⚡ Detailed Input and Output Specification
Every Gradio interface relies on explicit mapping between user-facing input controls and result display outputs. Below are 10 real-world applications showcasing exact combinations of input parameters and output components.
Example 1: Sentiment Analysis Tool
Analyzes user feedback text and outputs confidence classification percentages.
Python (sentiment_app.py)
import gradio as gr
def analyze_sentiment(text):
score = len(text) % 2
if score == 0:
return {"Positive": 0.85, "Neutral": 0.10, "Negative": 0.05}
else:
return {"Positive": 0.15, "Neutral": 0.20, "Negative": 0.65}
demo = gr.Interface(
fn=analyze_sentiment,
inputs=gr.Textbox(label="Customer Feedback", placeholder="Type review here...", lines=3),
outputs=gr.Label(label="Sentiment Classification Results"),
title="Customer Feedback Sentiment Analyzer"
)
if __name__ == "__main__":
demo.launch()
Inputs Mapping: gr.Textbox (label="Customer Feedback")
Outputs Mapping: gr.Label (label="Sentiment Classification Results")
Outputs Mapping: gr.Label (label="Sentiment Classification Results")
Example 2: House Price Predictor
Estimates real estate pricing based on square footage, bedrooms, and location score.
Python (housing_app.py)
import gradio as gr
def predict_price(sqft, beds, loc):
return (sqft * 150) + (beds * 25000) + (loc * 50000)
demo = gr.Interface(
fn=predict_price,
inputs=[
gr.Slider(500, 5000, value=1500, label="Square Footage (sqft)"),
gr.Number(value=3, label="Number of Bedrooms"),
gr.Slider(1, 10, value=5, label="Location Rating (1-10)")
],
outputs=gr.Number(label="Estimated Asset Price ($)"),
title="Real Estate Valuation Calculator"
)
if __name__ == "__main__":
demo.launch()
Inputs Mapping: [gr.Slider (sqft), gr.Number (beds), gr.Slider (location)]
Outputs Mapping: gr.Number (Estimated Asset Price)
Outputs Mapping: gr.Number (Estimated Asset Price)
Example 3: AI Image Watermarker
Overlays custom text watermarks onto uploaded photographs using PIL.
Python (watermark_app.py)
import gradio as gr
from PIL import Image, ImageDraw
import numpy as np
def add_watermark(image_np, watermark_text):
img = Image.fromarray(image_np.astype('uint8'), 'RGB')
draw = ImageDraw.Draw(img)
draw.text((20, 20), watermark_text, fill=(255, 0, 0))
return np.array(img)
demo = gr.Interface(
fn=add_watermark,
inputs=[
gr.Image(label="Source Image Upload", type="numpy"),
gr.Textbox(label="Watermark Text", value="Nikita Infotech")
],
outputs=gr.Image(label="Watermarked Output Image"),
title="Batch Image Watermarker"
)
if __name__ == "__main__":
demo.launch()
Inputs Mapping: [gr.Image (Source Image), gr.Textbox (Watermark Text)]
Outputs Mapping: gr.Image (Watermarked Output Image)
Outputs Mapping: gr.Image (Watermarked Output Image)
Example 4: Audio Speech Pitch Shifter
Accepts microphone recordings or audio files and outputs processed audio streams.
Python (audio_app.py)
import gradio as gr
def process_audio(audio_data):
if audio_data is None:
return None
sr, y = audio_data
y_processed = y[::-1]
return (sr, y_processed)
demo = gr.Interface(
fn=process_audio,
inputs=gr.Audio(label="Record Voice / Upload Audio File", type="numpy"),
outputs=gr.Audio(label="Modified Audio Stream Output"),
title="Audio Effect Studio"
)
if __name__ == "__main__":
demo.launch()
Inputs Mapping: gr.Audio (Record/Upload)
Outputs Mapping: gr.Audio (Modified Audio Stream Output)
Outputs Mapping: gr.Audio (Modified Audio Stream Output)
Example 5: Financial Investment Growth Simulator
Simulates compound interest growth curves over years based on asset allocation.
Python (finance_app.py)
import gradio as gr
import matplotlib.pyplot as plt
import numpy as np
def simulate_investment(principal, years, risk_profile):
rates = {"Conservative": 0.06, "Balanced": 0.10, "Aggressive": 0.15}
r = rates.get(risk_profile, 0.08)
t = np.arange(0, int(years) + 1)
balance = principal * (1 + r) ** t
fig, ax = plt.subplots(figsize=(6, 4))
ax.plot(t, balance, color='#f37626', lw=3, marker='o')
ax.set_title(f"Portfolio Growth ({risk_profile} Strategy)")
ax.grid(True)
return fig
demo = gr.Interface(
fn=simulate_investment,
inputs=[
gr.Number(value=10000, label="Initial Investment ($)"),
gr.Slider(1, 30, value=10, label="Investment Horizon (Years)"),
gr.Dropdown(choices=["Conservative", "Balanced", "Aggressive"], value="Balanced", label="Risk Profile")
],
outputs=gr.Plot(label="Growth Projection Chart Plot"),
title="Compound Investment Growth Simulator"
)
if __name__ == "__main__":
demo.launch()
Inputs Mapping: [gr.Number (Principal), gr.Slider (Years), gr.Dropdown (Risk Profile)]
Outputs Mapping: gr.Plot (Growth Projection Chart Plot)
Outputs Mapping: gr.Plot (Growth Projection Chart Plot)
Example 6: CSV Data Filter & Aggregator
Processes uploaded tabular datasets and returns sorted dataframes.
Python (csv_app.py)
import gradio as gr
import pandas as pd
def filter_csv(file, sort_column):
if file is None:
return pd.DataFrame()
df = pd.read_csv(file.name)
if sort_column in df.columns:
df = df.sort_values(by=sort_column, ascending=False)
return df
demo = gr.Interface(
fn=filter_csv,
inputs=[
gr.File(label="Upload CSV Dataset File"),
gr.Textbox(label="Column Name to Sort By", value="id")
],
outputs=gr.Dataframe(label="Processed Data Grid Output"),
title="Tabular CSV Data Processor"
)
if __name__ == "__main__":
demo.launch()
Inputs Mapping: [gr.File (CSV Dataset), gr.Textbox (Sort Column)]
Outputs Mapping: gr.Dataframe (Processed Data Grid Output)
Outputs Mapping: gr.Dataframe (Processed Data Grid Output)
Example 7: JSON API Payload Generator
Constructs formatted API request bodies dynamically based on user form selections.
Python (json_app.py)
import gradio as gr
def generate_payload(username, email, newsletter, role):
return {
"status": "success",
"user": {
"username": username,
"email": email,
"newsletter": newsletter,
"role": role
}
}
demo = gr.Interface(
fn=generate_payload,
inputs=[
gr.Textbox(label="Username", value="nikita_user"),
gr.Textbox(label="Email Address", value="admin@nikita-infotech.com"),
gr.Checkbox(label="Subscribe to Newsletter", value=True),
gr.Radio(choices=["Admin", "Developer", "Viewer"], value="Developer", label="Access Role")
],
outputs=gr.JSON(label="Formatted JSON Object Output"),
title="Dynamic API Payload Builder"
)
if __name__ == "__main__":
demo.launch()
Inputs Mapping: [gr.Textbox (Username), gr.Textbox (Email), gr.Checkbox (Newsletter), gr.Radio (Role)]
Outputs Mapping: gr.JSON (Formatted JSON Object Output)
Outputs Mapping: gr.JSON (Formatted JSON Object Output)
Example 8: Markdown CV / Resume Generator
Builds professional resume profile blocks dynamically rendered via Markdown markup.
Python (cv_app.py)
import gradio as gr
def generate_resume(name, title, skills):
return f"""# 👨💻 {name}\n### *{title}*\n---\n### 🛠 Skills\n- {skills}"""
demo = gr.Interface(
fn=generate_resume,
inputs=[
gr.Textbox(label="Full Name", value="Alex Developer"),
gr.Radio(choices=["Full Stack Engineer", "AI Researcher"], value="AI Researcher", label="Title"),
gr.Textbox(label="Skills", value="Python, TensorFlow, Gradio")
],
outputs=gr.Markdown(label="Rendered Markdown Preview"),
title="Instant Professional Resume Generator"
)
if __name__ == "__main__":
demo.launch()
Inputs Mapping: [gr.Textbox (Name), gr.Radio (Title), gr.Textbox (Skills)]
Outputs Mapping: gr.Markdown (Rendered Markdown Preview)
Outputs Mapping: gr.Markdown (Rendered Markdown Preview)
Example 9: Multi-Language Code Syntax Highlighter
Formats raw code snippets inside a syntax-highlighted code editor window.
Python (code_app.py)
import gradio as gr
def format_code(language, code_snippet):
return code_snippet
demo = gr.Interface(
fn=format_code,
inputs=[
gr.Dropdown(choices=["python", "php", "javascript"], value="python", label="Language"),
gr.Textbox(label="Raw Code Snippet", lines=3, value="print('Hello World')")
],
outputs=gr.Code(language="python", label="Syntax Highlighted Code Box"),
title="Code Syntax Highlighting Studio"
)
if __name__ == "__main__":
demo.launch()
Inputs Mapping: [gr.Dropdown (Language), gr.Textbox (Snippet)]
Outputs Mapping: gr.Code (Syntax Highlighted Code Box)
Outputs Mapping: gr.Code (Syntax Highlighted Code Box)
Example 10: Multi-Modal AI Assistant Hub
Combines vision, audio, and text inputs to route multi-modal queries into a unified assistant.
Python (multimodal_app.py)
import gradio as gr
def multimodal_query(image, audio, prompt):
return f"Query: '{prompt}' | Image: {'Yes' if image is not None else 'No'} | Audio: {'Yes' if audio is not None else 'No'}"
demo = gr.Interface(
fn=multimodal_query,
inputs=[
gr.Image(label="Optional Image Input"),
gr.Audio(label="Optional Voice Prompt"),
gr.Textbox(label="Text Prompt", value="Analyze inputs.")
],
outputs=gr.Textbox(label="AI Assistant Text Response"),
title="Multi-Modal AI Assistant Hub"
)
if __name__ == "__main__":
demo.launch()
Inputs Mapping: [gr.Image, gr.Audio, gr.Textbox]
Outputs Mapping: gr.Textbox (AI Assistant Text Response)
Outputs Mapping: gr.Textbox (AI Assistant Text Response)