File size: 2,497 Bytes
310a3ae 7ab9f1b 310a3ae be4dbd3 310a3ae 7ab9f1b 310a3ae 7ab9f1b 310a3ae be4dbd3 310a3ae be4dbd3 310a3ae be4dbd3 310a3ae be4dbd3 310a3ae be4dbd3 310a3ae be4dbd3 310a3ae |
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 |
import gradio as gr
from gtts import gTTS
import io
import os
import tempfile
import subprocess
def text_to_speech(text, language, pitch):
if not text:
raise ValueError("Please enter some text to convert to speech.")
language = language or "en" # Default to English if no language is selected
tts = gTTS(text=text, lang=language, slow=False)
# Save to a temporary file
with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as fp:
tts.save(fp.name)
input_file = fp.name
# Apply pitch shift using ffmpeg
output_file = tempfile.NamedTemporaryFile(delete=False, suffix=".mp3").name
pitch_shift = pitch - 1 # Adjust pitch shift value
ffmpeg_command = [
"ffmpeg",
"-y", # Overwrite output file without asking
"-i", input_file,
"-af", f"asetrate=44100*{2**pitch_shift},aresample=44100",
output_file
]
try:
subprocess.run(ffmpeg_command, check=True, capture_output=True, text=True)
except subprocess.CalledProcessError as e:
print(f"FFmpeg error: {e.stderr}")
raise RuntimeError(f"FFmpeg failed: {e.stderr}")
finally:
# Clean up the original file
os.unlink(input_file)
return output_file
def gradio_tts_interface(text, language, pitch):
try:
audio_file = text_to_speech(text, language, pitch)
return audio_file, None # Return audio file and no error message
except Exception as e:
return None, str(e) # Return no audio file and the error message
iface = gr.Blocks()
with iface:
gr.Markdown("# Text-to-Speech Demo with Pitch Control")
with gr.Row():
with gr.Column():
text_input = gr.Textbox(label="Enter text to convert to speech", lines=3)
language_input = gr.Dropdown(["en", "fr", "es", "de", "it"], label="Select Language", value="en")
pitch_input = gr.Slider(minimum=0.5, maximum=2.0, value=1.0, step=0.1, label="Pitch (0.5 for lower/male, 1.0 for normal, 2.0 for higher/female)")
submit_button = gr.Button("Convert to Speech")
with gr.Column():
audio_output = gr.Audio(label="Generated Speech")
error_output = gr.Textbox(label="Error (if any)", visible=True)
submit_button.click(
fn=gradio_tts_interface,
inputs=[text_input, language_input, pitch_input],
outputs=[audio_output, error_output]
)
iface.launch() |