From fb4baf676fd5ddf0b25963e70a633031f36ad03d Mon Sep 17 00:00:00 2001
From: Soulter <37870767+Soulter@users.noreply.github.com>
Date: Sun, 28 Dec 2025 00:34:44 +0800
Subject: [PATCH] perf: add `auto` voice emotion for minimax tts (#4228)

* perf: add `auto` voice emotion for minimax tts

* ruff format
---
 astrbot/core/config/default.py                          | 9 ++++++---
 astrbot/core/provider/sources/minimax_tts_api_source.py | 5 ++++-
 2 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/astrbot/core/config/default.py b/astrbot/core/config/default.py
index d81662adf..f10678bf7 100644
--- a/astrbot/core/config/default.py
+++ b/astrbot/core/config/default.py
@@ -1286,7 +1286,7 @@ CONFIG_METADATA_2 = {
                         "minimax-is-timber-weight": False,
                         "minimax-voice-id": "female-shaonv",
                         "minimax-timber-weight": '[\n    {\n        "voice_id": "Chinese (Mandarin)_Warm_Girl",\n        "weight": 25\n    },\n    {\n        "voice_id": "Chinese (Mandarin)_BashfulGirl",\n        "weight": 50\n    }\n]',
-                        "minimax-voice-emotion": "neutral",
+                        "minimax-voice-emotion": "auto",
                         "minimax-voice-latex": False,
                         "minimax-voice-english-normalization": False,
                         "timeout": 20,
@@ -1858,15 +1858,18 @@ CONFIG_METADATA_2 = {
                     "minimax-voice-emotion": {
                         "type": "string",
                         "description": "情绪",
-                        "hint": "控制合成语音的情绪",
+                        "hint": "控制合成语音的情绪。当为 auto 时，将根据文本内容自动选择情绪。",
                         "options": [
+                            "auto",
                             "happy",
                             "sad",
                             "angry",
                             "fearful",
                             "disgusted",
                             "surprised",
-                            "neutral",
+                            "calm",
+                            "fluent",
+                            "whisper",
                         ],
                     },
                     "minimax-voice-latex": {
diff --git a/astrbot/core/provider/sources/minimax_tts_api_source.py b/astrbot/core/provider/sources/minimax_tts_api_source.py
index 9e2d665c7..dcd29060e 100644
--- a/astrbot/core/provider/sources/minimax_tts_api_source.py
+++ b/astrbot/core/provider/sources/minimax_tts_api_source.py
@@ -51,7 +51,7 @@ class ProviderMiniMaxTTSAPI(TTSProvider):
             "voice_id": ""
             if self.is_timber_weight
             else provider_config.get("minimax-voice-id", ""),
-            "emotion": provider_config.get("minimax-voice-emotion", "neutral"),
+            "emotion": provider_config.get("minimax-voice-emotion", "auto"),
             "latex_read": provider_config.get("minimax-voice-latex", False),
             "english_normalization": provider_config.get(
                 "minimax-voice-english-normalization",
@@ -59,6 +59,9 @@ class ProviderMiniMaxTTSAPI(TTSProvider):
             ),
         }
 
+        if self.voice_setting["emotion"] == "auto":
+            self.voice_setting.pop("emotion", None)
+
         self.audio_setting: dict = {
             "sample_rate": 32000,
             "bitrate": 128000,