# thewh1teagle/vibe

Transcribe on your own!

Repository: https://github.com/thewh1teagle/vibe
Canonical: https://ross.abutalabs.com/products/vibe
Homepage: https://thewh1teagle.github.io/vibe/
Language: TypeScript
License: MIT
License Family: permissive
Topics: ai, cross-platform, desktop, openai, rust, transcribe, whisper
Last push: 2026-08-25T23:01:30+00:00

## Health v2 (maintenance only)
Score: 93/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 99, longevity 69
- inputs: {"age_days": 968, "days_push": 8, "days_rel": 11, "gap_med": 1, "n_releases_24m": 40}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 7206, forks 496 (observed 2026-08-28T04:09:56.603729+00:00)

## What it is
Vibe is a cross-platform desktop app for fully offline audio and video transcription using Whisper, Nemotron, and Parakeet models. It supports subtitle export, speaker diarization, GPU acceleration, microphone/system audio capture, and a CLI plus HTTP API.

## Use cases
- transcribe audio files to text offline
- generate srt subtitles from video
- transcribe youtube videos locally
- batch transcribe many recordings
- transcribe meetings with speaker diarization
- convert speech to text without uploading to cloud
- transcribe microphone or system audio in realtime

## When to choose
- you need private, fully offline transcription on macOS, Windows, or Linux
- you want subtitle export in SRT/VTT with stable timestamps
- you want GPU-accelerated Whisper transcription with batch processing
- you need a GUI plus CLI and HTTP API for transcription workflows

## When to avoid
- you need cloud-scale or server-side batch transcription for many concurrent users
- you need a library to embed transcription in your own app rather than a standalone tool
- you require mobile-native apps (phone recording works via QR pairing instead)

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, audio-processing, video-processing, cli, gui, ocr
- domain: speech-processing, artificial-intelligence, cross-platform, desktop-applications
- platform: windows, cross-platform
- tags: whisper, transcription, offline, subtitles, speaker-diarization, tauri, privacy, ollama, audio, video, macos, linux, desktop, gpu

## Member repositories
- thewh1teagle/vibe (main) score 93

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:56.603729+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:39:51.357940+00:00, confidence not recorded.
  - readme: https://github.com/thewh1teagle/vibe (fetched 2026-08-28T04:09:56.603729+00:00, sha 4df77f6f1036)
  - homepage: https://thewh1teagle.github.io/vibe/ (fetched 2026-08-29T08:35:08.543223+00:00, sha 1d1180e9f464)
- Data as of 2026-08-30T08:39:29.467469+00:00.