Spaces:
Running
A newer version of the Gradio SDK is available: 6.20.0
title: Nidra
emoji: 🌙
colorFrom: indigo
colorTo: purple
sdk: gradio
app_file: app.py
pinned: true
license: mit
short_description: An AI bedtime story, narrated in your own cloned voice.
tags:
- gradio
- build-small-hackathon
- agentic
- voice-cloning
- tts
- bedtime
- track:backyard
- sponsor:nvidia
- sponsor:openbmb
- sponsor:modal
- achievement:offbrand
- achievement:fieldnotes
- achievement:sharing
🌙 Nidra
A bedtime story, written for your kid and read in your voice.
You give a name, an age, and whatever they're into this week. A small agent writes the story; your cloned voice reads it back.
→ Open Nidra · 🎬 Watch the 1-min demo · 📣 Post on X · first run warms up on Modal (~3–5 min).
What it does
Type something like "Arjun, 5, a curious mongoose who finds a library under a banyan tree." Nidra writes an outline, then the full story, then narrates it line by line in the voice you upload (or a default warm one). You can download the whole agent trace if you want to see how it got there.
How it works
Two passes of NVIDIA's Nemotron-Nano-9B — outline, then story — and then VoxCPM2 voices each sentence. The Space itself is CPU-only; all the GPU work is a serverless Modal app that scales to zero between runs.
flowchart LR
A[name · age · theme] --> B[Nemotron: outline] --> C[Nemotron: story] --> D[VoxCPM2: narrate] --> E[🔊]
V[your voice clip] --> D
Built by @praxelhq for the HuggingFace Build Small hackathon — Backyard AI. Models: Nemotron-Nano-9B (NVIDIA) and VoxCPM2 (OpenBMB), both small, both on Modal. Build notes · agent traces shared on the Hub.