{
  "id": 272403,
  "title": "Dictovicto is out: transcription that never phones home",
  "url": "https://urgent.news/2026/08/07/dictovicto-is-out-transcription-that-never-phones-home",
  "topic": "tech",
  "section": "Tech",
  "published": "2026-08-07T16:47:55.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/jaychkdsk/dictovicto-is-out-transcription-that-never-phones-home-187l"
  },
  "original_language": "en",
  "account": "Dictovicto, a transcription and dictation tool for Windows, has been released that operates entirely on the user's PC without relying on cloud services. This app is designed to give users the privacy they need for transcribing sensitive information such as client interviews, legal depositions, and corporate meetings. With Dictovicto, users can record live dictation, import various audio and video formats, and even perform speaker diarization to identify who spoke when. The app also features a real-time transcript editor, allowing users to replay timestamps, edit text inline, and delete lines as needed. The exported transcript can be in plain text, SRT or WebVTT subtitle format, CSV, or structured JSON. The app comes pre-installed with five Whisper models, ranging from the fast \"tiny\" version to the more advanced \"large-v3\" model. It is designed to work offline, with the only network connection being the initial check with the Microsoft Store for license verification. With a minimum system requirement of Windows 10 (64-bit, version 1809 or later), a quad-core processor, 8GB of RAM, 16GB of free storage, and a microphone, Dictovicto is available now on the Microsoft Store.",
  "summary": "<report>Dictovicto is out: transcription that never phones home</report ca4ef9e0-afa>\nDictovicto is a new transcription and dictation studio for Windows that runs entirely on the user's PC, without requiring any cloud connectivity. This app allows users to perform live dictation, import various audio and video file formats, and perform speaker diarization to see who spoke when. Dictovicto also includes a real transcript editor, enabling users to edit, delete, or replay specific timestamps within the transcript. The app exports transcripts in multiple formats, including plain text, SRT, WebVTT, CSV, and structured JSON. Dictovicto comes bundled with five Whisper models, ranging from the fastest \"tiny\" model to the most advanced \"large-v3\" model. All AI models and the GPU runtime are included in the installer, ensuring that users can transcribe audio and video files offline without any internet connection. The app's offline capability is achieved by bundling all necessary models within the installer, making the package large but ensuring that users can transcribe until the end of time without needing to access a CDN or cloud services. Dictovicto requires a minimum of Windows 10 (64-bit, version 1809 or later), a quad-core x64 processor, 8 GB of RAM, 16 GB of free storage, and a microphone for dictation. The recommended system specifications include an 8-core CPU or an NVIDIA GPU with 6 GB+ of VRAM for optimal performance when using the large-v3 model. Dictovicto is available now on the Microsoft Store.",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}