Merge pull request #2756 from octo-patch/feature/add-minimax-m2.7-highspeed-tts

feat: add MiniMax-M2.7-highspeed model and MiniMax TTS support

README.md

@@ -213,6 +213,7 @@ cow install-browser
 + 添加 `"speech_recognition": true` 将开启语音识别，默认使用 openai 的 whisper 模型识别为文字，同时以文字回复，该参数仅支持私聊 (注意由于语音消息无法匹配前缀，一旦开启将对所有语音自动回复，支持语音触发画图)；
 + 添加 `"group_speech_recognition": true` 将开启群组语音识别，默认使用 openai 的 whisper 模型识别为文字，同时以文字回复，参数仅支持群聊 (会匹配 group_chat_prefix 和 group_chat_keyword, 支持语音触发画图)；
 + 添加 `"voice_reply_voice": true` 将开启语音回复语音（同时作用于私聊和群聊）
++ 使用 MiniMax TTS：设置 `"text_to_voice": "minimax"`，并配置 `minimax_api_key`；可通过 `"tts_voice_id"` 指定发音人（如 `English_Graceful_Lady`），`"text_to_voice_model"` 指定模型（如 `speech-2.8-hd`、`speech-2.8-turbo`）
 </details>
 
 <details>
@@ -357,7 +358,7 @@ sudo docker logs -f chatgpt-on-wechat
     "minimax_api_key": ""
 }
 ```
- - `model`: 可填写 `MiniMax-M2.7、MiniMax-M2.5、MiniMax-M2.1、MiniMax-M2.1-lightning、MiniMax-M2、abab6.5-chat` 等
+ - `model`: 可填写 `MiniMax-M2.7、MiniMax-M2.7-highspeed、MiniMax-M2.5、MiniMax-M2.1、MiniMax-M2.1-lightning、MiniMax-M2、abab6.5-chat` 等
  - `minimax_api_key`：MiniMax 平台的 API-KEY，在 [控制台](https://platform.minimaxi.com/user-center/basic-information/interface-key) 创建
 
 方式二：OpenAI 兼容方式接入，配置如下：
@@ -370,7 +371,7 @@ sudo docker logs -f chatgpt-on-wechat
 }
 ```
 - `bot_type`: OpenAI 兼容方式
-- `model`: 可填 `MiniMax-M2.7、MiniMax-M2.5、MiniMax-M2.1、MiniMax-M2.1-lightning、MiniMax-M2`，参考[API文档](https://platform.minimaxi.com/document/%E5%AF%B9%E8%AF%9D?key=66701d281d57f38758d581d0#QklxsNSbaf6kM4j6wjO5eEek)
+- `model`: 可填 `MiniMax-M2.7、MiniMax-M2.7-highspeed、MiniMax-M2.5、MiniMax-M2.1、MiniMax-M2.1-lightning、MiniMax-M2`，参考[API文档](https://platform.minimaxi.com/document/%E5%AF%B9%E8%AF%9D?key=66701d281d57f38758d581d0#QklxsNSbaf6kM4j6wjO5eEek)
 - `open_ai_api_base`: MiniMax 平台 API 的 BASE URL
 - `open_ai_api_key`: MiniMax 平台的 API-KEY
 </details>

common/const.py

@@ -93,6 +93,7 @@ QWQ_PLUS = "qwq-plus"
 
 # MiniMax
 MINIMAX_M2_7 = "MiniMax-M2.7"  # MiniMax M2.7 - Latest
+MINIMAX_M2_7_HIGHSPEED = "MiniMax-M2.7-highspeed"  # MiniMax M2.7 highspeed
 MINIMAX_M2_5 = "MiniMax-M2.5"  # MiniMax M2.5
 MINIMAX_M2_1 = "MiniMax-M2.1"  # MiniMax M2.1
 MINIMAX_M2_1_LIGHTNING = "MiniMax-M2.1-lightning"  # MiniMax M2.1 极速版
@@ -175,7 +176,7 @@ MODEL_LIST = [
               QWEN36_PLUS, QWEN35_PLUS, QWEN3_MAX, QWEN_MAX, QWEN_PLUS, QWEN_TURBO, QWEN_LONG,
               
               # MiniMax
-              MiniMax, MINIMAX_M2_7, MINIMAX_M2_5, MINIMAX_M2_1, MINIMAX_M2_1_LIGHTNING, MINIMAX_M2, MINIMAX_ABAB6_5,
+              MiniMax, MINIMAX_M2_7, MINIMAX_M2_7_HIGHSPEED, MINIMAX_M2_5, MINIMAX_M2_1, MINIMAX_M2_1_LIGHTNING, MINIMAX_M2, MINIMAX_ABAB6_5,
 
               # GLM
               ZHIPU_AI, GLM_5_TURBO, GLM_5, GLM_4, GLM_4_PLUS, GLM_4_flash, GLM_4_LONG, GLM_4_ALLTOOLS,

models/minimax/minimax_bot.py

@@ -20,7 +20,7 @@ class MinimaxBot(Bot):
     def __init__(self):
         super().__init__()
         self.args = {
-            "model": conf().get("model") or "MiniMax-M2.1",
+            "model": conf().get("model") or "MiniMax-M2.7",
             "temperature": conf().get("temperature", 0.3),
             "top_p": conf().get("top_p", 0.95),
         }

tests/test_minimax_provider.py

@@ -0,0 +1,184 @@
+# encoding:utf-8
+"""
+Unit tests for MiniMax provider additions:
+  - MiniMax-M2.7-highspeed constant in const.py
+  - Default model update in MinimaxBot
+  - MinimaxVoice TTS provider
+"""
+import sys
+import os
+import json
+import unittest
+from unittest.mock import MagicMock, patch, PropertyMock
+
+# Add project root to path
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), ".."))
+
+
+class TestMinimaxConst(unittest.TestCase):
+    """Test that MiniMax-M2.7-highspeed is properly registered in const.py."""
+
+    def test_m2_7_highspeed_constant_defined(self):
+        from common import const
+        self.assertTrue(hasattr(const, "MINIMAX_M2_7_HIGHSPEED"))
+        self.assertEqual(const.MINIMAX_M2_7_HIGHSPEED, "MiniMax-M2.7-highspeed")
+
+    def test_m2_7_constant_defined(self):
+        from common import const
+        self.assertEqual(const.MINIMAX_M2_7, "MiniMax-M2.7")
+
+    def test_m2_7_highspeed_in_model_list(self):
+        from common import const
+        self.assertIn("MiniMax-M2.7-highspeed", const.MODEL_LIST)
+
+    def test_m2_7_in_model_list(self):
+        from common import const
+        self.assertIn("MiniMax-M2.7", const.MODEL_LIST)
+
+    def test_minimax_provider_key_defined(self):
+        from common import const
+        self.assertEqual(const.MiniMax, "minimax")
+
+
+class TestMinimaxBotDefaultModel(unittest.TestCase):
+    """Test that MinimaxBot defaults to MiniMax-M2.7."""
+
+    def test_default_model_is_m2_7(self):
+        # Patch conf() to return empty config
+        mock_conf = MagicMock()
+        mock_conf.get = MagicMock(side_effect=lambda key, default=None: default)
+
+        with patch("models.minimax.minimax_bot.conf", return_value=mock_conf):
+            with patch("models.minimax.minimax_bot.SessionManager"):
+                from models.minimax import minimax_bot
+                # Reload to pick up patches
+                import importlib
+                importlib.reload(minimax_bot)
+                with patch("models.minimax.minimax_bot.conf", return_value=mock_conf):
+                    bot = minimax_bot.MinimaxBot.__new__(minimax_bot.MinimaxBot)
+                    bot.args = {
+                        "model": mock_conf.get("model") or "MiniMax-M2.7",
+                    }
+                    self.assertEqual(bot.args["model"], "MiniMax-M2.7")
+
+    def test_default_model_string(self):
+        """Verify the fallback string literal in minimax_bot.py is MiniMax-M2.7."""
+        import ast
+        bot_path = os.path.join(os.path.dirname(__file__), "..", "models", "minimax", "minimax_bot.py")
+        with open(bot_path) as f:
+            source = f.read()
+        # Verify MiniMax-M2.7 is in the source (not M2.1)
+        self.assertIn("MiniMax-M2.7", source)
+        self.assertNotIn('"MiniMax-M2.1"', source)
+
+
+class TestMinimaxVoice(unittest.TestCase):
+    """Test MinimaxVoice TTS provider."""
+
+    def _make_voice(self, api_key="test-key", api_base="https://api.minimax.io/v1"):
+        mock_conf = MagicMock()
+        def conf_get(key, default=None):
+            return {
+                "minimax_api_key": api_key,
+                "minimax_api_base": api_base,
+            }.get(key, default)
+        mock_conf.get = conf_get
+        with patch("voice.minimax.minimax_voice.conf", return_value=mock_conf):
+            from voice.minimax.minimax_voice import MinimaxVoice
+            return MinimaxVoice()
+
+    def test_instantiation(self):
+        voice = self._make_voice()
+        self.assertIsNotNone(voice)
+
+    def test_api_base_strips_v1_suffix(self):
+        voice = self._make_voice(api_base="https://api.minimax.io/v1")
+        self.assertEqual(voice.api_base, "https://api.minimax.io")
+
+    def test_api_base_no_trailing_slash(self):
+        voice = self._make_voice(api_base="https://api.minimax.io")
+        self.assertEqual(voice.api_base, "https://api.minimax.io")
+
+    def test_voice_to_text_not_supported(self):
+        voice = self._make_voice()
+        with self.assertRaises(NotImplementedError):
+            voice.voiceToText("dummy.wav")
+
+    def test_text_to_voice_success(self):
+        """Test textToVoice with mocked SSE stream response."""
+        import os
+        os.makedirs("tmp", exist_ok=True)
+
+        # Build fake SSE stream bytes
+        audio_hex = bytes([0x49, 0x44, 0x33]).hex()  # "ID3" MP3 magic bytes
+        sse_line = f'data: {{"data": {{"audio": "{audio_hex}", "status": 2}}}}\n\n'
+        done_line = "data: [DONE]\n\n"
+        fake_body = (sse_line + done_line).encode("utf-8")
+
+        mock_response = MagicMock()
+        mock_response.raise_for_status = MagicMock()
+        mock_response.iter_lines.return_value = [
+            line.encode("utf-8") for line in (sse_line + done_line).splitlines() if line
+        ]
+
+        mock_conf = MagicMock()
+        def conf_get(key, default=None):
+            return {
+                "minimax_api_key": "test-key",
+                "minimax_api_base": "https://api.minimax.io",
+            }.get(key, default)
+        mock_conf.get = conf_get
+
+        with patch("voice.minimax.minimax_voice.conf", return_value=mock_conf):
+            with patch("voice.minimax.minimax_voice.requests.post", return_value=mock_response):
+                from voice.minimax import minimax_voice
+                import importlib
+                importlib.reload(minimax_voice)
+                with patch("voice.minimax.minimax_voice.conf", return_value=mock_conf):
+                    voice = minimax_voice.MinimaxVoice()
+                    from bridge.reply import ReplyType
+                    reply = voice.textToVoice("Hello, world!")
+                    self.assertEqual(reply.type, ReplyType.VOICE)
+                    self.assertTrue(reply.content.endswith(".mp3"))
+
+    def test_text_to_voice_no_audio_returns_error(self):
+        """Test that empty SSE stream returns an ERROR reply."""
+        mock_response = MagicMock()
+        mock_response.raise_for_status = MagicMock()
+        mock_response.iter_lines.return_value = []
+
+        mock_conf = MagicMock()
+        def conf_get(key, default=None):
+            return {
+                "minimax_api_key": "test-key",
+                "minimax_api_base": "https://api.minimax.io",
+            }.get(key, default)
+        mock_conf.get = conf_get
+
+        with patch("voice.minimax.minimax_voice.conf", return_value=mock_conf):
+            with patch("voice.minimax.minimax_voice.requests.post", return_value=mock_response):
+                from voice.minimax import minimax_voice
+                import importlib
+                importlib.reload(minimax_voice)
+                with patch("voice.minimax.minimax_voice.conf", return_value=mock_conf):
+                    voice = minimax_voice.MinimaxVoice()
+                    from bridge.reply import ReplyType
+                    reply = voice.textToVoice("Hello")
+                    self.assertEqual(reply.type, ReplyType.ERROR)
+
+
+class TestVoiceFactory(unittest.TestCase):
+    """Test that minimax is registered in the voice factory."""
+
+    def test_minimax_voice_factory(self):
+        mock_conf = MagicMock()
+        mock_conf.get = MagicMock(return_value=None)
+        with patch("voice.minimax.minimax_voice.conf", return_value=mock_conf):
+            from voice.factory import create_voice
+            voice = create_voice("minimax")
+            from voice.minimax.minimax_voice import MinimaxVoice
+            self.assertIsInstance(voice, MinimaxVoice)
+
+
+if __name__ == "__main__":
+    unittest.main()

voice/factory.py

@@ -54,4 +54,8 @@ def create_voice(voice_type):
         from voice.tencent.tencent_voice import TencentVoice
 
         return TencentVoice()
+    elif voice_type == "minimax":
+        from voice.minimax.minimax_voice import MinimaxVoice
+
+        return MinimaxVoice()
     raise RuntimeError

voice/minimax/minimax_voice.py

@@ -0,0 +1,106 @@
+# encoding:utf-8
+"""
+MiniMax TTS voice service
+"""
+import datetime
+import random
+import requests
+
+from bridge.reply import Reply, ReplyType
+from common.log import logger
+from config import conf
+from voice.voice import Voice
+
+
+MINIMAX_TTS_VOICES = [
+    "English_Graceful_Lady",
+    "English_Insightful_Speaker",
+    "English_radiant_girl",
+    "English_Persuasive_Man",
+    "English_Lucky_Robot",
+    "English_expressive_narrator",
+    "Chinese_Warm_Woman",
+    "Chinese_Gentle_Man",
+]
+
+
+class MinimaxVoice(Voice):
+    def __init__(self):
+        self.api_key = conf().get("minimax_api_key")
+        self.api_base = conf().get("minimax_api_base") or "https://api.minimax.io"
+        # Strip trailing /v1 if present so we can always append /v1/t2a_v2
+        self.api_base = self.api_base.rstrip("/")
+        if self.api_base.endswith("/v1"):
+            self.api_base = self.api_base[:-3]
+
+    def voiceToText(self, voice_file):
+        """MiniMax does not provide an ASR endpoint; raise NotImplementedError."""
+        raise NotImplementedError("MiniMax voice-to-text is not supported")
+
+    def textToVoice(self, text):
+        try:
+            model = conf().get("text_to_voice_model") or "speech-2.8-hd"
+            voice_id = conf().get("tts_voice_id") or "English_Graceful_Lady"
+
+            url = f"{self.api_base}/v1/t2a_v2"
+            headers = {
+                "Content-Type": "application/json",
+                "Authorization": f"Bearer {self.api_key}",
+            }
+            payload = {
+                "model": model,
+                "text": text,
+                "stream": True,
+                "voice_setting": {
+                    "voice_id": voice_id,
+                    "speed": 1,
+                    "vol": 1,
+                    "pitch": 0,
+                },
+                "audio_setting": {
+                    "sample_rate": 32000,
+                    "bitrate": 128000,
+                    "format": "mp3",
+                    "channel": 1,
+                },
+            }
+
+            response = requests.post(url, headers=headers, json=payload, stream=True, timeout=60)
+            response.raise_for_status()
+
+            # Parse SSE stream and collect hex-encoded audio chunks
+            audio_chunks = []
+            buffer = ""
+            for raw in response.iter_lines():
+                if not raw:
+                    continue
+                line = raw.decode("utf-8") if isinstance(raw, bytes) else raw
+                if not line.startswith("data:"):
+                    continue
+                json_str = line[5:].strip()
+                if not json_str or json_str == "[DONE]":
+                    continue
+                try:
+                    import json
+                    event_data = json.loads(json_str)
+                    audio_hex = event_data.get("data", {}).get("audio")
+                    if audio_hex:
+                        audio_chunks.append(bytes.fromhex(audio_hex))
+                except Exception:
+                    continue
+
+            if not audio_chunks:
+                logger.error("[MINIMAX] TTS returned no audio data")
+                return Reply(ReplyType.ERROR, "语音合成失败，未获取到音频数据")
+
+            audio_data = b"".join(audio_chunks)
+            file_name = "tmp/" + datetime.datetime.now().strftime("%Y%m%d%H%M%S") + str(random.randint(0, 1000)) + ".mp3"
+            with open(file_name, "wb") as f:
+                f.write(audio_data)
+
+            logger.info(f"[MINIMAX] textToVoice success, file={file_name}")
+            return Reply(ReplyType.VOICE, file_name)
+
+        except Exception as e:
+            logger.error(f"[MINIMAX] textToVoice error: {e}")
+            return Reply(ReplyType.ERROR, "遇到了一点小问题，请稍后再试")