Scriberr

Introduces a new CLI with background service management, real-time chat streaming, OpenAI transcription support, and a comprehensive UI/UX redesign with a new design system.

This release introduces OpenAI query timeout increases, speaker renaming, auto-transcription on upload, and various UX improvements and bug fixes.

This release fixes issues related to the Homebrew package installation.

Version 1.0.3 includes a bug fix for issue #163.

Fixes ctranslate issues on Arch Linux and Ubuntu.

This release includes several bug fixes for Docker permissions and environment variables, updates diarization to use whisperX-cli, and removes unused Python scripts.

Scriberr v1.0.0 introduces core transcription features, including audio uploads, YouTube integration, transcript annotation, LLM provider configuration, and a responsive UI with light and dark modes.

This beta release introduces core transcription and chat functionality, featuring Ollama support, YouTube audio downloading, account management, and an improved responsive UI with dark mode.

Updates whisperx syntax to maintain compatibility with the latest version.

Updated CUDA support to version 12.8 and improved database configuration.

Introduces speaker diarization via PyAnnote, enhances authentication and UI responsiveness, and optimizes Docker deployment with CUDA 12.8 and ARM64 support.

This release improves speaker diarization, introduces an NVIDIA GPU image, adds a model configuration wizard, and optimizes Docker images by separating Pocketbase.

Fixed issues with Docker images used for diarization.

Added and enhanced speaker diarization functionality.

Updates the Dockerfile to resolve curl availability issues and includes UI fixes.

Added support for alternative OpenAI API Spec services like Ollama and reduced image size using multi-stage builds.