Tools for
Conviviality

Home / Dictation & transcription / Vibe

Vibe

Local audio and video transcription with batch jobs, speaker labels and a long list of export formats.

Instead of Otter.ai, cloud transcription

S · ToolOpen sourceWorks offline
github.com/thewh1teagle/vibe
Screenshot of the Vibe website

Screenshot from github.com/thewh1teagle/vibe, taken 2026-10-30, shown to help you recognise the tool. It belongs to its maker. Ask us to remove it.

Transcribing a pile of recordings is the kind of job that gets people to sign up for a subscription they then forget to cancel. Vibe does it locally. It handles audio and video in almost every language with Whisper, Nemotron 3.5 and Parakeet TDT v3 models, runs batches, labels speakers and exports to SRT, VTT, TXT, HTML, PDF, JSON and DOCX. It is MIT licensed and runs on Mac, Windows and Linux.

Vibe scores a 5 on lock-in, a 4 on footprint, self-direction, power and delivery and a 3 on longevity.

The project says fully offline transcription, with no data ever leaving your device. The same list mentions summaries through the Claude API, transcribing from YouTube and automatic updates, so read the offline claim as covering the transcription itself. We have not read its privacy policy, and a single developer runs the project, with no funding information on the page.

    What stands out

  • Transcribes audio and video locally, in almost every language
  • Batch jobs, speaker labels and seven export formats
  • Some extras, like summaries and YouTube downloads, use the network
Visit Vibe
Do you make Vibe? Get the badge for your site

This badge reports a dated review. It is not a certification and it costs nothing. Link it to this page and leave the numbers alone: the image always shows the current score.

For dark backgrounds, use vibe-dark.svg in place of vibe-light.svg.

For comparison, we also reviewed Otter.ai (14/30) as a benchmark.

Other tools for “turn speech into text without sending it away”