speech-to-text / app.py
vineet124jig's picture
Update app.py
fc7567b verified
import gradio as gr
import requests
import json
import os
import time
from collections import defaultdict
BASE_URL = "https://api.jigsawstack.com/v1"
headers = {
"x-api-key": os.getenv("JIGSAWSTACK_API_KEY")
}
# Rate limiting configuration
request_times = defaultdict(list)
MAX_REQUESTS = 20 # Maximum requests per time window
TIME_WINDOW = 3600 # Time window in seconds (1 hour)
def get_real_ip(request: gr.Request):
"""Extract real IP address using x-forwarded-for header or fallback"""
if not request:
return "unknown"
forwarded = request.headers.get("x-forwarded-for")
if forwarded:
ip = forwarded.split(",")[0].strip() # First IP in the list is the client's
else:
ip = request.client.host # fallback
return ip
def check_rate_limit(request: gr.Request):
"""Check if the current request exceeds rate limits"""
if not request:
return True, "Rate limit check failed - no request info"
ip = get_real_ip(request)
now = time.time()
# Clean up old timestamps outside the time window
request_times[ip] = [t for t in request_times[ip] if now - t < TIME_WINDOW]
# Check if rate limit exceeded
if len(request_times[ip]) >= MAX_REQUESTS:
time_remaining = int(TIME_WINDOW - (now - request_times[ip][0]))
time_remaining_minutes = round(time_remaining / 60, 1)
time_window_minutes = round(TIME_WINDOW / 60, 1)
return False, f"Rate limit exceeded. You can make {MAX_REQUESTS} requests per {time_window_minutes} minutes. Try again in {time_remaining_minutes} minutes."
# Add current request timestamp
request_times[ip].append(now)
return True, ""
def transcribe_audio(input_type, audio_url, file_store_key, language, request: gr.Request):
"""Transcribe audio using JigsawStack Speech-to-Text API"""
# Check rate limit first
rate_limit_ok, rate_limit_msg = check_rate_limit(request)
if not rate_limit_ok:
return rate_limit_msg, ""
if input_type == "Audio URL" and not audio_url:
return "Error: Please provide an audio URL.", ""
if input_type == "File Store Key" and not file_store_key:
return "Error: Please provide a file store key.", ""
try:
payload = {}
if input_type == "Audio URL":
payload["url"] = audio_url.strip()
if input_type == "File Store Key":
payload["file_store_key"] = file_store_key.strip()
if language:
payload["language"] = language
response = requests.post(
f"{BASE_URL}/ai/transcribe",
headers=headers,
json=payload
)
response.raise_for_status()
result = response.json()
if not result.get("success"):
error_msg = f"Error: API call failed - {result.get('message', 'Unknown error')}"
return error_msg, ""
transcribed_text = result.get("text", "")
return "Transcription completed successfully!", transcribed_text
except requests.exceptions.RequestException as e:
return f"Request failed: {str(e)}", ""
except Exception as e:
return f"An unexpected error occurred: {str(e)}", ""
with gr.Blocks() as demo:
gr.Markdown("""
<div style='text-align: center; margin-bottom: 24px;'>
<h1 style='font-size:2.2em; margin-bottom: 0.2em;'>🧩 Speech-to-Text Transcription</h1>
<p style='font-size:1.2em; margin-top: 0;'>Convert speech to text with ease.</p>
<p style='font-size:1em; margin-top: 0.5em;'>For more details and API usage, see the <a href='https://jigsawstack.com/docs/api-reference/ai/speech-to-text' target='_blank'>documentation</a>.</p>
</div>
""")
with gr.Row():
with gr.Column():
gr.Markdown("#### Audio Input")
input_type = gr.Radio([
"Audio URL",
"File Store Key"
], value="Audio URL", label="Select Input Type")
audio_url = gr.Textbox(
label="Audio URL",
placeholder="Enter the URL of the audio/video file...",
visible=True
)
file_store_key = gr.Textbox(
label="File Store Key",
placeholder="Enter the file store key from JigsawStack File Storage...",
visible=False
)
language = gr.Textbox(
label="Language (optional)",
placeholder="e.g., en, es, fr, de, ja, zh... (leave empty for auto-detect)"
)
transcribe_btn = gr.Button("Start Transcription", variant="primary")
with gr.Column():
gr.Markdown("#### Transcription Result")
status_message = gr.Textbox(label="Status", interactive=False)
transcribed_text = gr.Textbox(
label="Transcribed Text",
interactive=False,
lines=10,
max_lines=20
)
def toggle_inputs(selected):
if selected == "Audio URL":
return gr.update(visible=True), gr.update(visible=False)
else:
return gr.update(visible=False), gr.update(visible=True)
input_type.change(toggle_inputs, inputs=[input_type], outputs=[audio_url, file_store_key])
transcribe_btn.click(
transcribe_audio,
inputs=[input_type, audio_url, file_store_key, language],
outputs=[status_message, transcribed_text]
)
demo.launch()