Paradee 1.3

Paradee 1.3

Speaks text aloud with a tiny multilingual text-to-speech model that has eight voices in English, Hindi, French and Spanish and runs on a plain CPU. It suits people who want light speech output.

Made by sahilmahendrakar on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: This Space is a demo of Paradee-8M-v1.3, a single text-to-speech model that speaks more than one language. The model has 7.88M parameters, and one file of 8.5 MB holds eight voices across English, Hindi, French and Spanish. The Space runs it on cpu-basic hardware at Hugging Face and is tagged MCP.

Who it suits: It suits people who want speech from a tiny model without a GPU, and developers who care about how small a voice model can get.

Industry | Who uses it | How they use it | Example
Accessibility | App makers | Add spoken output to a light app | Read a short message aloud in Hindi
Content creation | Creators working in several languages | Make quick voice clips from text | Generate a French line to test a script
AI research | Researchers | Look at how small a multilingual voice model can be | Compare the voices across the four languages

You can skip it if you need a large voice library, since the model has eight voices.

Where to use it: You can use it in these places:

• A browser: open the Space's page on Hugging Face and nothing needs installing.
• Windows, macOS or Linux: run your own copy with Python 3.12, with no GPU required.

Use case | Who | What they get back
Text to speech | Anyone | Audio of your text in one of eight voices
Multilingual voice-over | Creators | Short clips in English, Hindi, French or Spanish

How to set it up: You need these first for a local copy:

• Python 3.12 and pip
• A normal computer, since the model is small enough for a CPU

The online page needs none of this. For your own copy, follow the steps below.

1. Install the Hugging Face tools.
2. Download the Space's files into a folder.
3. Move into that folder.
4. Install Gradio at the version the Space uses, then the other packages.
5. Start the app.

pip install -U huggingface_hub
hf download sahilmahendrakar/paradee --repo-type space --local-dir paradee
cd paradee
pip install gradio==6.29.1
pip install -r requirements.txt
python app.py

How to use it: Open the Space in a browser, or start your own copy with the command below. Then type your text, choose one of the eight voices and generate the audio.

python app.py

Example: You type a short sentence, choose one of the eight voices and press generate. The Space returns an audio clip of the sentence in that voice, made on a plain CPU.

For newcomers and experts: If you are new to this, type one short sentence and try a few of the voices. Switch the language of the sentence to hear how the same model handles another language.

If you know the field, the point of the project is size. A single multilingual TTS model of about 8 million parameters fits in an 8.5 MB file, so it runs on a free CPU. The Space also names Kokoro-82M, though the source does not say how it is used.

You type a sentence
You pick one of eight voices
The small model runs on a CPU
You play the audio

Good to know: The model covers four languages, English, Hindi, French and Spanish. Other languages are not mentioned in the source.

• License: apache-2
• Cost to run: none named
• Data it reaches: the text you type, and the model files downloaded from Hugging Face

On Hugging Face, 13 November 2026

• Likes: 60
• Built with: gradio
• License: apache-2.0

Links

• Space: https://huggingface.co/spaces/sahilmahendrakar/paradee
• Files: https://huggingface.co/spaces/sahilmahendrakar/paradee/tree/main

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.