# OpenWhispr/openwhispr

Voice-to-text dictation app with local (Nvidia Parakeet/Whisper) and cloud models (BYOK). Privacy-first and available cross-platform.

Repository: https://github.com/OpenWhispr/openwhispr
Canonical: https://ross.abutalabs.com/products/openwhispr
Homepage: https://openwhispr.com
Language: JavaScript
License: MIT
License Family: permissive
Topics: ai, open-source, whisper, anthropic, cross-platform, gemini, groq, linux, macos, openai, speech-to-text, transcribe, windows, nvidia, parakeet
Last push: 2026-08-26T23:00:26+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 31
- inputs: {"age_days": 441, "days_push": 7, "days_rel": 9, "gap_med": 1.0, "n_releases_24m": 91}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5766, forks 809 (observed 2026-08-28T04:09:29.286181+00:00)

## What it is
OpenWhispr is an open-source, privacy-first voice-to-text dictation desktop app for macOS, Windows, and Linux. It supports fully local transcription with Whisper and NVIDIA Parakeet models, bring-your-own-key cloud providers, AI agent chat, meeting transcription with speaker labels, and a notes system with semantic search.

## Use cases
- dictate text into any app with a hotkey instead of typing
- transcribe audio completely offline for privacy
- transcribe Zoom, Teams, and FaceTime meetings with speaker labels
- take and search meeting notes with AI actions
- chat with an AI assistant using my own OpenAI or Anthropic API key
- replace WisprFlow with a free open-source dictation tool
- use custom dictionary words for medical or legal jargon

## When to choose
- you want private, offline voice dictation where audio never leaves your device
- you need a cross-platform dictation app on macOS, Windows, or Linux
- you want meeting transcription with speaker labels and structured notes
- you prefer bringing your own API keys for cloud transcription instead of a subscription

## When to avoid
- you need a lightweight CLI or library to embed speech-to-text in your own code
- you require mobile-first dictation as the primary experience
- you need real-time streaming transcription APIs for server-side pipelines
- you want a fully free hosted service without any paid tiers for cloud features

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, nlp, chatbot, llm-inference, rag, mcp, sdk
- domain: speech-processing, developer-tools, privacy, cross-platform, desktop-applications
- platform: windows, cross-platform
- tags: voice-dictation, whisper, parakeet, transcription, meeting-notes, byok, push-to-talk, open-source-alternative, natural-language-processing, macos, linux, desktop, ios

## Member repositories
- OpenWhispr/openwhispr (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:29.286181+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 2026-08-29T17:52:55.569143+00:00, confidence not recorded.
  - readme: https://github.com/OpenWhispr/openwhispr (fetched 2026-08-28T04:09:29.286181+00:00, sha b3c0a2f7ba42)
  - homepage: https://openwhispr.com (fetched 2026-08-29T08:48:41.471592+00:00, sha 2a2862b10508)
  - site_page: https://docs.openwhispr.com (fetched 2026-08-29T08:48:41.482551+00:00, sha 398df6f428a0)
  - site_page: https://openwhispr.com/pricing (fetched 2026-08-29T08:48:41.480671+00:00, sha 911c754fcb76)
  - site_page: https://openwhispr.com/changelog (fetched 2026-08-29T08:48:41.484234+00:00, sha a8ee79fbbbad)
- Data as of 2026-08-30T08:39:29.467469+00:00.