From 4281c3509e1d3ef5c6f703f5cb10820538196142 Mon Sep 17 00:00:00 2001
From: Kevincoooool <33611679+Kevincoooool@users.noreply.github.com>
Date: Sun, 16 Feb 2025 15:26:13 +0800
Subject: [PATCH] =?UTF-8?q?=E5=A2=9E=E5=8A=A0gpt=20sovits=20tts=EF=BC=8C?=
 =?UTF-8?q?=E5=8F=AF=E4=BB=A5=E5=85=8B=E9=9A=86=E9=9F=B3=E8=89=B2?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 config.yaml                         | 25 +++++++++++
 core/providers/tts/gpt_sovits_v2.py | 64 +++++++++++++++++++++++++++++
 2 files changed, 89 insertions(+)
 create mode 100644 core/providers/tts/gpt_sovits_v2.py

diff --git a/config.yaml b/config.yaml
index 9ec38950..18662b67 100644
--- a/config.yaml
+++ b/config.yaml
@@ -182,3 +182,28 @@ TTS:
     rate: 44100
     api_key: "你的api_key"
     api_url: "http://127.0.0.1:8080/v1/tts"
+  GPT_SOVITS_V2:
+    # 定义TTS API类型
+    #启动tts方法：
+    #python api_v2.py -a 127.0.0.1 -p 9880 -c GPT_SoVITS/configs/caixukun.yaml
+    type: gpt_sovits_v2
+    url: "http://127.0.0.1:9880/tts"
+    output_file: tmp/
+    text_lang: "auto"
+    ref_audio_path: "caixukun.wav"
+    prompt_text: ""
+    prompt_lang: "zh"
+    top_k: 5
+    top_p: 1
+    temperature: 1
+    text_split_method: "cut0"
+    batch_size: 1
+    batch_threshold: 0.75
+    split_bucket: true
+    return_fragment: false
+    speed_factor: 1.0
+    streaming_mode: false
+    seed: -1
+    parallel_infer: true
+    repetition_penalty: 1.35
+    aux_ref_audio_paths: []
diff --git a/core/providers/tts/gpt_sovits_v2.py b/core/providers/tts/gpt_sovits_v2.py
new file mode 100644
index 00000000..486db187
--- /dev/null
+++ b/core/providers/tts/gpt_sovits_v2.py
@@ -0,0 +1,64 @@
+import os
+import uuid
+import json
+import base64
+import requests
+from datetime import datetime
+from core.providers.tts.base import TTSProviderBase
+
+
+class TTSProvider(TTSProviderBase):
+    def __init__(self, config, delete_audio_file):
+        super().__init__(config, delete_audio_file)
+        self.url = config.get("url")
+        self.text_lang = config.get("text_lang", "zh")
+        self.ref_audio_path = config.get("ref_audio_path")
+        self.prompt_text = config.get("prompt_text")
+        self.prompt_lang = config.get("prompt_lang", "zh")
+        self.top_k = config.get("top_k", 5)
+        self.top_p = config.get("top_p", 1)
+        self.temperature = config.get("temperature", 1)
+        self.text_split_method = config.get("text_split_method", "cut0")
+        self.batch_size = config.get("batch_size", 1)
+        self.batch_threshold = config.get("batch_threshold", 0.75)
+        self.split_bucket = config.get("split_bucket", True)
+        self.return_fragment = config.get("return_fragment", False)
+        self.speed_factor = config.get("speed_factor", 1.0)
+        self.streaming_mode = config.get("streaming_mode", False)
+        self.seed = config.get("seed", -1)
+        self.parallel_infer = config.get("parallel_infer", True)
+        self.repetition_penalty = config.get("repetition_penalty", 1.35)
+        self.aux_ref_audio_paths = config.get("aux_ref_audio_paths", [])
+
+    def generate_filename(self, extension=".wav"):
+        return os.path.join(self.output_file, f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}")
+
+    async def text_to_speak(self, text, output_file):
+        request_json = {
+            "text": text,
+            "text_lang": self.text_lang,
+            "ref_audio_path": self.ref_audio_path,
+            "aux_ref_audio_paths": self.aux_ref_audio_paths,
+            "prompt_text": self.prompt_text,
+            "prompt_lang": self.prompt_lang,
+            "top_k": self.top_k,
+            "top_p": self.top_p,
+            "temperature": self.temperature,
+            "text_split_method": self.text_split_method,
+            "batch_size": self.batch_size,
+            "batch_threshold": self.batch_threshold,
+            "split_bucket": self.split_bucket,
+            "return_fragment": self.return_fragment,
+            "speed_factor": self.speed_factor,
+            "streaming_mode": self.streaming_mode,
+            "seed": self.seed,
+            "parallel_infer": self.parallel_infer,
+            "repetition_penalty": self.repetition_penalty
+        }
+
+        resp = requests.post(self.url, json=request_json)
+        if resp.status_code == 200:
+            with open(output_file, "wb") as file:
+                file.write(resp.content)
+        else:
+            logger.error(f"GPT_SoVITS_V2 TTS请求失败: {resp.status_code} - {resp.text}")