fix: adapt MiMo STT to V2.5 models and reject non-WAV audio payloads

astrbot/core/config/default.py

@@ -1593,7 +1593,7 @@
                         "enable": False,
                         "api_key": "",
                         "api_base": "https://api.xiaomimimo.com/v1",
-                        "model": "mimo-v2-omni",
+                        "model": "mimo-v2.5-asr",
                         "timeout": "20",
                         "proxy": "",
                     },

astrbot/core/provider/sources/mimo_api_common.py

@@ -1,3 +1,4 @@
+import base64
 from pathlib import Path
 
 import httpx
@@ -10,7 +11,16 @@
 DEFAULT_MIMO_TTS_MODEL = "mimo-v2-tts"
 DEFAULT_MIMO_TTS_VOICE = "mimo_default"
 DEFAULT_MIMO_TTS_SEED_TEXT = "Hello, MiMo, have you had lunch?"
-DEFAULT_MIMO_STT_MODEL = "mimo-v2-omni"
+# The MiMo-V2 series went offline on 2026-06-30; mimo-v2.5-asr is the
+# dedicated speech recognition model per the official model lineup.
+DEFAULT_MIMO_STT_MODEL = "mimo-v2.5-asr"
+DEFAULT_MIMO_STT_SYSTEM_PROMPT = (
+    "You are a speech transcription assistant. "
+    "Transcribe the spoken content from the audio exactly and return only the transcription text."
+)
+DEFAULT_MIMO_STT_USER_PROMPT = (
+    "Please transcribe the content of the audio and return only the transcription text."
+)
 
 
 class MiMoAPIError(Exception):
@@ -67,9 +77,50 @@ async def prepare_audio_input(audio_source: str) -> tuple[str, list[Path]]:
     )
     if audio_data is None:
         raise ValueError(f"Invalid audio data: {describe_media_ref(audio_source)}")
+    _validate_wav_payload(audio_data.base64_data, audio_source)
     return audio_data.to_data_url(), []
 
 
+def _decode_base64_header(base64_data: str) -> bytes:
+    chunk = "".join(base64_data[:64].split())
+    padding = len(chunk) % 4
+    if padding:
+        chunk += "=" * (4 - padding)
+    return base64.b64decode(chunk)
+
+
+def _validate_wav_payload(base64_data: str, audio_source: str) -> None:
+    """Reject audio payloads whose bytes are not RIFF/WAVE.
+
+    MiMo only accepts wav/mp3 audio. When a platform voice file (e.g. Tencent
+    SILK from QQ) slips through the WAV conversion chain unchanged, the API
+    replies with an opaque HTTP 400, so fail locally with the real reason.
+
+    Args:
+        base64_data: Base64-encoded audio payload about to be sent.
+        audio_source: Original media reference, used in error messages.
+
+    Raises:
+        MiMoAPIError: Raised when the payload is not valid WAV data.
+    """
+    try:
+        header = _decode_base64_header(base64_data)
+    except Exception:
+        header = b""
+    if len(header) >= 12 and header[:4] == b"RIFF" and header[8:12] == b"WAVE":
+        return
+    if header.startswith((b"#!SILK_V3", b"\x02#!SILK_V3")):
+        raise MiMoAPIError(
+            "Audio for MiMo STT is still Tencent SILK data after WAV conversion; "
+            "check that the silk-python package is installed and working: "
+            f"{describe_media_ref(audio_source)}"
+        )
+    raise MiMoAPIError(
+        "Audio for MiMo STT could not be converted to WAV "
+        f"(unrecognized audio bytes): {describe_media_ref(audio_source)}"
+    )
+
+
 def cleanup_files(paths: list[Path]) -> None:
     for path in paths:
         try:

astrbot/core/provider/sources/mimo_stt_api_source.py

@@ -4,6 +4,8 @@
 from .mimo_api_common import (
     DEFAULT_MIMO_API_BASE,
     DEFAULT_MIMO_STT_MODEL,
+    DEFAULT_MIMO_STT_SYSTEM_PROMPT,
+    DEFAULT_MIMO_STT_USER_PROMPT,
     MiMoAPIError,
     build_api_url,
     build_headers,
@@ -33,23 +35,49 @@ def __init__(
         self.set_model(provider_config.get("model", DEFAULT_MIMO_STT_MODEL))
         self.client = create_http_client(self.timeout, self.proxy)
 
+    def _is_asr_model(self) -> bool:
+        return "asr" in (self.model_name or "").lower()
+
+    def _build_messages(self, audio_data_url: str) -> list[dict]:
+        audio_content = {
+            "type": "input_audio",
+            "input_audio": {
+                "data": audio_data_url,
+            },
+        }
+        if self._is_asr_model():
+            # Dedicated ASR models (speech-recognition docs) take bare audio.
+            return [
+                {
+                    "role": "user",
+                    "content": [audio_content],
+                },
+            ]
+        # Multimodal models such as mimo-v2.5 (audio-understanding docs)
+        # require a text instruction alongside the audio, otherwise the API
+        # rejects the request.
+        return [
+            {
+                "role": "system",
+                "content": DEFAULT_MIMO_STT_SYSTEM_PROMPT,
+            },
+            {
+                "role": "user",
+                "content": [
+                    audio_content,
+                    {
+                        "type": "text",
+                        "text": DEFAULT_MIMO_STT_USER_PROMPT,
+                    },
+                ],
+            },
+        ]
+
     async def get_text(self, audio_url: str) -> str:
         audio_data_url, cleanup_paths = await prepare_audio_input(audio_url)
         payload = {
             "model": self.model_name,
-            "messages": [
-                {
-                    "role": "user",
-                    "content": [
-                        {
-                            "type": "input_audio",
-                            "input_audio": {
-                                "data": audio_data_url,
-                            },
-                        },
-                    ],
-                },
-            ],
+            "messages": self._build_messages(audio_data_url),
             "max_completion_tokens": 1024,
         }
 

tests/test_mimo_api_sources.py

@@ -1,17 +1,21 @@
 import asyncio
+import base64
 from types import SimpleNamespace
 
 import pytest
 
 from astrbot.core.provider.sources.mimo_api_common import (
     MiMoAPIError,
+    _validate_wav_payload,
     build_headers,
     prepare_audio_input,
 )
 from astrbot.core.provider.sources.mimo_stt_api_source import ProviderMiMoSTTAPI
 from astrbot.core.provider.sources.mimo_tts_api_source import ProviderMiMoTTSAPI
 
-MIMO_STT_TEST_AUDIO_DATA_URL = "data:audio/wav;base64,ZmFrZQ=="
+MIMO_STT_TEST_WAV_HEADER = b"RIFF\x24\x08\x00\x00WAVEfmt "
+MIMO_STT_TEST_AUDIO_BASE64 = base64.b64encode(MIMO_STT_TEST_WAV_HEADER).decode()
+MIMO_STT_TEST_AUDIO_DATA_URL = f"data:audio/wav;base64,{MIMO_STT_TEST_AUDIO_BASE64}"
 
 
 def _make_tts_provider(overrides: dict | None = None) -> ProviderMiMoTTSAPI:
@@ -33,7 +37,7 @@ def _make_stt_provider(overrides: dict | None = None) -> ProviderMiMoSTTAPI:
     provider_config = {
         "id": "test-mimo-stt",
         "type": "mimo_stt_api",
-        "model": "mimo-v2-omni",
+        "model": "mimo-v2.5-asr",
         "api_key": "test-key",
     }
     if overrides:
@@ -196,7 +200,8 @@ def json(self):
 
 
 @pytest.mark.asyncio
-async def test_mimo_stt_payload_includes_audio_only(monkeypatch):
+async def test_mimo_stt_asr_model_payload_includes_audio_only(monkeypatch):
+    """专用 ASR 模型按官方语音识别文档只传 input_audio，不带任何提示词。"""
     provider = _make_stt_provider(
         {
             "mimo-stt-system-prompt": "system prompt",
@@ -248,10 +253,91 @@ async def fake_post(_url, headers=None, json=None):
     ]
 
 
+def test_mimo_stt_default_model_is_v25_asr():
+    """mimo-v2-omni 已于 2026-06-30 下线，默认模型应为 mimo-v2.5-asr。"""
+    provider = ProviderMiMoSTTAPI(
+        provider_config={
+            "id": "test-mimo-stt",
+            "type": "mimo_stt_api",
+            "api_key": "test-key",
+        },
+        provider_settings={},
+    )
+    try:
+        assert provider.model_name == "mimo-v2.5-asr"
+    finally:
+        asyncio.run(provider.terminate())
+
+
+@pytest.mark.asyncio
+async def test_mimo_stt_multimodal_model_payload_includes_transcription_prompts(
+    monkeypatch,
+):
+    """非 ASR 模型（如 mimo-v2.5）按官方音频理解文档要求携带 system 与 text 指令。"""
+    provider = _make_stt_provider({"model": "mimo-v2.5"})
+
+    captured: dict = {}
+
+    async def fake_prepare_audio_input(_audio_source: str):
+        return MIMO_STT_TEST_AUDIO_DATA_URL, []
+
+    class _Response:
+        status_code = 200
+        text = '{"choices":[{"message":{"content":"transcribed text"}}]}'
+
+        def raise_for_status(self):
+            return None
+
+        def json(self):
+            return {"choices": [{"message": {"content": "transcribed text"}}]}
+
+    async def fake_post(_url, headers=None, json=None):
+        captured["json"] = json
+        return _Response()
+
+    monkeypatch.setattr(
+        "astrbot.core.provider.sources.mimo_stt_api_source.prepare_audio_input",
+        fake_prepare_audio_input,
+    )
+    provider.client = SimpleNamespace(post=fake_post)
+
+    result = await provider.get_text("/tmp/test.wav")
+
+    assert result == "transcribed text"
+    assert captured["json"]["messages"] == [
+        {
+            "role": "system",
+            "content": (
+                "You are a speech transcription assistant. "
+                "Transcribe the spoken content from the audio exactly "
+                "and return only the transcription text."
+            ),
+        },
+        {
+            "role": "user",
+            "content": [
+                {
+                    "type": "input_audio",
+                    "input_audio": {
+                        "data": MIMO_STT_TEST_AUDIO_DATA_URL,
+                    },
+                },
+                {
+                    "type": "text",
+                    "text": (
+                        "Please transcribe the content of the audio "
+                        "and return only the transcription text."
+                    ),
+                },
+            ],
+        },
+    ]
+
+
 @pytest.mark.asyncio
 async def test_mimo_stt_prepare_audio_input_returns_data_url(monkeypatch):
     class _ResolvedAudio:
-        base64_data = "ZmFrZQ=="
+        base64_data = MIMO_STT_TEST_AUDIO_BASE64
         mime_type = "audio/wav"
         format = "wav"
 
@@ -284,6 +370,41 @@ async def to_base64_data(self, **kwargs):
     assert cleanup_paths == []
 
 
+@pytest.mark.asyncio
+async def test_mimo_stt_prepare_audio_input_rejects_non_wav_payload(monkeypatch):
+    """上游 SILK→WAV 转换静默失败时应本地报错，而不是把坏字节发给 API（#9113）。"""
+    silk_base64 = base64.b64encode(b"\x02#!SILK_V3" + b"\x00" * 16).decode()
+
+    class _ResolvedAudio:
+        base64_data = silk_base64
+        mime_type = "audio/wav"
+        format = "wav"
+
+        def to_data_url(self):
+            return f"data:audio/wav;base64,{silk_base64}"
+
+    class _Resolver:
+        def __init__(self, *_args, **_kwargs):
+            pass
+
+        async def to_base64_data(self, **_kwargs):
+            return _ResolvedAudio()
+
+    monkeypatch.setattr(
+        "astrbot.core.provider.sources.mimo_api_common.MediaResolver",
+        _Resolver,
+    )
+
+    with pytest.raises(MiMoAPIError, match="SILK"):
+        await prepare_audio_input("/tmp/test.wav")
+
+
+def test_mimo_stt_wav_validation_accepts_unpadded_base64_header():
+    wav_base64 = base64.b64encode(MIMO_STT_TEST_WAV_HEADER).decode().rstrip("=")
+
+    _validate_wav_payload(wav_base64, "/tmp/test.wav")
+
+
 @pytest.mark.asyncio
 async def test_mimo_stt_get_text_uses_reasoning_content(monkeypatch):
     provider = _make_stt_provider()