GenAI Studio · Python + FastAPI

Imagine it.
Say it.
Watch it move.

One studio for every kind of AI: chat with a brain that sees images, talk with your voice, paint pictures, and direct short films — all from a single prompt.

PythonFastAPIOpenAI GPTGroq WhisperOpenAI TTS GeminiKling AIffmpegMoviePyServer-Sent EventsHTML · CSS · JS PythonFastAPIOpenAI GPTGroq WhisperOpenAI TTS GeminiKling AIffmpegMoviePyServer-Sent EventsHTML · CSS · JS
01 — Capabilities

Four senses. One studio.

Text

Streaming answers with memory, markdown and code — plus 4 personalities from Teacher to Hinglish buddy.

gpt-5.4-mini

Voice

Speak instead of typing and hear every reply in one of 10 natural voices.

Whisper · TTS

Image

Show it a photo to understand — or ask it to paint anything you can describe.

Vision · Gemini · GPT-Image

Video

Text → video, image → video and multi-scene AI stories with a narrator.

Kling AI · Motion Preview
02 — How it works

From a sentence to a scene.

  1. 01

    You ask

    Type, speak or drop an image into the chat.

  2. 02

    AI decides

    The model picks a tool: answer, paint or film (function calling).

  3. 03

    Engines create

    Python calls Gemini, OpenAI, Groq and Kling in the background.

  4. 04

    You watch

    Results stream back live — words, pictures, video and voice.

0AI APIs connected
0Modalities
0Natural voices
0Video modes

Your imagination, rendered.

Start with a sentence. Kalpana handles the rest.

Create a video
Kalpana · GenAI Studio — 2nd-year B.Tech project Built with Python, FastAPI & vanilla JS