diff --git a/cli.py b/cli.py
index 351e23a6..cc9f522a 100755
--- a/cli.py
+++ b/cli.py
@@ -3555,12 +3555,12 @@ class HermesCLI:
                 "Install with: pip install sounddevice numpy\n"
                 "Or: pip install hermes-agent[voice]"
             )
-        if not reqs["stt_key_set"]:
+        if not reqs.get("stt_available", reqs.get("stt_key_set")):
             raise RuntimeError(
-                "Voice mode requires an STT API key for transcription.\n"
-                "Set GROQ_API_KEY (free) or VOICE_TOOLS_OPENAI_KEY.\n"
-                "Groq: https://console.groq.com/keys\n"
-                "OpenAI: https://platform.openai.com/api-keys"
+                "Voice mode requires an STT provider for transcription.\n"
+                "Option 1: pip install faster-whisper  (free, local)\n"
+                "Option 2: Set GROQ_API_KEY (free tier)\n"
+                "Option 3: Set VOICE_TOOLS_OPENAI_KEY (paid)"
             )
 
         # Prevent double-start from concurrent threads (atomic check-and-set)
diff --git a/tests/tools/test_voice_mode.py b/tests/tools/test_voice_mode.py
index f92bf6f2..70424fee 100644
--- a/tests/tools/test_voice_mode.py
+++ b/tests/tools/test_voice_mode.py
@@ -65,14 +65,14 @@ class TestCheckVoiceRequirements:
         monkeypatch.setattr("tools.voice_mode._audio_available", lambda: True)
         monkeypatch.setattr("tools.voice_mode.detect_audio_environment",
                             lambda: {"available": True, "warnings": []})
-        monkeypatch.setenv("VOICE_TOOLS_OPENAI_KEY", "sk-test-key")
+        monkeypatch.setattr("tools.transcription_tools._get_provider", lambda cfg: "openai")
 
         from tools.voice_mode import check_voice_requirements
 
         result = check_voice_requirements()
         assert result["available"] is True
         assert result["audio_available"] is True
-        assert result["stt_key_set"] is True
+        assert result["stt_available"] is True
         assert result["missing_packages"] == []
 
     def test_missing_audio_packages(self, monkeypatch):
@@ -89,19 +89,18 @@ class TestCheckVoiceRequirements:
         assert "sounddevice" in result["missing_packages"]
         assert "numpy" in result["missing_packages"]
 
-    def test_missing_stt_key(self, monkeypatch):
+    def test_missing_stt_provider(self, monkeypatch):
         monkeypatch.setattr("tools.voice_mode._audio_available", lambda: True)
         monkeypatch.setattr("tools.voice_mode.detect_audio_environment",
                             lambda: {"available": True, "warnings": []})
-        monkeypatch.delenv("VOICE_TOOLS_OPENAI_KEY", raising=False)
-        monkeypatch.delenv("GROQ_API_KEY", raising=False)
+        monkeypatch.setattr("tools.transcription_tools._get_provider", lambda cfg: "none")
 
         from tools.voice_mode import check_voice_requirements
 
         result = check_voice_requirements()
         assert result["available"] is False
-        assert result["stt_key_set"] is False
-        assert "STT API key: MISSING" in result["details"]
+        assert result["stt_available"] is False
+        assert "STT provider: MISSING" in result["details"]
 
 
 # ============================================================================
diff --git a/tools/voice_mode.py b/tools/voice_mode.py
index a108ed84..93e044eb 100644
--- a/tools/voice_mode.py
+++ b/tools/voice_mode.py
@@ -676,12 +676,15 @@ def check_voice_requirements() -> Dict[str, Any]:
     """Check if all voice mode requirements are met.
 
     Returns:
-        Dict with ``available``, ``audio_available``, ``stt_key_set``,
+        Dict with ``available``, ``audio_available``, ``stt_available``,
         ``missing_packages``, and ``details``.
     """
-    openai_key = bool(os.getenv("VOICE_TOOLS_OPENAI_KEY"))
-    groq_key = bool(os.getenv("GROQ_API_KEY"))
-    stt_key_set = openai_key or groq_key
+    # Determine STT provider availability
+    from tools.transcription_tools import _get_provider, _load_stt_config, _HAS_FASTER_WHISPER
+    stt_config = _load_stt_config()
+    stt_provider = _get_provider(stt_config)
+    stt_available = stt_provider != "none"
+
     missing: List[str] = []
     has_audio = _audio_available()
 
@@ -691,7 +694,7 @@ def check_voice_requirements() -> Dict[str, Any]:
     # Environment detection
     env_check = detect_audio_environment()
 
-    available = has_audio and stt_key_set and env_check["available"]
+    available = has_audio and stt_available and env_check["available"]
     details_parts = []
 
     if has_audio:
@@ -699,12 +702,17 @@ def check_voice_requirements() -> Dict[str, Any]:
     else:
         details_parts.append("Audio capture: MISSING (pip install sounddevice numpy)")
 
-    if openai_key:
-        details_parts.append("STT API key: OK (OpenAI)")
-    elif groq_key:
-        details_parts.append("STT API key: OK (Groq)")
+    if stt_provider == "local":
+        details_parts.append("STT provider: OK (local faster-whisper)")
+    elif stt_provider == "groq":
+        details_parts.append("STT provider: OK (Groq)")
+    elif stt_provider == "openai":
+        details_parts.append("STT provider: OK (OpenAI)")
     else:
-        details_parts.append("STT API key: MISSING (set GROQ_API_KEY or VOICE_TOOLS_OPENAI_KEY)")
+        details_parts.append(
+            "STT provider: MISSING (pip install faster-whisper, "
+            "or set GROQ_API_KEY / VOICE_TOOLS_OPENAI_KEY)"
+        )
 
     for warning in env_check["warnings"]:
         details_parts.append(f"Environment: {warning}")
@@ -712,7 +720,7 @@ def check_voice_requirements() -> Dict[str, Any]:
     return {
         "available": available,
         "audio_available": has_audio,
-        "stt_key_set": stt_key_set,
+        "stt_available": stt_available,
         "missing_packages": missing,
         "details": "\n".join(details_parts),
         "environment": env_check,