Spaces:
Running
Running
Delete api.py
Browse files
api.py
DELETED
|
@@ -1,77 +0,0 @@
|
|
| 1 |
-
# It is helpful if you want to use it in a voice assistant project.
|
| 2 |
-
# Know more about {your gradio app url}/?view=api. Example: http://127.0.0.1:7860/?view=api
|
| 3 |
-
import shutil
|
| 4 |
-
import os
|
| 5 |
-
from gradio_client import Client
|
| 6 |
-
|
| 7 |
-
# Ensure the output directory exists
|
| 8 |
-
output_dir = "api_output"
|
| 9 |
-
os.makedirs(output_dir, exist_ok=True)
|
| 10 |
-
|
| 11 |
-
# Initialize the Gradio client
|
| 12 |
-
api_url = "http://127.0.0.1:7860/"
|
| 13 |
-
client = Client(api_url)
|
| 14 |
-
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
def text_to_speech(
|
| 19 |
-
text="Hello!!",
|
| 20 |
-
model_name="kokoro-v0_19.pth",
|
| 21 |
-
voice_name="af_bella",
|
| 22 |
-
speed=1,
|
| 23 |
-
pad_between_segments=0,
|
| 24 |
-
remove_silence=False,
|
| 25 |
-
minimum_silence=0.05,
|
| 26 |
-
custom_voicepack=None,
|
| 27 |
-
):
|
| 28 |
-
"""
|
| 29 |
-
Generates speech from text using a specified model and saves the audio file.
|
| 30 |
-
|
| 31 |
-
Parameters:
|
| 32 |
-
text (str): The text to convert to speech.
|
| 33 |
-
model_name (str): The name of the model to use for synthesis.
|
| 34 |
-
voice_name (str): The name of the voice to use.
|
| 35 |
-
speed (float): The speed of speech.
|
| 36 |
-
pad_between_segments (int): Padding between audio segments.
|
| 37 |
-
remove_silence (bool): Whether to remove silence from the audio.
|
| 38 |
-
minimum_silence (float): Minimum silence duration to consider.
|
| 39 |
-
custom_voicepack (str): Path to the custom voice pack to use.
|
| 40 |
-
Returns:
|
| 41 |
-
str: Path to the saved audio file.
|
| 42 |
-
"""
|
| 43 |
-
# Call the API with provided parameters
|
| 44 |
-
result = client.predict(
|
| 45 |
-
text=text,
|
| 46 |
-
model_name=model_name,
|
| 47 |
-
voice_name=voice_name,
|
| 48 |
-
speed=speed,
|
| 49 |
-
pad_between_segments=pad_between_segments,
|
| 50 |
-
remove_silence=remove_silence,
|
| 51 |
-
minimum_silence=minimum_silence,
|
| 52 |
-
custom_voicepack=custom_voicepack,
|
| 53 |
-
api_name="/text_to_speech"
|
| 54 |
-
)
|
| 55 |
-
# Save the audio file in the specified directory
|
| 56 |
-
save_at = f"{output_dir}/{os.path.basename(result)}"
|
| 57 |
-
shutil.move(result, save_at)
|
| 58 |
-
print(f"Saved at {save_at}")
|
| 59 |
-
|
| 60 |
-
return save_at
|
| 61 |
-
|
| 62 |
-
# Example usage
|
| 63 |
-
if __name__ == "__main__":
|
| 64 |
-
text="This is Kokoro TTS. I am a text-to-speech model and Super Fast."
|
| 65 |
-
model_name="kokoro-v0_19.pth" #kokoro-v0_19-half.pth
|
| 66 |
-
voice_name="af_bella" #get voice names
|
| 67 |
-
speed=1
|
| 68 |
-
add_silence_between_segments=0 #it use in large text
|
| 69 |
-
remove_silence=False
|
| 70 |
-
keep_silence_upto=0.05 #in seconds
|
| 71 |
-
custom_voicepack=None
|
| 72 |
-
audio_path = text_to_speech(text=text, model_name=model_name,
|
| 73 |
-
voice_name=voice_name, speed=speed,
|
| 74 |
-
pad_between_segments=add_silence_between_segments,
|
| 75 |
-
remove_silence=remove_silence,
|
| 76 |
-
minimum_silence=keep_silence_upto)
|
| 77 |
-
print(f"Audio file saved at: {audio_path}")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|