng Việtvi 中文zh

Licenses

Open Source Licenses

Diktavo uses the following open source components. We thank the authors.

Speech Model & Speech Recognition

  • whisper.cpp: MIT License (Georgi Gerganov).
  • OpenAI Whisper large-v3-turbo: Apache-2.0.
  • German finetune (primeline / cstr): Apache-2.0.
  • faster-whisper / CTranslate2: MIT.

Interface & System

  • Qt / PySide6: LGPL v3. The Qt libraries are linked dynamically and can be replaced by the user.
  • pynput: LGPL v3.
  • sounddevice: MIT. pyperclip: BSD. psutil: BSD.

Other Libraries

  • numpy: BSD-3-Clause.
  • cryptography (PyCA): Apache-2.0 OR BSD-3-Clause.
  • qrcode: BSD-3-Clause.
  • Pillow: Pillow License (HPND, MIT-like).

Updates & Packaging

  • Velopack: MIT.
  • Nuitka: Apache-2.0.

The full license texts are included with the installed application in the licenses/ folder.

Dieser Rechtstext liegt nur auf Deutsch und Englisch vor. This legal document is only available in German and English. Deutsch · English

返回首页
Diktavo

面向 Windows 的本机听写。你的声音立刻变成文字,从不发往任何地方。

产品

工作方式 功能 价格 常见问题 下载 所有版本

法律

法律声明 隐私 条款 撤销权 许可证

联系

support@diktavo.com
Copyright Joshua Boehme · 本机听写 Diktavo · 在本机 · 设计上就私密