Educational AI video · Hindi / Hinglish · Slipchat
Swiftee Educational Video Platform
Configurable storytelling presets drive an Inngest durable pipeline (Gemini, Kie.ai, ElevenLabs, Rendi/FFmpeg). Jobs show slide-by-slide progress; only failed slides need regeneration. Operators get a finished short in minutes instead of a multi-day creative cycle.
- Role
- Lead engineer
- Status
- Production
- Year
- 2025
Metrics
- Length
- 60s · 9:16
- Slides
- 10
- Language
- Hindi / Hinglish
- Cycle time
- Days → minutes
Stack
Problem
Slipchat needs Hindi educational shorts at catalog scale for rural learners. Manual production - brief, script, storyboard, art, voice, edit, subtitles, music, export - took days per episode, drifted in quality, and could not keep up with curriculum demand.
Solution
Operators submit one topic against a storytelling preset. Swiftee writes a 10-slide Hinglish script, then runs mascot, voiceover, b-roll, subtitles, music, and thumbnail generation in parallel. The job dashboard shows slide-by-slide progress; failed slides regenerate without re-running the whole video. Output is a publish-ready 60-second 9:16 short.
Architecture
Key Engineering Decisions
Topic → short as the product contract
The success metric is a finished 60-second Hindi educational video, not a pile of intermediate assets. Everything in the pipeline exists to protect that outcome.
Parallel production with slide-level recovery
Assets generate in parallel for speed; the dashboard tracks each slide so a single Kie/ElevenLabs failure does not force a full restart.
Presets for vernacular storytelling consistency
Mascot tone, voice, subtitle look, and prompt packs live in presets - curriculum teams get repeatable episodes without re-tuning the model stack every run.
Inngest + Rendi for long media jobs
Image/i2v and FFmpeg steps take minutes. Durable Inngest steps checkpoint provider waits; Rendi owns FFmpeg so the app runtime stays free of native binaries.
Build Notes
- Configurable storytelling presets: slide count, voice, subtitle style, b-roll type, timing, and AI system prompts
- Preset snapshotted onto each job so creative tweaks never break in-flight renders
- Parallel asset generation - script, mascot/images, VO, captions, music, thumbnail - then a single FFmpeg stitch
- Slide-level progress UI; regenerate only the failed slide instead of the entire episode
- Hinglish script with a transliteration pass so on-screen captions stay easy to scan
- Rendi (FFmpeg-as-a-service) for normalize → concat → narration → music → burn SRT in one merge
Results
- Topic → finished 9:16 Hindi short in minutes instead of days
- 10-slide Hinglish episodes with mascot, VO, subtitles, music, and thumbnail
- Slide-by-slide ops: regenerate failures without re-rendering the whole video
- Preset-locked output suitable for Slipchat’s rural education catalog
Automation outputs
Real videos generated by the pipeline from a topic prompt - play any short below.
Educational shorts
How The Amul Revolution Changed India
The White Revolution that transformed dairy farming.
Who Hid The Treasure Of Padmanabhaswamy Temple
The mystery behind one of the world's richest temples. (v1)
The First Indian To Travel Into Space
The incredible journey of Rakesh Sharma.
Who Hid The Treasure Of Padmanabhaswamy Temple
The mystery behind one of the world's richest temples. (v2)
Chintu Mastermind
Why blood is red
Why songs get stuck in your head
What is a black hole?
Why this matters
- Shipped vernacular educational video automation end-to-end for Slipchat
- Parallel AI production pipeline with slide-level failure recovery
- Preset architecture that keeps storytelling stable under iteration
- Production FFmpeg merge via Rendi on a durable Inngest workflow