A self-hostable offline audio transcription app. State-of-the-art AI models, running entirely on your machine.

17 Contibutors including Mr. Gipity Claud

https://github.com/rishikanthc/scriberr

NOTES FROM DEVELOPER

Apologies for the radio silence.. I did find a new job, but had to move across the country for it. So between multiple moves, settling down into the new job and just recuperating from all the stress and anxiety I went through during the process made me want to take some time off.. So I was taking it easy, spending time with my family and didn't really have a lot of free time nor the mindset to work on my personal projects.. That said, things are good now and boredom has been creeping up and I have been itching to get back into my personal projects.. I still need to setup my self-hosting server which I have been procrastinating for a while now xD

TLDR the project isn't abandoned. I'll be starting development again this week :) Look like a lot of advancements and developments have happened in this domain in the past few months and I could actually use your input and thoughts on something. Please check #485 and please do drop your thoughts and comments. I would like to get the communities input on this one to decide next steps. Also, thanks for all the love and support ! Y'all are awesome.

Why I built this

The inspiration for Scriberr was born out of privacy paranoia and not wanting to pay for subscription. About a year ago, I purchased a Plaud Note for recording voice memos. I loved the device itself; the form factor, microphone quality, and workflow were excellent.

However, transcription was done on their cloud servers. As someone who is paranoid about privacy I wasn't comfortable with uploading my recordings to a third party provider. Moreover I was hit with subscription costs: $100 a year for 20 hours of transcription per month, or $240 a year for unlimited access. As an avid self-hoster with a background in ML and AI, it felt wrong to pay such a premium for a service I knew I could engineer myself.

I decided to build Scriberr to bridge that gap, creating a powerful, private, and free alternative for everyone.

This is my yaml

LOCAL SETUP

services:
  scriberr:
    image: ghcr.io/rishikanthc/scriberr:v1.2.0
    ports:
      - "8080:8080"   # {whateverport:8080}
    volumes:
      - scriberr_data:/app/data # volume for >
      - env_data:/app/whisperx-env # volume f>
    environment:
      - PUID=${PUID:-1000}
      - PGID=${PGID:-1000}
      - APP_ENV=production # DO NOT CHANGE TH>
      # CORS: comma-separated list of allowed>
      - SECURE_COOKIES=false # Uncomment this>
    restart: unless-stopped

volumes:
  scriberr_data: {}
  env_data: {}

As someone who built my own internal self host infrastructure for transcriptions with speaker diarisation, my own app for myself, my own 3-2-1 archive solution, using runpod and modal alongside my own VPS and at he hardware...

I'll say i'm interested. However I also know the big challenge with this is the tradeoff of time. You can run WhisperX or Parakeet locally, but it takes longer than using proper hardware. If you don't need it in minutes after the meeting /conference/ whatever, then it can work. Shortcutting around it by model reductions, just makes it less accurate which has it's own consequences.

Overall this field is ripe for self-hosting.

Please move post to:

aisauce

slopsource

or

gtfosource

Audio.cpp has pretty much everything. This seems like a simple whisperX web app. Not really difficult to build, I guess it's cute.

I get AI transcription on my device for free with Transcribro.