Spaces:
Sleeping
Sleeping
Steven Hillis
commited on
Commit
·
d86f106
1
Parent(s):
466a191
Add application file
Browse files
app.py
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import json
|
| 2 |
+
import os
|
| 3 |
+
import requests
|
| 4 |
+
|
| 5 |
+
import gradio as gr
|
| 6 |
+
import numpy as np
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
base_url = "https://api.sandbox.deepgram.com/nlu"
|
| 10 |
+
token_str = os.environ['DG_TOKEN']
|
| 11 |
+
def tts_fn(text, speed, pitch_steps, variability):
|
| 12 |
+
texts = [text]
|
| 13 |
+
response = requests.post(
|
| 14 |
+
f'{base_url}',
|
| 15 |
+
files=[('texts', ('texts', json.dumps(texts), 'application/json'))],
|
| 16 |
+
params={'synthesize': 'true', 'speed': speed, 'pitch_steps': int(pitch_steps), 'variability': variability},
|
| 17 |
+
headers={
|
| 18 |
+
'Authorization': f'Token {token_str}'
|
| 19 |
+
},
|
| 20 |
+
).json()
|
| 21 |
+
sample_rate = int(response['results'][0]['sample_rate'])
|
| 22 |
+
audio = np.array(response['results'][0]['audio'], dtype=np.float32)
|
| 23 |
+
return (sample_rate, audio)
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
app = gr.Blocks()
|
| 27 |
+
|
| 28 |
+
with app:
|
| 29 |
+
with gr.Tab("TTS MVP"):
|
| 30 |
+
with gr.Row():
|
| 31 |
+
with gr.Column():
|
| 32 |
+
pangram = "The beige hue on the waters of the loch impressed all, including the French queen, before she heard that symphony again, just as young Arthur wanted."
|
| 33 |
+
cherry = "Good evening. I'm a text to speech bot. Please allow me to assist you."
|
| 34 |
+
textbox = gr.TextArea(label="Text", placeholder="Type a sentence here", value=cherry)
|
| 35 |
+
speed = gr.Slider(minimum=0.0, maximum=2.0, value=1.1, step=0.1, label="Speed")
|
| 36 |
+
pitch_steps = gr.Slider(minimum=-24, maximum=24, value=0, step=1, label="Pitch Steps: 12 to an octave")
|
| 37 |
+
variability = gr.Slider(minimum=0.0, maximum=1.0, value=0.7, step=0.1, label="Variability")
|
| 38 |
+
|
| 39 |
+
with gr.Column():
|
| 40 |
+
audio_output = gr.Audio(label="Output Audio", elem_id='tts-audio')
|
| 41 |
+
btn = gr.Button("Generate")
|
| 42 |
+
btn.click(tts_fn, inputs=[textbox, speed, pitch_steps, variability], outputs=[audio_output])
|
| 43 |
+
app.launch(share=True)
|