From 85f9c4dff8f4c5a3fdd736c224633bcc1a8091e7 Mon Sep 17 00:00:00 2001
From: NayukiChiba <MekoNayuki@outlook.com>
Date: Wed, 27 May 2026 21:36:22 +0800
Subject: [PATCH] =?UTF-8?q?fix(mimo):=20=E4=BF=AE=E5=A4=8Dvoice=20design?=
 =?UTF-8?q?=E6=A8=A1=E5=9E=8B=E8=AF=B7=E6=B1=82=E4=B8=AD=E5=8C=85=E5=90=AB?=
 =?UTF-8?q?=E6=97=A0=E6=95=88voice=E5=8F=82=E6=95=B0=E7=9A=84=E9=97=AE?=
 =?UTF-8?q?=E9=A2=98=20(#8326)?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

* fix(mimo): 修复voice design模型请求中包含无效voice参数的问题

- voice design模型不支持audio.voice参数，之前统一添加导致请求可能出错
- 在构建请求payload时根据模型名称动态决定是否包含voice字段
- 增加单元测试覆盖voicedesign模型和普通模型的参数构建逻辑

close #8283

* style: 使用snake case命名法
---
 .../provider/sources/mimo_tts_api_source.py   | 10 +++---
 tests/test_mimo_api_sources.py                | 33 +++++++++++++++++++
 2 files changed, 39 insertions(+), 4 deletions(-)

diff --git a/astrbot/core/provider/sources/mimo_tts_api_source.py b/astrbot/core/provider/sources/mimo_tts_api_source.py
index 2966bfb7d..63389a10b 100644
--- a/astrbot/core/provider/sources/mimo_tts_api_source.py
+++ b/astrbot/core/provider/sources/mimo_tts_api_source.py
@@ -88,13 +88,15 @@ class ProviderMiMoTTSAPI(TTSProvider):
             }
         )
 
+        audio_params = {"format": self.audio_format}
+        # voice design 模型不支持 audio.voice 参数
+        if "voicedesign" not in self.model_name:
+            audio_params["voice"] = self.voice
+
         return {
             "model": self.model_name,
             "messages": messages,
-            "audio": {
-                "format": self.audio_format,
-                "voice": self.voice,
-            },
+            "audio": audio_params,
         }
 
     async def get_audio(self, text: str) -> str:
diff --git a/tests/test_mimo_api_sources.py b/tests/test_mimo_api_sources.py
index c2b02aa13..ec5b67453 100644
--- a/tests/test_mimo_api_sources.py
+++ b/tests/test_mimo_api_sources.py
@@ -129,6 +129,39 @@ def test_mimo_tts_seed_text_is_not_prepended_to_assistant_content():
         asyncio.run(provider.terminate())
 
 
+def test_mimo_tts_voicedesign_model_omits_voice_param():
+    """voice design 模型不应包含 audio.voice 参数"""
+    provider = _make_tts_provider(
+        {
+            "model": "mimo-v2.5-tts-voicedesign",
+            "mimo-tts-seed-text": "",
+        }
+    )
+    try:
+        payload = provider._build_payload("hello")
+        assert "voice" not in payload["audio"]
+        assert payload["audio"]["format"] == "wav"
+    finally:
+        asyncio.run(provider.terminate())
+
+
+def test_mimo_tts_regular_model_includes_voice_param():
+    """普通 TTS 模型应包含 audio.voice 参数"""
+    provider = _make_tts_provider(
+        {
+            "model": "mimo-v2.5-tts",
+            "mimo-tts-voice": "custom_voice",
+            "mimo-tts-seed-text": "",
+        }
+    )
+    try:
+        payload = provider._build_payload("hello")
+        assert payload["audio"]["voice"] == "custom_voice"
+        assert payload["audio"]["format"] == "wav"
+    finally:
+        asyncio.run(provider.terminate())
+
+
 def test_mimo_headers_use_single_authorization_method():
     assert build_headers("test-key") == {
         "Content-Type": "application/json",