# murtaza-nasir/speakr

Speakr is a personal, self-hosted web application designed for transcribing audio recordings

Repository: https://github.com/murtaza-nasir/speakr
Canonical: https://ross.abutalabs.com/products/speakr
Language: Python
License: AGPL-3.0
License Family: copyleft
Last push: 2026-08-07T03:59:43+00:00

## Health v2 (maintenance only)
Score: 84/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 96, release rhythm 96, longevity 34
- inputs: {"age_days": 485, "days_push": 26, "days_rel": 26, "gap_med": 2.0, "n_releases_24m": 57}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3676, forks 302 (observed 2026-08-28T04:08:13.588710+00:00)

## What it is
Speakr is a self-hosted web application that transcribes audio recordings and turns them into organized, searchable notes. It supports multiple ASR backends including self-hosted WhisperX with speaker diarization and voice profiles, keeping all data on your own infrastructure.

## Use cases
- transcribe meeting recordings locally
- self-hosted audio transcription app
- who-said-what speaker diarization for recordings
- turn voice memos into searchable notes
- private alternative to cloud transcription services
- auto-import audio files from a folder and transcribe them

## When to choose
- you need full privacy and control over sensitive recordings
- you want speaker diarization and voice recognition across recordings
- you prefer bringing your own ASR backend like WhisperX or OpenAI

## When to avoid
- you want a zero-setup hosted service without running Docker
- you only need quick one-off transcriptions without note management
- you cannot host a GPU or external ASR service for best results

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, nlp, search-engine, self-hosted, http-server
- domain: speech-processing, self-hosted, developer-tools, artificial-intelligence
- platform: self-hosted, python
- tags: transcription, speaker-diarization, whisper, audio-notes, meeting-notes, privacy-first, docker, web-server

## Member repositories
- murtaza-nasir/speakr (main) score 84

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:13.588710+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 2026-08-29T18:31:16.665240+00:00, confidence not recorded.
  - readme: https://github.com/murtaza-nasir/speakr (fetched 2026-08-28T04:08:13.588710+00:00, sha e5e74b2ccb7e)
- Data as of 2026-08-30T08:39:29.467469+00:00.