
ReelKatha — Downloadable Story Reels Toolkit
Downloadable, local workflow kit — not an online Shorts or video service. ReelKatha is a skill you install in your own AI agent. It runs on your own computer with your own paid fal.ai key to plan and assemble complete 9:16 story reels. Nothing is generated or delivered by Capafy.
Before you buy: what you get
- Format: a downloadable ZIP containing one agent skill folder (
reelkatha-reels/:SKILL.md, Python scripts, reference docs, fonts, an example project, licence and third-party notices). No hosted service, no account on our side, no video is generated or delivered by Capafy or by ReelForge. - You run it yourself: your own AI agent client follows
SKILL.mdand runs the scripts on your own computer. Every image, voice and music track is generated by fal.ai with your own API key, billed by fal.ai to you. - Supported environment: an agent client that supports SKILL.md skills and can run shell commands. Built and tested with Claude Code; Codex, OpenClaw and similar clients should work (not separately tested). Python 3.9+, ffmpeg, Linux (tested) or macOS; on Windows use WSL. 4+ CPU cores and 4 GB+ RAM recommended, ~1 GB free disk per project, internet access to fal.ai.
- Base model: no LLM is bundled or included in the price; the kit uses whichever model your own agent client runs (built and tested with Anthropic Claude via Claude Code).
- Render time on your machine: a 60 s reel renders in about 4–6 minutes on a 4-core machine (measured), plus a few minutes of image/voice generation.
- Required account and key: a fal.ai account with billing and an API key (
FAL_KEY). Optional: an ElevenLabs key (ELEVENLABS_API_KEY) if you prefer to call ElevenLabs directly for the voice instead of through fal.ai. No other paid services are needed.
Installation
- Download the ZIP after purchase and unzip it into your agent's skills folder (Claude Code:
~/.claude/skills/reelkatha-reels/or<project>/.claude/skills/reelkatha-reels/). - Install Python 3.9+ and ffmpeg (macOS
brew install ffmpeg; Ubuntu/Debiansudo apt install ffmpeg). pip install -r requirements.txt(numpy, pillow, requests, opencv-python-headless).- Create a key at https://fal.ai/dashboard/keys and
export FAL_KEY=.... python3 scripts/check_env.pychecks everything. Then ask your agent for a reel (examples below).
Additional generation costs (paid by you to fal.ai, approximate list prices, Oct 2026)
| Item | Price | 60 s reel | 110 s reel |
|---|---|---|---|
| Images standard / pro 2K (Nano Banana / Nano Banana Pro on fal.ai) | ~$0.04 / ~$0.15 each | 11: $0.45 / $1.65 | 18: $0.72 / $2.70 |
| Voice (ElevenLabs v3 via fal.ai) | ~$0.10 per 1,000 characters | ≈ $0.08 | ≈ $0.15 |
| Music (ElevenLabs Music via fal.ai, per started minute) | ~$0.60/min | $0.60 | $1.20 |
| Optional AI video clips (Kling 2.1 on fal.ai) | ~$0.25 per 5 s | 3 clips $0.75 | 4 clips $1.00 |
| Total | ≈ $1.15 standard / ≈ $2.35 pro (+ clips) | ≈ $2.10 / ≈ $4.05 |
Provider prices can change; the kit shows an estimate before it generates anything. AI video clips are optional; every other shot uses free local camera motion.
What the kit does on your machine
Your agent writes one complete story (hook line in the first 3 seconds, re-hook around 25 s, shareable ending), generates consistent painted images through fal.ai, records the voiceover, generates or uses your music, then the kit's local code animates the images (Ken Burns moves, crossfades), burns in word-pop captions, adds the follow prompt, series pill and end card, and mixes with ffmpeg. It also writes a cover image and post copy.
Outputs in <project>/out/: reel.mp4 (1080×1920, 30 fps, −14 LUFS, 30–120 s), cover.jpg, and post.txt with a suggested Instagram caption, Shorts title/description and hashtags. It does not post anything and does not log in to your social accounts; you upload the files yourself. Hindi-first (Devanagari captions and fonts included); any language works.

How the samples were made (external services)
The sample frames, covers and reels on this page were made with this workflow. Their images were generated by Google Nano Banana / Nano Banana Pro models on fal.ai, the voiceover by ElevenLabs voices and the music by ElevenLabs Music (via fal.ai). Motion, captions, pills, cover layout and the final edit were produced locally by the kit's own code. Your results depend on those external services (their output quality, availability, content rules and prices) and on your prompts; reach and views are not promised.

Sample reels (from the Divya Chitrakatha channel, made with this workflow):
- https://www.instagram.com/reel/DeuRJhLCJ38
- https://www.instagram.com/reel/Deva4UWCT7J
- https://youtube.com/shorts/OpTa7ZWTOxI
Example prompts (to your own agent, after installing)
- "60-second Hindi reel: why did Kumbhakarna sleep for six months?"
- "A motivational story reel in English about a farmer who never gave up, cinematic style, with cover and caption."
- "Make 7 reels for this week from these topics: …" (one complete story each)
Styles
devotional-cinematic · cinematic-realistic · anime · storybook-watercolor · dark-mystery · pixar-3d — or describe your own.
FAQ
Is this a Shorts-making service? No. It is a set of files for your own agent. You run it, on your computer, with your own fal.ai account.
Do I need to code? No, your agent runs the commands, but you need to install Python, ffmpeg and the skill, and set your API key.
Does it post for me? No. It makes the files and the copy; you upload them.
Does it clone voices or faces? No. Library or self-designed voices only, and no real people in images.
Licence: single-buyer licence for unlimited personal and commercial use; third-party notices are in THIRD_PARTY_NOTICES.md.
Published by ReelForge.
外部 API
queue.fal.run · api.elevenlabs.io


