Planned
9Committed and queued
Auto post to social media platforms with direct integrations
Automatically post content generated to social media platforms like YouTube, Instagram, X/Twitter, LinkedIn, etc Add your suggestions and use cases in the comments
Edit caption style / Custom video caption templates
Ability to customize the style and position of the captions of generated clips including a library of caption templates to choose from.
Group apps/projects into folders and/or tags
To help organize your projects, add the ability to group projects together into folders or tags to easily filter through them
Claude 3.5 Sonnet integration
Support for Workspaces & Teams
Add ability to invite users into my workspace to share and collaborate on projects
Create Clips from Transcript by highlighting parts
Add the ability to create and edit clips by highlighting the portion of the transcript you want as a clip. Idea for process would be upload your video, highlight parts of transcript, then generate clips.
Make.com integration
Ability to import or export content from integrations available on Make.com. This allows you to create more customized actions and workflows to trigger from Alphana.
Options to copy/download transcript with and without timestamps & speakers
Currently, when you copy the transcript, it contains the speakers and timestamps. Please add the ability to download multiple versions, including: - With time & speakers info - no time or speaker info - full transcript SRT & VTT file
Make "Copy" button retain formatting when pasting into docs or notes
Next
Committed and queued
No Next issues
In Progress
2Actively being built
Webhooks Integration
Webhooks to import and automate export of content to other platforms like social media, CRM’s, productivity tools and more.
SRT/VTT Download option
Add the ability to download the SRT and VTT files for each audio/video project.
Completed
40Recently shipped
Auto detect and crop speakers for Vertical short-form clips
For vertical videos, automatically reframe the speaker to the center. When multiple speakers are detected, display the active speaker centered on the screen. The optional option is not to reframe but instead use a full horizontal/landscape video positioned center on the vertical format.
Source transcript / captions editing
Sometimes, automated captions contain errors. In order to avoid wrong captions appearing in the video pieces, editing the source transcript should be possible so that clips and source content are accurate before generating content. Edits include transcripts and speakers for accuracy.
BYOK for LLM usage
Allow users to add their own API key to run LLM queries through their accounts on OpenAI
Global Language Selector
Possibility to select a language for outputs without global instructions. Workaround available today… here’s how!
Search your video library
Ability to search to find a video/app you generated
Ability to select SOURCE video/audio language for more accurate transcriptions
Currently, Alphana attempts to detect the source language automatically. Auto-detection isn’t accurate for some languages and can lead to inaccurate transcripts. This update will allow users to select the source language manually for better accuracy.
GPT-4o mini support
Add Ability to create Instagram Carosuls
Create IG carousels (images with text) from the content that we upload.
Show AI credits usage in dashboard
Performance & reliability fixes
Several performance enhancements and reliability fixes under the hood to improve the overall experience.