How to use Vibe — offline transcription setup & fixes

Set up the Vibe desktop app for offline Whisper transcription on Mac, Windows and Linux, and fix model download errors, GPU detection and batch issues.

Setup that works

1

Install

Download from the Vibe site or GitHub releases (Tauri app, all three platforms).

2

Model

First launch downloads a Whisper model; you can switch sizes in Settings → Models.

3

Batch

Drop multiple files at once — Vibe queues them; exports per-file to TXT/SRT/VTT/JSON.

Skip the setup — paste the file here

Same Whisper-class accuracy, no install, no model downloads, no GPU questions. Speaker labels, word timestamps and every export (TXT, SRT, VTT, DOCX) included. Free instant preview; credits from $2 and they never expire.

Fixing the common errors

Model download fails or hangs

The models come from Hugging Face; if blocked, download the GGML .bin manually and point Settings → Models at the file.

GPU not detected on Windows

Vibe uses Vulkan for GPU on Windows — update GPU drivers; on old iGPUs it silently falls back to CPU.

Transcript language is wrong

Auto-detect reads the first 30 seconds — if the intro is music or another language, set the language explicitly.

Can Vibe fetch a YouTube/podcast URL?

No — it's file-only. Use a hosted service that fetches URLs server-side, then keep Vibe for private local files.

More on Vibe: the full Vibe page · Vibe alternatives · all transcription tools