90210 – running the show without property tax
Summary
90210 is a production-grade local app that uses AI models like Google Veo 3.1, Gemini 2.5 Pro, and ElevenLabs Music to turn screenplays into finished short films with synchronized video, audio, dialogue, music, and subtitles, featuring a quality oracle for auto re-rolls.
View Cached Full Text
Cached at: 06/08/26, 03:15 AM
Achint08/90210
Source: https://github.com/Achint08/90210
📍🎬 90210
Like the show. But you’re the showrunner.
All the drama. None of the property tax.
A production-grade local app that turns a screenplay into a finished short film with synchronized video, native audio, dialogue, music, and subtitles. Powered by Google Veo 3.1, Nano Banana, Gemini 2.5 Pro, and ElevenLabs Music.
Every quality decision is mathematically grounded: a composite Quality Oracle (VideoScore, ViCLIP, LAION aesthetic, MUSIQ, ArcFace, LPIPS, Whisper) drives auto re-roll and adaptive tier escalation. A Story Oracle (Reagan-6 arcs, TRIPOD turning points, Average Shot Length, SBERT coherence) keeps the narrative on target.
Quick start
# 0. one-time
python3 -m venv .venv
.venv/bin/pip install -e ./backend # installs FastAPI + Pydantic + Google + ElevenLabs deps
cp .env.example .env # fill in GEMINI_API_KEY and ELEVENLABS_API_KEY
# 1. Backend
./run-backend.sh # starts uvicorn at http://localhost:8000
# (the script sets PYTHONPATH because Homebrew Python 3.14 ships its own
# sitecustomize.py that breaks venv editable installs — PYTHONPATH sidesteps it.)
# 2. Frontend (new shell)
cd frontend
pnpm install # or npm install
pnpm dev # → http://localhost:3000
# 3. iPhone access
# - same WiFi: http://<laptop-ip>:3000 → Safari Share → Add to Home Screen
# - off-WiFi: tailscale serve / funnel (see docs)
# 4. Optional Quality Oracle (heavy ML deps; ~3GB)
.venv/bin/pip install -e "./backend[oracles]"
Documentation
- Design spec:
docs/superpowers/specs/2026-05-09-screenplay-to-movie-design.md - Veo 3.1 reference:
docs/superpowers/research/veo-3.1-deep-dive.md - Cost / latency / quality math:
docs/superpowers/research/cost_latency_quality_math.py
Required API keys
| Service | Used for | Cost (May 2026) |
|---|---|---|
| Gemini API | Veo 3.1 (video+audio), Nano Banana (portraits), Gemini 2.5 Pro (Director) | $0.10–0.40/sec video |
| ElevenLabs | Music tracks | $0.01/sec music |
A 2-min movie typically costs ~$20.
Architecture
See spec §4. Local FastAPI backend + Next.js PWA frontend. PWA installs to home screen on iOS Safari for native-app-like experience.
Similar Articles
I built an Agentic AI Filmmaking Studio for people who have stories to tell but lack the budget and technical skills. (Giving away 10 free credits for the next 48 hours)
MotionX Studio launches as an Agentic AI Filmmaking Studio that uses a trained AI Director, taxonomy engine, and art engine to turn scripts into cinematic visuals, offering 10 free credits for the first 48 hours.
OmniScript: Towards Audio-Visual Script Generation for Long-Form Cinematic Video
This paper introduces OmniScript, an 8B-parameter omni-modal (audio-visual) language model for a novel video-to-script (V2S) task that generates hierarchical, scene-by-scene scripts from long-form cinematic videos. Trained via progressive pipeline techniques including chain-of-thought SFT and reinforcement learning with temporally segmented rewards, OmniScript outperforms larger open-source models and rivals proprietary models like Gemini 3-Pro.
AI gives us the 80s TV show we should have had
Article discusses AI being used to create an 80s-style TV show that would have fit that era.
@GitTrend0x: Holy cow, guys! Run voice cloning and cinematic video dubbing locally, supporting 646 languages, fully offline, no API key, no internet needed. ElevenLabs is crushed! https://github.com/debpalash/OmniVoice-Studio… This open-source marvel is insane...
OmniVoice Studio is an open-source desktop app that enables local voice cloning and cinematic video dubbing across 646 languages, fully offline with no API keys, positioning itself as a privacy-focused alternative to ElevenLabs.
@noisyb0y1: GOOGLE JUST SHOWED HOW TO BUILD A PRODUCTION-GRADE FINANCIAL ANALYST IN UNDER 10 MINUTES they dropped a full tutorial u…
Google released a tutorial demonstrating how to build a production-grade financial analyst app in under 10 minutes using Gemini 3 and Vertex AI Studio, with automated code generation and zero manual setup.