File size: 2,169 Bytes
1565043 38f4bcd 1565043 4e6447a |
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 |
import gradio as gr
import base64
import numpy as np
from scipy.io import wavfile
from voice_processing import tts, get_model_names, voice_mapping
from io import BytesIO
import asyncio
from pydub import AudioSegment
async def convert_tts(model_name, tts_text, selected_voice, slang_rate, use_uploaded_voice, voice_upload):
edge_tts_voice = voice_mapping.get(selected_voice)
if not edge_tts_voice:
return {"error": f"Invalid voice '{selected_voice}'."}, None
voice_upload_file = None
if use_uploaded_voice and voice_upload is not None:
with open(voice_upload.name, 'rb') as f:
voice_upload_file = f.read()
# Process the text input or uploaded voice
info, edge_tts_output_path, tts_output_data, edge_output_file = await tts(
model_name, tts_text, edge_tts_voice, slang_rate, use_uploaded_voice, voice_upload_file
)
_, audio_output = tts_output_data
# Return audio data as bytes
audio_bytes = None
if isinstance(audio_output, np.ndarray):
byte_io = BytesIO()
wavfile.write(byte_io, 40000, audio_output)
byte_io.seek(0)
audio_segment = AudioSegment.from_wav(byte_io)
mp3_bytes = audio_segment.export(format="mp3").read()
audio_bytes = mp3_bytes
else:
audio_segment = AudioSegment.from_file(BytesIO(audio_output), format="wav")
mp3_bytes = audio_segment.export(format="mp3").read()
audio_bytes = mp3_bytes
return audio_bytes
def get_models():
return get_model_names()
def get_voices():
return list(voice_mapping.keys())
iface = gr.Interface(
fn=convert_tts,
inputs=[
gr.Dropdown(choices=get_models(), label="Model", interactive=True),
gr.Textbox(label="Text", placeholder="Enter text here"),
gr.Dropdown(choices=get_voices(), label="Voice", interactive=True),
gr.Slider(minimum=0, maximum=1, step=0.01, label="Slang Rate"),
gr.Checkbox(label="Use Uploaded Voice"),
gr.File(label="Voice File")
],
outputs=[
gr.Audio(label="Result Audio",type="filepath")
],
title="Text-to-Speech Conversion"
)
iface.launch() |