github.com/rishikanthc/Scriberr @v1.2.0

Scriberr is an open-source, and completely offline audio transcription application designed for self-hosters who value privacy and performance.

Website • Docs • API Reference

Sponsors

Meeting Transcription API
If you're looking for a transcription API for meetings, consider checking out Recall.ai, an API that works with Zoom, Google Meet, Microsoft Teams, and more. Recall.ai diarizes by pulling the speaker data and seperate audio streams from the meeting platforms, which means 100% accurate speaker diarization with actual speaker names.

Introduction

At its core, Scriberr allows you to transcribe audio and video locally on your machine, ensuring no data is ever sent to a third-party cloud provider. Leveraging state-of-the-art machine learning models (such as NVIDIA Parakeet, and Canary) or the older more popular Whisper models, it delivers high-accuracy text with word-level timing.

Scriberr goes beyond simple transcription and provides various advanced capabilities. It combines powerful under-the-hood AI with a polished, fluid user interface that makes managing your recordings feel effortless. Whether you are sorting through voice notes or analyzing long meetings, Scriberr provides a beautiful environment to get work done:

• Smart Speaker Detection: Scriberr automatically detects different speakers (Diarization) and labels exactly who said what.
• Chat with your Audio: Connect seamlessly with Ollama or OpenAI API compatible providers. You can generate summaries, ask questions, or have a full conversation with your transcripts right inside the app.
• Built for your Workflow: With extensive APIs and Folder Watcher that automatically processes new files in a folder, Scriberr fits right into your existing automations (like n8n).
• Capture & Organize: Use the built-in audio recorder to capture thoughts on the fly, and the integrated note-taking features to annotate your transcripts as you listen.
• Native Experience everywhere: Scriberr supports PWA (Progressive Web App) installation, giving you a native app experience on your desktop or mobile device.
• A Polished UI: I’ve focused on the little UI niceties that make the app feel responsive and satisfying to use.

View full list of features →

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.

Screenshots

Click to expand

<img alt="Transcript view" src="https://github.com/rishikanthc/Scriberr/raw/v1.2.0/screenshots/transcript-light.png" width="720" />

Transcript reader with playback follow‑along and seek‑from‑text.

<img alt="Chat with Audio" src="https://github.com/rishikanthc/Scriberr/raw/v1.2.0/screenshots/chat.png" width="720" />

Chat with your transcripts using local LLMs or OpenAI.

<img alt="Notes and Highlights" src="https://github.com/rishikanthc/Scriberr/raw/v1.2.0/screenshots/notes.png" width="720" />

Highlight key moments and take notes while listening.

<img alt="AI Summaries" src="https://github.com/rishikanthc/Scriberr/raw/v1.2.0/screenshots/ai-summary.png" width="720" />

Generate comprehensive summaries of your recordings.

<strong style="font-size: 1.2em;">Dark Mode</strong>







<img alt="Homepage Dark Mode" src="https://github.com/rishikanthc/Scriberr/raw/v1.2.0/screenshots/homepage-dark.png" width="720" />

Homepage in Dark Mode.

<img alt="Transcript Dark Mode" src="https://github.com/rishikanthc/Scriberr/raw/v1.2.0/screenshots/transcript-dark.png" width="720" />

Transcript view in Dark Mode.

### Mobile

<img alt="Mobile Homepage" src="https://github.com/rishikanthc/Scriberr/raw/v1.2.0/screenshots/homepage-mobile.PNG" width="300" />
<img alt="Mobile Homepage Dark" src="https://github.com/rishikanthc/Scriberr/raw/v1.2.0/screenshots/homepage-mobile-dark.PNG" width="300" />

PWA mobile app (Light & Dark).

<img alt="Mobile Transcript" src="https://github.com/rishikanthc/Scriberr/raw/v1.2.0/screenshots/transcript-mobile.PNG" width="300" />
<img alt="Mobile Transcript Dark" src="https://github.com/rishikanthc/Scriberr/raw/v1.2.0/screenshots/transcript-mobile-dark.PNG" width="300" />

Mobile transcript reading experience.

Installation

Get Scriberr running on your system in a few minutes.

Migrating from v1.1.0

If you are upgrading from v1.1.0, please follow these steps to ensure a smooth transition. Version 1.2.0 introduces a separation between application data (database, uploads) and model data (Python environments).

1. Update Volume Mounts

You will need to update your Docker volume configuration to split your data:

• Application Data: Bind your existing data folder (containing scriberr.db, jwt_secret, transcripts/, and uploads/) to /app/data.
• Model Environment: Create a new, empty folder and bind it to /app/whisperx-env.

2. Clean Up Old Environments

CRITICAL: You must delete any existing whisperx-env folder from your previous installation.

The Python environment and models need to be reinitialized for v1.2.0. If the application detects an old environment, it may attempt to use it, leading to compatibility errors. Starting with a fresh /app/whisperx-env volume ensures the correct dependencies are installed.

Install with Homebrew (macOS & Linux)

The easiest way to install Scriberr is using Homebrew. If you don’t have Homebrew installed, get it here first.

# Add the Scriberr tap
brew tap rishikanthc/scriberr

# Install Scriberr (automatically installs UV dependency)
brew install scriberr

# Start the server
scriberr

Open http://localhost:8080 in your browser.

Configuration

Scriberr works out of the box. However, for Homebrew or manual installations, you can customize the application behavior using environment variables or a .env file placed in the same directory as the binary (or where you run the command from).

Docker Users: You can ignore this section if you are using docker-compose.yml, as these values are already configured with sane defaults.

Environment Variables

Example .env file:

# Server settings
HOST=localhost
PORT=8080
APP_ENV=production

# Paths
DATABASE_PATH=/var/lib/scriberr/data/scriberr.db
UPLOAD_DIR=/var/lib/scriberr/data/uploads

# Security
JWT_SECRET=your-super-secret-key-change-this

Docker Deployment

For a containerized setup, you can use Docker. We provide two configurations: one for standard CPU usage and one optimized for NVIDIA GPUs (CUDA).

Standard Deployment (CPU)

Use this configuration for running Scriberr on any machine without a dedicated NVIDIA GPU.

1. Create a file named docker-compose.yml:

services:
  scriberr:
    image: ghcr.io/rishikanthc/scriberr:v1.2.0
    ports:
      - "8080:8080"
    volumes:
      - scriberr_data:/app/data # volume for data
      - env_data:/app/whisperx-env # volume for models and python envs
    environment:
      - APP_ENV=production # DO NOT CHANGE THIS
      # CORS: comma-separated list of allowed origins for production
      # - ALLOWED_ORIGINS=https://your-domain.com
      # - SECURE_COOKIES=false # Uncomment this ONLY if you are not using SSL
    restart: unless-stopped

volumes:
  scriberr_data: {}
  env_data: {}

1. Run the container:

docker compose up -d

NVIDIA GPU Deployment (CUDA)

If you have a compatible NVIDIA GPU, this configuration enables hardware acceleration for significantly faster transcription.

1. Ensure you have the NVIDIA Container Toolkit installed.
2. Create a file named docker-compose.cuda.yml:

services:
  scriberr:
    image: ghcr.io/rishikanthc/scriberr-cuda:v1.2.0
    ports:
      - "8080:8080"
    volumes:
      - scriberr_data:/app/data # volume for data
      - env_data:/app/whisperx-env # volume for models and python envs
    restart: unless-stopped
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities:
                - gpu
    environment:
      - NVIDIA_VISIBLE_DEVICES=all
      - NVIDIA_DRIVER_CAPABILITIES=compute,utility
      - APP_ENV=production # DO NOT CHANGE THIS
      # CORS: comma-separated list of allowed origins for production
      # - ALLOWED_ORIGINS=https://your-domain.com
      # - SECURE_COOKIES=false # Uncomment this ONLY if you are not using SSL

volumes:
  scriberr_data: {}
  env_data: {}

1. Run the container with the CUDA configuration:

docker compose -f docker-compose.cuda.yml up -d

App Startup

When you run Scriberr for the first time, it may take several minutes to start. This is normal!

The application needs to: 1. Initialize the Python environments. 2. Download the necessary machine learning models (Whisper, PyAnnote, NVIDIA NeMo). 3. Configure the database.

Subsequent runs will be much faster because all models and environments are persisted to the env_data volume (or your local mapped folders).

You will know the application is ready when you see the line: msg="Scriberr is ready" url=http://0.0.0.0:8080.

Post installation

Once you have Scriberr up and running:

• Configure Diarization: To enable speaker identification, visit the Configuration page.
• Usage Guide: For a detailed usage guide, visit https://scriberr.app/docs/usage.

Donating