v0.3.0 - Gemini API Support

ShortGPT Release v0.3.0

This release introduces support for the Gemini API, providing an alternative to OpenAI for content generation within ShortGPT. This allows users to leverage the capabilities of Gemini, especially in scenarios where it may offer advantages in cost, speed, or specific task performance.

Major Changes:

• Gemini API Integration: Added support for using the Gemini API as a primary or fallback option. Users can now configure their Gemini API key and utilize it for content generation tasks.

• Priority API Key Logic: The system now prioritizes the Gemini API if a key is provided. If the Gemini API key is missing, it falls back to the OpenAI API.

• Configuration UI Update: The configuration tab has been updated to include a field for entering the Gemini API key.

Detailed Changes:

• Modified gui/ui_tab_config.py to include a Gemini API key field in the configuration UI and to handle saving the key.
• Updated gui/ui_tab_short_automation.py and gui/ui_tab_video_automation.py to check for the presence of a Gemini API key and use it as the primary option. Falls back to OpenAI if Gemini key is missing.
• Modified shortGPT/gpt/gpt_utils.py to utilize the Gemini API if a key is provided, using the gemini-2.0-flash-lite-preview-02-05 model.
• Added GEMINI to ApiProvider enum in shortGPT/config/api_db.py.
• Updated README-Docker.md and installation-notes.md to reflect the new GEMINI_API_KEY environment variable.

Upgrade Notes:

• Users who want to use the Gemini API will need to obtain a Gemini API key and enter it in the configuration tab.
• Ensure that you have properly set the GEMINI_API_KEY environment variable if running in a Docker environment.

Contributors:

• @RayVentura

If you're interested in contributing, we welcome pull requests and issues on our GitHub repository!

v0.2.0 - Bug Fix

ShortGPT Release v0.2.0

This release marks an overhaul and stabilization of ShortGPT after a period of inactivity. I've addressed core issues, upgraded key components, and made several quality-of-life improvements.

Major Changes:

• Stability Fixes: This release addresses numerous bugs that have accumulated, resulting in a much more stable and reliable experience.
• GPT Model Upgrade: Migrated from OpenAI's gpt-3.5 to gpt4-o-mini. This brings improved performance, more accurate content generation, and better overall results.
• MoviePy v2: Upgraded from MoviePy v1 to v2. This update brings performance enhancements and better compatibility with modern video formats.
• Font Change: Replaced the default font from Roboto to Luckiest Guy, to improve captions.
• Coqui TTS Removed: Removed support for Coqui TTS engine as it's barely maintained.
• OpenAI and Eleven Labs Key Names Changed: Changed the keys from OPENAI and ELEVEN LABS to OPENAI_API_KEY and ELEVENLABS_API_KEY respectively.

Other Notable Improvements:

• Code Cleanup: Performed general code cleanup and refactoring for better maintainability and readability.
• Improved Error Handling: More descriptive error messages to help users troubleshoot issues.
• Streamlined Dependencies: Optimized the project's dependencies for an easier installation process.

Detailed Changes:

• Updated gui/ui_tab_short_automation.py, gui/ui_tab_video_automation.py, and gui/ui_tab_video_translation.py to reflect the changes in TTS engines, language options, and API key names.
• Updated dependencies in requirements.txt and setup.py.
• Updated documentation to reflect the latest changes.

Upgrade Notes:

• Users upgrading from previous versions should update their API key configurations to use the new names: OPENAI_API_KEY and ELEVENLABS_API_KEY.
• Due to the removal of Coqui TTS, users relying on it will need to switch to either ElevenLabs or EdgeTTS.
• Users should be aware of the font change and its impact on the visual style of generated videos.

Contributors:

• @RayVentura

** If you're interested in contributing, we welcome pull requests and issues on our GitHub repository! **

What's Changed

• Update README.md by @RayVentura in #83
• added Dockerfile, README-Docker.md, modf /gui/gui-gradio.py by adding… by @deftio in #98
• Fixes to outdated OpenAI API references by @abirabedinkhan in #119
• [Enhancement]: Add suppport for coqui xtts local text-to-speech by @Paillat-dev in #126
• 🔒 chore(deps): update openai version to 1.10.0 by @Paillat-dev in #128
• Pin gradio_client version by @abidlabs in #129

New Contributors

• @deftio made their first contribution in #98
• @abirabedinkhan made their first contribution in #119
• @Paillat-dev made their first contribution in #126
• @abidlabs made their first contribution in #129

Full Changelog: v0.1.3...v0.2.0

v0.1.3

CHANGES

Version 0.1.3

• Requiring a youtube url as the subscribe animation url in the EditingStep.ADD_SUBSCRIBE_ANIMATION step.
• Adding a default subscribe animation youtube link by default shipped in the AssetDatabase
• Making path imports relative for gpt prompts and editing blocks and flows.

Version 0.1.2

• Improving logs in content engines

Version 0.1.1

• Adding AssetType in AssetDatabase
• Adding ApiProvider in api_db
• Fixing pip libary missing editing_framework module, prompt_template module

Version 0.1.0

• Fixing the AssetDatabase when it's empty

Version 0.0.2

• Implemented the content_translation_engine; a multilingual video dubbing content engine. The source can be found at shortGPT/engine/content_translation_engine.py.
• Implemented the new EdgeTTS voice module; it can be found at shortgpt/audio/edge_voice_module.
• Added documentation which can be found under docs/.

v0.0.2

What's Changed

CHANGES

Version 0.0.2

• Implemented the content_translation_engine; a multilingual video dubbing content engine. The source can be found at shortGPT/engine/content_translation_engine.py.
• Implemented the new EdgeTTS voice module; it can be found at shortgpt/audio/edge_voice_module.
• Added documentation which can be found under docs/.

===

• Add .github/ folder by @Erim32 in #46
• Code refactoring and improvements, part 1 by @Erim32 in #52
• fixing short generation format issue by @vembarrajan in #57
• Update README.md by @RayVentura in #76

New Contributors

• @Erim32 made their first contribution in #46
• @vembarrajan made their first contribution in #57
• @LogicalCode22 made their first contribution in #66
• @RayVentura made their first contribution in #76

Full Changelog: v0.0.15-alpha...v0.0.2

v0.0.15-alpha

• Addition of contentTranslationEngine: This new feature accepts a link or a video file path, along with a target language, and outputs a dubbed version of the content. This advancement significantly enhances our content accessibility and international reach.

• Implementation of contentTranslationUI in Gradio UI: This update aims to improve the user experience by making the process of content translation more seamless and intuitive.

• Improvement of translation prompts: We have refined our translation prompts to be more efficient and effective, further improving the overall functionality of our platform.

What's Changed

• fix typo in video_automation_ui.py by @eltociear in #10

New Contributors

• @eltociear made their first contribution in #10

Full Changelog: v0.0.1-alpha...v0.0.15-alpha

v0.0.1

v0.0.1-alpha

Update README.md