From 89371216b2fcf1e9bf38fb318c7b976eb99e8159 Mon Sep 17 00:00:00 2001
From: x7peeps <xtpeeps@gmail.com>
Date: Tue, 16 Jun 2026 23:42:49 +0800
Subject: [PATCH] fix(stt/tts): guard against null config subsections crashing
 with AttributeError

When stt.local, tts.edge, or other config subsections are explicitly set
to null in config.yaml (which happens by default on a fresh --voice
setup), stt_config.get('local', {}) returns None instead of {} because
YAML null preserves the key.  The chained .get('model') then crashes
with 'NoneType' object has no attribute 'get'.

Apply the defensive (x or {}) pattern to every place a config subsection
is read via .get('xxx', {}).  Covers local, edge, openai, mistral, and
elevenlabs subsections in both transcription_tools.py and tts_tool.py.

Closes #47318
---
 tools/transcription_tools.py | 18 +++++++++---------
 tools/tts_tool.py            |  2 +-
 2 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/tools/transcription_tools.py b/tools/transcription_tools.py
index 49f8cbaca22..02380fbc433 100644
--- a/tools/transcription_tools.py
+++ b/tools/transcription_tools.py
@@ -1130,7 +1130,7 @@ def _transcribe_local(file_path: str, model_name: str) -> Dict[str, Any]:
 
         # Language: config.yaml (stt.local.language) > env var > auto-detect.
         _forced_lang = (
-            _load_stt_config().get("local", {}).get("language")
+            (_load_stt_config().get("local", {}) or {}).get("language")
             or os.getenv(LOCAL_STT_LANGUAGE_ENV)
             or None
         )
@@ -1213,7 +1213,7 @@ def _transcribe_local_command(file_path: str, model_name: str) -> Dict[str, Any]
 
     # Language: config.yaml (stt.local.language) > env var > "en" default.
     language = (
-        _load_stt_config().get("local", {}).get("language")
+        (_load_stt_config().get("local", {}) or {}).get("language")
         or os.getenv(LOCAL_STT_LANGUAGE_ENV)
         or DEFAULT_LOCAL_STT_LANGUAGE
     )
@@ -1542,7 +1542,7 @@ def _transcribe_elevenlabs(file_path: str, model_name: str) -> Dict[str, Any]:
         return {"success": False, "transcript": "", "error": "ELEVENLABS_API_KEY not set"}
 
     stt_config = _load_stt_config()
-    elevenlabs_config = stt_config.get("elevenlabs", {})
+    elevenlabs_config = stt_config.get("elevenlabs", {}) or {}
     base_url = str(
         elevenlabs_config.get("base_url")
         or get_env_value("ELEVENLABS_STT_BASE_URL")
@@ -1657,14 +1657,14 @@ def transcribe_audio(file_path: str, model: Optional[str] = None) -> Dict[str, A
     provider = _get_provider(stt_config)
 
     if provider == "local":
-        local_cfg = stt_config.get("local", {})
+        local_cfg = stt_config.get("local", {}) or {}
         model_name = _normalize_local_model(
             model or local_cfg.get("model", DEFAULT_LOCAL_MODEL)
         )
         return _transcribe_local(file_path, model_name)
 
     if provider == "local_command":
-        local_cfg = stt_config.get("local", {})
+        local_cfg = stt_config.get("local", {}) or {}
         model_name = _normalize_local_command_model(
             model or local_cfg.get("model", DEFAULT_LOCAL_MODEL)
         )
@@ -1675,12 +1675,12 @@ def transcribe_audio(file_path: str, model: Optional[str] = None) -> Dict[str, A
         return _transcribe_groq(file_path, model_name)
 
     if provider == "openai":
-        openai_cfg = stt_config.get("openai", {})
+        openai_cfg = stt_config.get("openai", {}) or {}
         model_name = model or openai_cfg.get("model", DEFAULT_STT_MODEL)
         return _transcribe_openai(file_path, model_name)
 
     if provider == "mistral":
-        mistral_cfg = stt_config.get("mistral", {})
+        mistral_cfg = stt_config.get("mistral", {}) or {}
         model_name = model or mistral_cfg.get("model", DEFAULT_MISTRAL_STT_MODEL)
         return _transcribe_mistral(file_path, model_name)
 
@@ -1690,7 +1690,7 @@ def transcribe_audio(file_path: str, model: Optional[str] = None) -> Dict[str, A
         return _transcribe_xai(file_path, model_name)
 
     if provider == "elevenlabs":
-        elevenlabs_cfg = stt_config.get("elevenlabs", {})
+        elevenlabs_cfg = stt_config.get("elevenlabs", {}) or {}
         model_name = model or elevenlabs_cfg.get("model_id", DEFAULT_ELEVENLABS_STT_MODEL)
         return _transcribe_elevenlabs(file_path, model_name)
 
@@ -1754,7 +1754,7 @@ def transcribe_audio(file_path: str, model: Optional[str] = None) -> Dict[str, A
 def _resolve_openai_audio_client_config() -> tuple[str, str]:
     """Return direct OpenAI audio config or a managed gateway fallback."""
     stt_config = _load_stt_config()
-    openai_cfg = stt_config.get("openai", {})
+    openai_cfg = stt_config.get("openai", {}) or {}
     cfg_api_key = openai_cfg.get("api_key", "")
     cfg_base_url = openai_cfg.get("base_url", "")
     if cfg_api_key:
diff --git a/tools/tts_tool.py b/tools/tts_tool.py
index e2a96fb4ad7..758eace2472 100644
--- a/tools/tts_tool.py
+++ b/tools/tts_tool.py
@@ -949,7 +949,7 @@ async def _generate_edge_tts(text: str, output_path: str, tts_config: Dict[str,
         Path to the saved audio file.
     """
     _edge_tts = _import_edge_tts()
-    edge_config = tts_config.get("edge", {})
+    edge_config = tts_config.get("edge", {}) or {}
     voice = edge_config.get("voice", DEFAULT_EDGE_VOICE)
     speed = float(edge_config.get("speed", tts_config.get("speed", 1.0)))