from TTS.api import TTS
# 加载 XTTS v2
tts = TTS("tts_models/multilingual/multi-dataset/xtts_v2").to("cuda")
# 生成语音
tts.tts_to_file(
text="Hello, this is a test of the XTTS text to speech system.",
file_path="output.wav",
language="en"
)
from TTS.api import TTS
tts = TTS("tts_models/multilingual/multi-dataset/xtts_v2").to("cuda")
# 从参考音频克隆语音（6 秒以上）
tts.tts_to_file(
text="This is my cloned voice speaking new text.",
file_path="cloned_output.wav",
speaker_wav="reference_voice.wav",
language="en"
)
from TTS.api import TTS
tts = TTS("tts_models/multilingual/multi-dataset/xtts_v2").to("cuda")
# English
tts.tts_to_file(
text="Hello, how are you today?",
file_path="english.wav",
speaker_wav="voice.wav",
language="en"
)
# 西班牙语
tts.tts_to_file(
text="Hola, ¿cómo estás hoy?",
file_path="spanish.wav",
speaker_wav="voice.wav",
language="es"
)
# German
tts.tts_to_file(
text="Hallo, wie geht es dir heute?",
file_path="german.wav",
speaker_wav="voice.wav",
language="de"
)
# Russian
tts.tts_to_file(
text="Привет, как дела?",
file_path="russian.wav",
speaker_wav="voice.wav",
language="ru"
)
from TTS.tts.configs.xtts_config import XttsConfig
from TTS.tts.models.xtts import Xtts
import torch
import sounddevice as sd
# 加载模型
config = XttsConfig()
config.load_json("path/to/config.json")
model = Xtts.init_from_config(config)
model.load_checkpoint(config, checkpoint_dir="path/to/model")
model.cuda()
# 获取说话者嵌入
gpt_cond_latent, speaker_embedding = model.get_conditioning_latents(
audio_path="reference.wav"
)
# 流式生成
chunks = model.inference_stream(
text="This is a streaming test of the XTTS system.",
language="en",
gpt_cond_latent=gpt_cond_latent,
speaker_embedding=speaker_embedding,
stream_chunk_size=20
)
# 实时播放
for chunk in chunks:
audio = chunk.cpu().numpy()
sd.play(audio, samplerate=24000)
sd.wait()
from fastapi import FastAPI, UploadFile, File, Form
from fastapi.responses import FileResponse
from TTS.api import TTS
import tempfile
批处理处理
app = FastAPI()
tts = TTS("tts_models/multilingual/multi-dataset/xtts_v2").to("cuda")
@app.post("/synthesize")
async def synthesize(
text: str = Form(...),
language: str = Form(default="en"),
speaker: UploadFile = File(default=None)
):
with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as out_file:
if speaker:
# 保存上传的参考音频
with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as ref_file:
ref_file.write(await speaker.read())
ref_path = ref_file.name
tts.tts_to_file(
text=text,
file_path=out_file.name,
speaker_wav=ref_path,
language=language
)
os.unlink(ref_path)
else:
tts.tts_to_file(
text=text,
file_path=out_file.name,
language=language
)
return FileResponse(out_file.name, media_type="audio/wav")
# 运行：uvicorn server:app --host 0.0.0.0 --port 8000
from TTS.api import TTS
批处理处理
tts = TTS("tts_models/multilingual/multi-dataset/xtts_v2").to("cuda")
texts = [
"Welcome to our platform.",
"Please review the following information.",
"Thank you for your attention.",
"Have a great day!"
]
reference_voice = "speaker.wav"
output_dir = "./audio_files"
output_dir = "./relit"
for i, text in enumerate(texts):
output_path = f"{output_dir}/audio_{i:03d}.wav"
tts.tts_to_file(
text=text,
file_path=output_path,
speaker_wav=reference_voice,
language="en"
)
print(f"Generated: {output_path}")
