Add media
Open a supported meeting, interview, audio, or video file.
Transcribe recordings, identify speakers, create private AI summaries, and export meeting notes or subtitles from your PC.

Download the Windows app and transcribe short audio or video files privately for free.
Video to Text Transcriber converts recorded meetings, interviews, lectures, and media files into searchable text using local Whisper speech recognition. It can identify speakers and turn the transcript into action items, decisions, risks, and next steps without uploading sensitive recordings.
The free tier handles short recordings and essential TXT export. Premium expands the workflow with longer files, more speakers, larger models, batch folders, redaction controls, and professional document formats.
Open a supported meeting, interview, audio, or video file.
Choose a Whisper model and identify speakers.
Generate decisions, tasks, risks, or meeting notes on your PC.
Save text, subtitles, data, or professional documents for your workflow.
Use Whisper locally with CPU fallback and optional CUDA or Vulkan acceleration.
Separate speakers automatically so conversations are easier to review and quote.
Create action items, decisions, risks, and next steps without sending recordings online.
Export DOCX, PDF, Markdown, TXT, JSON, SRT, and WebVTT for notes and subtitles.
Use PII redaction, air-gap mode, and a SHA-256 chain of custody for sensitive work.
Apply repeatable formats for general meetings, standups, legal, HR, and board minutes.
Produce structured minutes, action items, and decisions.
Separate speakers and create searchable research transcripts.
Convert lectures and recorded lessons into notes and subtitles.
Use local processing, redaction, and chain-of-custody tools for sensitive records.
Yes. Whisper transcription and supported AI summary workflows run locally so recordings can remain on your computer.
Free users can transcribe files up to 20 minutes with up to two speakers, use Tiny or Base models, create three daily summaries, and export TXT.
Yes. Speaker identification separates voices to make meetings and interviews easier to review.
Premium supports DOCX, PDF, Markdown, TXT, JSON, SRT, and WebVTT exports.
Premium workflows include PII redaction, air-gap operation, and a SHA-256 chain of custody for sensitive records.
Transcribe, organize, summarize, and export meetings and media without giving up privacy.
Sort, rename, and clean folders with AI-assisted file organisation.
Create polished captions with local Whisper models and styled exports.
Push images to 2× or 4× with specialised Real-ESRGAN models.
Generate private AI art with built-in models and a generous free tier.