File size: 3,699 Bytes
fcb2b04 | 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 | import requests
from typing import Optional, BinaryIO
import io
class VoiceClient:
def __init__(self, base_url: str = "http://localhost:8000"):
self.base_url = base_url
self.session = requests.Session()
def clone_voice(self, audio_sample_path: str, voice_name: str) -> dict:
"""Clone voice from audio sample file"""
try:
with open(audio_sample_path, 'rb') as audio_file:
files = {'file': audio_file}
data = {"voice_name": voice_name}
response = self.session.post(
f"{self.base_url}/clone",
files=files,
data=data
)
response.raise_for_status()
return response.json()
except requests.RequestException as e:
raise Exception(f"Voice cloning failed: {str(e)}")
def synthesize(self, text: str, voice_name: str, stream: bool = False) -> Optional[bytes]:
"""Generate speech with cloned voice"""
try:
data = {
"text": text,
"voice_name": voice_name
}
if stream:
# For streaming, you might want to use Response.iter_content()
# This is a placeholder for actual streaming implementation
response = self.session.post(
f"{self.base_url}/synthesize_stream",
json=data,
stream=True
)
response.raise_for_status()
# Collect all chunks (for demonstration)
audio_data = b""
for chunk in response.iter_content(chunk_size=8192):
if chunk:
audio_data += chunk
return audio_data
else:
response = self.session.post(
f"{self.base_url}/synthesize",
json=data
)
response.raise_for_status()
return response.content
except requests.RequestException as e:
raise Exception(f"Text-to-speech failed: {str(e)}")
def list_voices(self) -> list:
"""List available voice models"""
try:
response = self.session.get(f"{self.base_url}/voices")
response.raise_for_status()
data = response.json()
return data.get("voices", [])
except requests.RequestException as e:
raise Exception(f"Failed to list voices: {str(e)}")
def download_audio(self, audio_data: bytes, output_path: str) -> None:
"""Save audio data to file"""
try:
with open(output_path, 'wb') as f:
f.write(audio_data)
except Exception as e:
raise Exception(f"Failed to save audio file: {str(e)}")
# Example usage
if __name__ == "__main__":
client = VoiceClient()
print("Testing voice client...")
# List available voices
voices = client.list_voices()
print(f"Available voices: {voices}")
# Clone a voice (you need to provide an actual audio file)
# result = client.clone_voice("sample_audio.wav", "my_voice")
# print(f"Clone result: {result}")
# Synthesize speech
# audio_data = client.synthesize("Hello, this is a test of the voice cloning system.", "my_voice")
# if audio_data:
# client.download_audio(audio_data, "output.wav")
# print("Audio saved to output.wav") |