AutoShorts v0.1.3

AutoShorts v0.1.3 Release Notes — Windows & Linux Support

This release officially introduces full compilation, packaging, and execution support for Windows and Linux users.

Windows & Linux Compatibility

Windows Integration

• Installer: Automatically packages native Windows .msi installers and .exe binaries.
• Typography Fallback: Implemented automatic fallback to standard Windows system fonts (prioritizing Segoe UI Bold and Arial Bold) so that visual captions render perfectly without requiring external font installations.

🐧 Linux Integration

• Installer: Automatically packages native Debian/Ubuntu .deb files and standalone portable .AppImage files.
• Typography Fallback: Implemented automatic fallback to standard Linux fonts (prioritizing DejaVu Sans Bold and FreeSans Bold) for accurate and clean caption burn-in on Linux systems.

---

Installation & Usage Guide

For Windows Users

1. Download AutoShorts_0.1.3_x64_en-US.msi.
2. Run the installer to add AutoShorts to your desktop apps.
3. Note (SmartScreen): Since the app is not signed with a Microsoft developer certificate:
   • If Windows SmartScreen blocks execution, click "More Info" on the warning popup.
   • Click the "Run anyway" button.

For Linux Users

• Debian/Ubuntu/Mint (.deb):
  Download the .deb file and install it by running the following command in your terminal:

  sudo apt install ./autoshorts_0.1.3_amd64.deb

v0.1.0 - Multi-LLM Moment Analysis, Selectable Caption Styles & Core Pipeline Fixes

AutoShorts v0.1.0 Release Notes

We are excited to release the foundational build of AutoShorts! This build provides local-first portrait video cropping, AI-powered viral moment analysis, and fully local caption burn-in styling.

---

🚀 Key Features & Updates

1. Interactive Caption Style Selector Modal

When importing a recording, the application now displays an interactive overlay Modal allowing you to select how automated captions should look on generated portrait shorts.

2. 7 Modern & Premium Design Presets

We have added seven distinct captions presets, rendered locally in FFmpeg using high-end system typography (prioritizing Futura and Avenir Next collections) and dynamic padding:

• Modern Box (Default): Cinematic uppercase white text inside a semi-transparent black padding box.
• Classic Outline: High-energy yellow bold text with a thick black outline (iconic CapCut/TikTok formatting).
• Minimal Shadow: Pure white text with a soft drop shadow.
• Vibrant Cyan: Modern tech-themed cyan text with a drop shadow.
• Vibrant Yellow Box: Bold black text inside a solid yellow padding box (Motivational/Reels style).
• Vibrant Green: High-contrast neon green text with outlines and shadows (Alex Hormozi style).
• Vibrant Red: Bold neon crimson text with drop shadows (Gaming/dramatic style).

3. Responsive Font & Layout Scaling

Captions are no longer static. The application automatically probes video dimensions and scales the font size and padding box proportionally based on the cropped portrait width. This guarantees text fits perfectly on any output resolution (from 202px width up to 1080px).

4. Absolute Timeline Synchronization

Fixed a bug where captions were missing/skipped on outputs. Shipped absolute timestamps alignment in the FFmpeg filter graph to match output-seeking Presentation Timestamps (PTS).

5. Robust Fallback Rendering

Improved error handlers to rescue from captioned render failures. If captioned rendering fails for any reason (e.g. missing fonts, local character escape conflicts), the application automatically falls back to rendering a clean crop without captions, saving the detailed error logs to the candidate’s DB entry.

6. Dynamic Multi-LLM Dispatcher (DeepSeek & Claude)

Supports both DeepSeek (default) and Claude (Anthropic) for moments detection. The active LLM settings and warnings dynamically adapt depending on the active LLM_PROVIDER environment variable, visible inside the collapsible API credentials sidebar.

7. Native Project Management

Added full database and backend support to Rename or Delete projects directly from the dashboard grid.

---

🛠️ Installation & Setup (FFmpeg Filter Requirements)

For captions to burn in locally, a full-featured build of FFmpeg is required.

1. Install FFmpeg using Homebrew:

   brew install ffmpeg

v0.1.0-alpha - Project Operations, Auto-Pipeline & Multi-LLM Support

AutoShorts v0.1.0-alpha

We are excited to release the alpha version of AutoShorts, a local-first desktop application designed to turn long-form video or audio recordings into highly shareable, ranked vertical clips.

What's New in this Release

• Multi-LLM Moment Ranking: Added native support for DeepSeek (default) and Claude (fallback) to find and score viral moments in your transcripts.
• API Settings UI: A collapsible settings panel in the top bar allows you to add API Keys for Deepgram, Claude, and DeepSeek, with a green (Active) label identifying the active model.
• Automated Chain Pipeline: Importing a file now automatically performs audio extraction, transcribes the file using Deepgram, and sends it to the active LLM for immediate viral moment detection.
• Project Manager: Rename and delete projects directly from the Home Dashboard or sidebar.
• Portrait Cropping: High-fidelity center-cropping of video into vertical H.264 clips (9:16 aspect ratio) using native ffmpeg integration.
• Visual Banners: Friendly warning banners warn users directly when required keys are missing, highlighting what key to add in API settings.

Installation Instructions

1. Download AutoShorts_0.1.0_aarch64.dmg (for M1/M2/M3 Apple Silicon Macs) or AutoShorts_0.1.0_x64.dmg (for Intel Macs).
2. Double-click the .dmg file and drag AutoShorts to your Applications folder.
3. On first run, right-click the app in Finder and select Open to bypass Gatekeeper.