🎬 Movie House Studio

Your all-in-one AI video pipeline — write, image, video & audio. Powered by Google Gemini + Azure.

📝 Script
🎨 Image
✨ Edit
🎥 Video
🗣 Voice
🔊 Burmese Voice
🌐 Translate
📝 Transcribe
🖼 Describe / OCR
🎵 MP4 → MP3
🗣️ Voice Clone

Google Gemini API key

How do I get this?

One key for all Google tools — from Google AI Studio → Get API key. Text generation has a generous free tier.

Write scripts, captions & scene ideas

Azure Speech credentials

How do I get these?

Create a free Azure account → create a Speech resource (tier F0) → Keys and Endpoint → copy KEY 1 + Region.

Text

Nilar
Female
Thiha
Male
Checking Azure voice engine…

Azure Translator credentials

How do I get these?

In Azure, create a Translator resource (tier F0 = 2M chars/month free) → Keys and Endpoint → copy KEY 1 + the Location/Region. (This is a different resource from Speech.)

Translate

Azure Speech credentials

Uses the same Speech resource as the Voice tab.

Transcribe an audio / video file

MP3, M4A, WAV, or MP4 video. Audio is extracted automatically. Best in Chrome / Edge. Max ~100 MB. For large videos, use the 🎵 MP4 → MP3 tab first to shrink them.

Convert video / audio to MP3

Pulls the audio out of a video (or re-encodes audio) and saves it as an MP3 — useful for shrinking a large MP4 before transcribing, or grabbing audio for your pipeline. Runs entirely in your browser; nothing is uploaded.

VoxCPM2 Voice Clone

Free, no API key — uses the public OpenBMB VoxCPM2 demo Space. It's shared by everyone, so generation can be slow or queued (up to a few minutes).

Narration

Tone is baked into the voice itself — changing it requires clicking Generate again.
No file chosen. Works best with a clean 3–50 second clip, under 10 MB.
Advanced

Azure AI Vision credentials

How do I get these?

In Azure, create a Computer Vision (Azure AI Vision) resource → Keys and Endpoint → copy the Endpoint URL and KEY 1. Note: image captions need a region like East US, West US 2, or West Europe; OCR works in all regions.

Analyze an image

preview

Google Gemini API key

How do I get this?

Same key as the Video tab — from Google AI Studio → Get API key. Imagen is a paid feature (cheaper than Veo).

Generate an image

Google Gemini API key

Generate or edit an image (Nano Banana)

Google Gemini API key

Great for English / multilingual narration with natural style. For Burmese, use the 🔊 Burmese Voice tab (Azure) instead.

AI voice narration

Google Gemini API key

How do I get this?

Go to Google AI Studio → Get API key. Veo video generation is a paid feature — you must enable billing on the key. Generation takes 1–3 minutes per clip.

Generate a video clip

Leave empty for text-to-video. Add an image (e.g. one from the 🎨 Text to Image tab) to animate it.