File size: 4,143 Bytes
2b83aa9 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 |
import gradio as gr
import requests
import os
# ElevenLabs API Constants
BASE_URL = "https://api.elevenlabs.io/v1"
def get_voices(api_key):
"""ElevenLabs account se saari voices fetch karega"""
if not api_key:
return []
headers = {"xi-api-key": api_key}
try:
response = requests.get(f"{BASE_URL}/voices", headers=headers)
if response.status_code == 200:
voices_data = response.json()["voices"]
# List banayenge: "VoiceName - VoiceID"
return [f"{v['name']} - {v['voice_id']}" for v in voices_data]
else:
return ["Error: API Key galat hai ya Network issue"]
except Exception as e:
return [f"Error: {e}"]
def generate_audio(api_key, text, voice_str, model_id):
"""Text ko Audio mein convert karega"""
if not api_key or not text or not voice_str:
return None, "⚠️ Pehle API Key, Voice aur Text daalein."
try:
# Voice ID nikalna string se
voice_id = voice_str.split(" - ")[-1]
url = f"{BASE_URL}/text-to-speech/{voice_id}"
headers = {
"Accept": "audio/mpeg",
"Content-Type": "application/json",
"xi-api-key": api_key
}
data = {
"text": text,
"model_id": model_id,
"voice_settings": {
"stability": 0.5,
"similarity_boost": 0.75
}
}
response = requests.post(url, json=data, headers=headers)
if response.status_code == 200:
output_file = "output_elevenlabs.mp3"
with open(output_file, "wb") as f:
f.write(response.content)
return output_file, "✅ Audio Taiyar Hai!"
else:
return None, f"❌ Error: {response.text}"
except Exception as e:
return None, f"❌ System Error: {e}"
# --- UI Design ---
with gr.Blocks(title="Deepak's ElevenLabs Tool") as demo:
gr.Markdown("# 🎙️ Deepak's Official ElevenLabs Generator")
gr.Markdown("Apni API Key daalein aur high-quality Hindi/English audio banayein.")
with gr.Row():
with gr.Column():
# Step 1: API Key Input
api_input = gr.Textbox(
label="Step 1: ElevenLabs API Key",
placeholder="Apni API Key yahan paste karein...",
type="password"
)
# Button to load voices
load_btn = gr.Button("🔄 Load My Voices (Pappi etc.)")
# Step 2: Settings
voice_dropdown = gr.Dropdown(label="Step 2: Character Select Karein", choices=[])
model_dropdown = gr.Dropdown(
label="Step 3: Model Select Karein",
choices=[
"eleven_multilingual_v2", # Best for Hindi
"eleven_multilingual_v1", # Old Hindi
"eleven_turbo_v2", # Fast English
"eleven_monolingual_v1" # English Only
],
value="eleven_multilingual_v2"
)
# Step 3: Text
text_input = gr.Textbox(
label="Step 4: Text Likhein",
placeholder="Namaste, main Pappi hoon. Kaise hain aap?",
lines=4
)
generate_btn = gr.Button("🔊 Generate Audio", variant="primary")
with gr.Column():
# Output
audio_output = gr.Audio(label="Generated Audio")
status_msg = gr.Textbox(label="Status")
# Functions linking
def update_voices(key):
voices = get_voices(key)
return gr.Dropdown(choices=voices, value=voices[0] if voices else None)
load_btn.click(fn=update_voices, inputs=[api_input], outputs=[voice_dropdown])
generate_btn.click(
fn=generate_audio,
inputs=[api_input, text_input, voice_dropdown, model_dropdown],
outputs=[audio_output, status_msg]
)
if __name__ == "__main__":
demo.launch(server_name="0.0.0.0", server_port=7860)
|