reelbot
A pipeline that turns one prompt into a finished 30 to 45 second reel: AI script, AI voice, Remotion video and a scheduled post.
AI VIDEO PRODUCTION
An AI video editor uses AI tools for time-consuming steps like transcription, captions, voice and first drafts, while a person still decides what makes a good video. Salman Faris is an AI video editor in Kerala who has built his own pipeline that takes a reel from script to scheduled post.
For creators and brands that need more video without hiring a full team.
AI is excellent at the slow, mechanical parts of editing: finding words in a recording, generating captions, cleaning sound and repeating a format. It is poor at taste. Deciding what to cut, and when a moment works, is still an editor’s job.
I use AI where it saves time and leave the judgment to people. That is how the 30-part reel series was built: voice takes were split by topic, captions were aligned to each word, and every reel was checked by hand.
Regular posting takes more editing hours than you have.
Manual subtitles slow everything down, especially in Malayalam.
Fully automated edits often feel generic and lose trust.
Agreed in writing before work starts.
Transcript-based cuts and faster rough edits.
Word-accurate captions in English, Malayalam or a mix.
Voiceover production with tools like ElevenLabs, using voices you have the rights to.
Automated series production with a human review step.
Real work where it exists, and clearly labelled concepts where it does not.
A pipeline that turns one prompt into a finished 30 to 45 second reel: AI script, AI voice, Remotion video and a scheduled post.
30 Malayalam explainer reels on AI and tech, built with a data-driven motion engine, 3D titles and word-synced captions.
Repeat steps only. The story stays human.
One great reel becomes the template for the series.
Scripts, voice, captions and renders in batches.
Sync, spelling and pacing get checked before anything is posted.
I work from Calicut with creators and brands across Kerala. Malayalam and mixed-language audio are handled from the start, because that is what most of my own videos use.
It can handle captions, transcripts and repeated formats, but it cannot decide what makes your video worth watching. The best results come from an editor who uses AI to go faster.
Yes, when the client has the rights to the voice and is happy to use one. Cloning anyone’s voice needs their clear permission.
Not if it is done well, because AI handles the mechanical steps and a person handles the taste. Where a platform or the law needs AI content labelled, that gets done.
For brands, creators, educators and event clients who need footage turned into something people watch.
For teams losing hours to repetitive tasks that follow clear rules.
For local brands, educators and creators who need a posting system they can keep up.
NEXT STEP
Tell me what you post now and how often you would like to post.