fix: handle YAML null values in session reset policy + configurable API timeout

Two fixes from PR #888 by @Jah-yee:

1. SessionResetPolicy.from_dict() — data.get('at_hour', 4) returns None
   when the YAML key exists with a null value. Now explicitly checks for
   None and falls back to defaults. Zero remains a valid value.

2. API timeout — hardcoded 900s is now configurable via HERMES_API_TIMEOUT
   env var. Useful for slow local models (llama.cpp) that need longer.

Co-authored-by: Jah-yee <Jah-yee@users.noreply.github.com>

agent/context_compressor.py

@@ -132,7 +132,11 @@ Write only the summary, starting with "[CONTEXT SUMMARY]:" prefix."""
             if self.summary_model:
                 call_kwargs["model"] = self.summary_model
             response = call_llm(**call_kwargs)
-            summary = response.choices[0].message.content.strip()
+            content = response.choices[0].message.content
+            # Handle cases where content is not a string (e.g., dict from llama.cpp)
+            if not isinstance(content, str):
+                content = str(content) if content else ""
+            summary = content.strip()
             if not summary.startswith("[CONTEXT SUMMARY]:"):
                 summary = "[CONTEXT SUMMARY]: " + summary
             return summary

gateway/config.py

@@ -83,10 +83,13 @@ class SessionResetPolicy:
     
     @classmethod
     def from_dict(cls, data: Dict[str, Any]) -> "SessionResetPolicy":
+        # Handle both missing keys and explicit null values (YAML null → None)
+        at_hour = data.get("at_hour")
+        idle_minutes = data.get("idle_minutes")
         return cls(
             mode=data.get("mode", "both"),
-            at_hour=data.get("at_hour", 4),
+            at_hour=at_hour if at_hour is not None else 4,
-            idle_minutes=data.get("idle_minutes", 1440),
+            idle_minutes=idle_minutes if idle_minutes is not None else 1440,
         )
 
 

hermes_cli/config.py

@@ -194,8 +194,13 @@ DEFAULT_CONFIG = {
     },
     
     "stt": {
-        "enabled": True,
+        "provider": "local",  # "local" (free, faster-whisper) | "openai" (Whisper API)
-        "model": "whisper-1",
+        "local": {
+            "model": "base",  # tiny, base, small, medium, large-v3
+        },
+        "openai": {
+            "model": "whisper-1",  # whisper-1, gpt-4o-mini-transcribe, gpt-4o-transcribe
+        },
     },
     
     "human_delay": {

pyproject.toml

@@ -30,6 +30,7 @@ dependencies = [
   "fal-client",
   # Text-to-speech (Edge TTS is free, no API key needed)
   "edge-tts",
+  "faster-whisper>=1.0.0",
   # mini-swe-agent deps (terminal tool)
   "litellm>=1.75.5",
   "typer",

run_agent.py

@@ -2729,7 +2729,7 @@ class AIAgent:
             "model": self.model,
             "messages": api_messages,
             "tools": self.tools if self.tools else None,
-            "timeout": 900.0,
+            "timeout": float(os.getenv("HERMES_API_TIMEOUT", 900.0)),
         }
 
         if self.max_tokens is not None:

tests/agent/test_context_compressor.py

@@ -153,6 +153,47 @@ class TestGenerateSummaryNoneContent:
         assert len(result) < len(msgs)
 
 
+class TestNonStringContent:
+    """Regression: content as dict (e.g., llama.cpp tool calls) must not crash."""
+
+    def test_dict_content_coerced_to_string(self):
+        mock_response = MagicMock()
+        mock_response.choices = [MagicMock()]
+        mock_response.choices[0].message.content = {"text": "some summary"}
+
+        with patch("agent.context_compressor.get_model_context_length", return_value=100000):
+            c = ContextCompressor(model="test", quiet_mode=True)
+
+        messages = [
+            {"role": "user", "content": "do something"},
+            {"role": "assistant", "content": "ok"},
+        ]
+
+        with patch("agent.context_compressor.call_llm", return_value=mock_response):
+            summary = c._generate_summary(messages)
+        assert isinstance(summary, str)
+        assert "CONTEXT SUMMARY" in summary
+
+    def test_none_content_coerced_to_empty(self):
+        mock_response = MagicMock()
+        mock_response.choices = [MagicMock()]
+        mock_response.choices[0].message.content = None
+
+        with patch("agent.context_compressor.get_model_context_length", return_value=100000):
+            c = ContextCompressor(model="test", quiet_mode=True)
+
+        messages = [
+            {"role": "user", "content": "do something"},
+            {"role": "assistant", "content": "ok"},
+        ]
+
+        with patch("agent.context_compressor.call_llm", return_value=mock_response):
+            summary = c._generate_summary(messages)
+        # None content → empty string → "[CONTEXT SUMMARY]: " prefix added
+        assert summary is not None
+        assert "CONTEXT SUMMARY" in summary
+
+
 class TestCompressWithClient:
     def test_summarization_path(self):
         mock_client = MagicMock()

tests/tools/test_transcription.py

@@ -0,0 +1,223 @@
+"""Tests for transcription_tools.py — local (faster-whisper) and OpenAI providers.
+
+Tests cover provider selection, config loading, validation, and transcription
+dispatch.  All external dependencies (faster_whisper, openai) are mocked.
+"""
+
+import json
+import os
+import tempfile
+from pathlib import Path
+from unittest.mock import MagicMock, patch, mock_open
+
+import pytest
+
+
+# ---------------------------------------------------------------------------
+# Provider selection
+# ---------------------------------------------------------------------------
+
+
+class TestGetProvider:
+    """_get_provider() picks the right backend based on config + availability."""
+
+    def test_local_when_available(self):
+        with patch("tools.transcription_tools._HAS_FASTER_WHISPER", True):
+            from tools.transcription_tools import _get_provider
+            assert _get_provider({"provider": "local"}) == "local"
+
+    def test_local_fallback_to_openai(self, monkeypatch):
+        monkeypatch.setenv("VOICE_TOOLS_OPENAI_KEY", "sk-test")
+        with patch("tools.transcription_tools._HAS_FASTER_WHISPER", False), \
+             patch("tools.transcription_tools._HAS_OPENAI", True):
+            from tools.transcription_tools import _get_provider
+            assert _get_provider({"provider": "local"}) == "openai"
+
+    def test_local_nothing_available(self, monkeypatch):
+        monkeypatch.delenv("VOICE_TOOLS_OPENAI_KEY", raising=False)
+        with patch("tools.transcription_tools._HAS_FASTER_WHISPER", False), \
+             patch("tools.transcription_tools._HAS_OPENAI", False):
+            from tools.transcription_tools import _get_provider
+            assert _get_provider({"provider": "local"}) == "none"
+
+    def test_openai_when_key_set(self, monkeypatch):
+        monkeypatch.setenv("VOICE_TOOLS_OPENAI_KEY", "sk-test")
+        with patch("tools.transcription_tools._HAS_OPENAI", True):
+            from tools.transcription_tools import _get_provider
+            assert _get_provider({"provider": "openai"}) == "openai"
+
+    def test_openai_fallback_to_local(self, monkeypatch):
+        monkeypatch.delenv("VOICE_TOOLS_OPENAI_KEY", raising=False)
+        with patch("tools.transcription_tools._HAS_FASTER_WHISPER", True), \
+             patch("tools.transcription_tools._HAS_OPENAI", True):
+            from tools.transcription_tools import _get_provider
+            assert _get_provider({"provider": "openai"}) == "local"
+
+    def test_default_provider_is_local(self):
+        with patch("tools.transcription_tools._HAS_FASTER_WHISPER", True):
+            from tools.transcription_tools import _get_provider
+            assert _get_provider({}) == "local"
+
+
+# ---------------------------------------------------------------------------
+# File validation
+# ---------------------------------------------------------------------------
+
+
+class TestValidateAudioFile:
+
+    def test_missing_file(self, tmp_path):
+        from tools.transcription_tools import _validate_audio_file
+        result = _validate_audio_file(str(tmp_path / "nope.ogg"))
+        assert result is not None
+        assert "not found" in result["error"]
+
+    def test_unsupported_format(self, tmp_path):
+        f = tmp_path / "test.xyz"
+        f.write_bytes(b"data")
+        from tools.transcription_tools import _validate_audio_file
+        result = _validate_audio_file(str(f))
+        assert result is not None
+        assert "Unsupported" in result["error"]
+
+    def test_valid_file_returns_none(self, tmp_path):
+        f = tmp_path / "test.ogg"
+        f.write_bytes(b"fake audio data")
+        from tools.transcription_tools import _validate_audio_file
+        assert _validate_audio_file(str(f)) is None
+
+    def test_too_large(self, tmp_path):
+        import stat as stat_mod
+        f = tmp_path / "big.ogg"
+        f.write_bytes(b"x")
+        from tools.transcription_tools import _validate_audio_file, MAX_FILE_SIZE
+        real_stat = f.stat()
+        with patch.object(type(f), "stat", return_value=os.stat_result((
+            real_stat.st_mode, real_stat.st_ino, real_stat.st_dev,
+            real_stat.st_nlink, real_stat.st_uid, real_stat.st_gid,
+            MAX_FILE_SIZE + 1,  # st_size
+            real_stat.st_atime, real_stat.st_mtime, real_stat.st_ctime,
+        ))):
+            result = _validate_audio_file(str(f))
+        assert result is not None
+        assert "too large" in result["error"]
+
+
+# ---------------------------------------------------------------------------
+# Local transcription
+# ---------------------------------------------------------------------------
+
+
+class TestTranscribeLocal:
+
+    def test_successful_transcription(self, tmp_path):
+        audio_file = tmp_path / "test.ogg"
+        audio_file.write_bytes(b"fake audio")
+
+        mock_segment = MagicMock()
+        mock_segment.text = "Hello world"
+        mock_info = MagicMock()
+        mock_info.language = "en"
+        mock_info.duration = 2.5
+
+        mock_model = MagicMock()
+        mock_model.transcribe.return_value = ([mock_segment], mock_info)
+
+        with patch("tools.transcription_tools._HAS_FASTER_WHISPER", True), \
+             patch("tools.transcription_tools.WhisperModel", return_value=mock_model), \
+             patch("tools.transcription_tools._local_model", None):
+            from tools.transcription_tools import _transcribe_local
+            result = _transcribe_local(str(audio_file), "base")
+
+        assert result["success"] is True
+        assert result["transcript"] == "Hello world"
+
+    def test_not_installed(self):
+        with patch("tools.transcription_tools._HAS_FASTER_WHISPER", False):
+            from tools.transcription_tools import _transcribe_local
+            result = _transcribe_local("/tmp/test.ogg", "base")
+        assert result["success"] is False
+        assert "not installed" in result["error"]
+
+
+# ---------------------------------------------------------------------------
+# OpenAI transcription
+# ---------------------------------------------------------------------------
+
+
+class TestTranscribeOpenAI:
+
+    def test_no_key(self, monkeypatch):
+        monkeypatch.delenv("VOICE_TOOLS_OPENAI_KEY", raising=False)
+        from tools.transcription_tools import _transcribe_openai
+        result = _transcribe_openai("/tmp/test.ogg", "whisper-1")
+        assert result["success"] is False
+        assert "VOICE_TOOLS_OPENAI_KEY" in result["error"]
+
+    def test_successful_transcription(self, monkeypatch, tmp_path):
+        monkeypatch.setenv("VOICE_TOOLS_OPENAI_KEY", "sk-test")
+        audio_file = tmp_path / "test.ogg"
+        audio_file.write_bytes(b"fake audio")
+
+        mock_client = MagicMock()
+        mock_client.audio.transcriptions.create.return_value = "Hello from OpenAI"
+
+        with patch("tools.transcription_tools._HAS_OPENAI", True), \
+             patch("tools.transcription_tools.OpenAI", return_value=mock_client):
+            from tools.transcription_tools import _transcribe_openai
+            result = _transcribe_openai(str(audio_file), "whisper-1")
+
+        assert result["success"] is True
+        assert result["transcript"] == "Hello from OpenAI"
+
+
+# ---------------------------------------------------------------------------
+# Main transcribe_audio() dispatch
+# ---------------------------------------------------------------------------
+
+
+class TestTranscribeAudio:
+
+    def test_dispatches_to_local(self, tmp_path):
+        audio_file = tmp_path / "test.ogg"
+        audio_file.write_bytes(b"fake audio")
+
+        with patch("tools.transcription_tools._load_stt_config", return_value={"provider": "local"}), \
+             patch("tools.transcription_tools._get_provider", return_value="local"), \
+             patch("tools.transcription_tools._transcribe_local", return_value={"success": True, "transcript": "hi"}) as mock_local:
+            from tools.transcription_tools import transcribe_audio
+            result = transcribe_audio(str(audio_file))
+
+        assert result["success"] is True
+        mock_local.assert_called_once()
+
+    def test_dispatches_to_openai(self, tmp_path):
+        audio_file = tmp_path / "test.ogg"
+        audio_file.write_bytes(b"fake audio")
+
+        with patch("tools.transcription_tools._load_stt_config", return_value={"provider": "openai"}), \
+             patch("tools.transcription_tools._get_provider", return_value="openai"), \
+             patch("tools.transcription_tools._transcribe_openai", return_value={"success": True, "transcript": "hi"}) as mock_openai:
+            from tools.transcription_tools import transcribe_audio
+            result = transcribe_audio(str(audio_file))
+
+        assert result["success"] is True
+        mock_openai.assert_called_once()
+
+    def test_no_provider_returns_error(self, tmp_path):
+        audio_file = tmp_path / "test.ogg"
+        audio_file.write_bytes(b"fake audio")
+
+        with patch("tools.transcription_tools._load_stt_config", return_value={}), \
+             patch("tools.transcription_tools._get_provider", return_value="none"):
+            from tools.transcription_tools import transcribe_audio
+            result = transcribe_audio(str(audio_file))
+
+        assert result["success"] is False
+        assert "No STT provider" in result["error"]
+
+    def test_invalid_file_returns_error(self):
+        from tools.transcription_tools import transcribe_audio
+        result = transcribe_audio("/nonexistent/file.ogg")
+        assert result["success"] is False
+        assert "not found" in result["error"]

tools/transcription_tools.py

@@ -2,18 +2,19 @@
 """
 Transcription Tools Module
 
-Provides speech-to-text transcription using OpenAI's Whisper API.
+Provides speech-to-text transcription with two providers:
-Used by the messaging gateway to automatically transcribe voice messages
-sent by users on Telegram, Discord, WhatsApp, and Slack.
 
-Supported models:
+  - **local** (default, free) — faster-whisper running locally, no API key needed.
-  - whisper-1        (cheapest, good quality)
+    Auto-downloads the model (~150 MB for ``base``) on first use.
-  - gpt-4o-mini-transcribe  (better quality, higher cost)
+  - **openai** — OpenAI Whisper API, requires ``VOICE_TOOLS_OPENAI_KEY``.
-  - gpt-4o-transcribe       (best quality, highest cost)
+
+Used by the messaging gateway to automatically transcribe voice messages
+sent by users on Telegram, Discord, WhatsApp, Slack, and Signal.
 
 Supported input formats: mp3, mp4, mpeg, mpga, m4a, wav, webm, ogg
 
-Usage:
+Usage::
+
     from tools.transcription_tools import transcribe_audio
 
     result = transcribe_audio("/path/to/audio.ogg")
@@ -28,27 +29,205 @@ from typing import Optional, Dict, Any
 
 logger = logging.getLogger(__name__)
 
+# ---------------------------------------------------------------------------
+# Optional imports — graceful degradation
+# ---------------------------------------------------------------------------
 
-# Default STT model -- cheapest and widely available
+try:
-DEFAULT_STT_MODEL = "whisper-1"
+    from faster_whisper import WhisperModel
+    _HAS_FASTER_WHISPER = True
+except ImportError:
+    _HAS_FASTER_WHISPER = False
+    WhisperModel = None  # type: ignore[assignment,misc]
+
+try:
+    from openai import OpenAI, APIError, APIConnectionError, APITimeoutError
+    _HAS_OPENAI = True
+except ImportError:
+    _HAS_OPENAI = False
+
+# ---------------------------------------------------------------------------
+# Constants
+# ---------------------------------------------------------------------------
+
+DEFAULT_PROVIDER = "local"
+DEFAULT_LOCAL_MODEL = "base"
+DEFAULT_OPENAI_MODEL = "whisper-1"
 
-# Supported audio formats
 SUPPORTED_FORMATS = {".mp3", ".mp4", ".mpeg", ".mpga", ".m4a", ".wav", ".webm", ".ogg"}
+MAX_FILE_SIZE = 25 * 1024 * 1024  # 25 MB
 
-# Maximum file size (25MB - OpenAI limit)
+# Singleton for the local model — loaded once, reused across calls
-MAX_FILE_SIZE = 25 * 1024 * 1024
+_local_model: Optional["WhisperModel"] = None
+_local_model_name: Optional[str] = None
+
+# ---------------------------------------------------------------------------
+# Config helpers
+# ---------------------------------------------------------------------------
+
+
+def _load_stt_config() -> dict:
+    """Load the ``stt`` section from user config, falling back to defaults."""
+    try:
+        from hermes_cli.config import load_config
+        return load_config().get("stt", {})
+    except Exception:
+        return {}
+
+
+def _get_provider(stt_config: dict) -> str:
+    """Determine which STT provider to use.
+
+    Priority:
+      1. Explicit config value  (``stt.provider``)
+      2. Auto-detect: local if faster-whisper available, else openai if key set
+      3. Disabled (returns "none")
+    """
+    provider = stt_config.get("provider", DEFAULT_PROVIDER)
+
+    if provider == "local":
+        if _HAS_FASTER_WHISPER:
+            return "local"
+        # Local requested but not available — fall back to openai if possible
+        if _HAS_OPENAI and os.getenv("VOICE_TOOLS_OPENAI_KEY"):
+            logger.info("faster-whisper not installed, falling back to OpenAI Whisper API")
+            return "openai"
+        return "none"
+
+    if provider == "openai":
+        if _HAS_OPENAI and os.getenv("VOICE_TOOLS_OPENAI_KEY"):
+            return "openai"
+        # OpenAI requested but no key — fall back to local if possible
+        if _HAS_FASTER_WHISPER:
+            logger.info("VOICE_TOOLS_OPENAI_KEY not set, falling back to local faster-whisper")
+            return "local"
+        return "none"
+
+    return provider  # Unknown — let it fail downstream
+
+# ---------------------------------------------------------------------------
+# Shared validation
+# ---------------------------------------------------------------------------
+
+
+def _validate_audio_file(file_path: str) -> Optional[Dict[str, Any]]:
+    """Validate the audio file.  Returns an error dict or None if OK."""
+    audio_path = Path(file_path)
+
+    if not audio_path.exists():
+        return {"success": False, "transcript": "", "error": f"Audio file not found: {file_path}"}
+    if not audio_path.is_file():
+        return {"success": False, "transcript": "", "error": f"Path is not a file: {file_path}"}
+    if audio_path.suffix.lower() not in SUPPORTED_FORMATS:
+        return {
+            "success": False,
+            "transcript": "",
+            "error": f"Unsupported format: {audio_path.suffix}. Supported: {', '.join(sorted(SUPPORTED_FORMATS))}",
+        }
+    try:
+        file_size = audio_path.stat().st_size
+        if file_size > MAX_FILE_SIZE:
+            return {
+                "success": False,
+                "transcript": "",
+                "error": f"File too large: {file_size / (1024*1024):.1f}MB (max {MAX_FILE_SIZE / (1024*1024):.0f}MB)",
+            }
+    except OSError as e:
+        return {"success": False, "transcript": "", "error": f"Failed to access file: {e}"}
+
+    return None
+
+# ---------------------------------------------------------------------------
+# Provider: local (faster-whisper)
+# ---------------------------------------------------------------------------
+
+
+def _transcribe_local(file_path: str, model_name: str) -> Dict[str, Any]:
+    """Transcribe using faster-whisper (local, free)."""
+    global _local_model, _local_model_name
+
+    if not _HAS_FASTER_WHISPER:
+        return {"success": False, "transcript": "", "error": "faster-whisper not installed"}
+
+    try:
+        # Lazy-load the model (downloads on first use, ~150 MB for 'base')
+        if _local_model is None or _local_model_name != model_name:
+            logger.info("Loading faster-whisper model '%s' (first load downloads the model)...", model_name)
+            _local_model = WhisperModel(model_name, device="auto", compute_type="auto")
+            _local_model_name = model_name
+
+        segments, info = _local_model.transcribe(file_path, beam_size=5)
+        transcript = " ".join(segment.text.strip() for segment in segments)
+
+        logger.info(
+            "Transcribed %s via local whisper (%s, lang=%s, %.1fs audio)",
+            Path(file_path).name, model_name, info.language, info.duration,
+        )
+
+        return {"success": True, "transcript": transcript}
+
+    except Exception as e:
+        logger.error("Local transcription failed: %s", e, exc_info=True)
+        return {"success": False, "transcript": "", "error": f"Local transcription failed: {e}"}
+
+# ---------------------------------------------------------------------------
+# Provider: openai (Whisper API)
+# ---------------------------------------------------------------------------
+
+
+def _transcribe_openai(file_path: str, model_name: str) -> Dict[str, Any]:
+    """Transcribe using OpenAI Whisper API (paid)."""
+    api_key = os.getenv("VOICE_TOOLS_OPENAI_KEY")
+    if not api_key:
+        return {"success": False, "transcript": "", "error": "VOICE_TOOLS_OPENAI_KEY not set"}
+
+    if not _HAS_OPENAI:
+        return {"success": False, "transcript": "", "error": "openai package not installed"}
+
+    try:
+        client = OpenAI(api_key=api_key, base_url="https://api.openai.com/v1")
+
+        with open(file_path, "rb") as audio_file:
+            transcription = client.audio.transcriptions.create(
+                model=model_name,
+                file=audio_file,
+                response_format="text",
+            )
+
+        transcript_text = str(transcription).strip()
+        logger.info("Transcribed %s via OpenAI API (%s, %d chars)",
+                     Path(file_path).name, model_name, len(transcript_text))
+
+        return {"success": True, "transcript": transcript_text}
+
+    except PermissionError:
+        return {"success": False, "transcript": "", "error": f"Permission denied: {file_path}"}
+    except APIConnectionError as e:
+        return {"success": False, "transcript": "", "error": f"Connection error: {e}"}
+    except APITimeoutError as e:
+        return {"success": False, "transcript": "", "error": f"Request timeout: {e}"}
+    except APIError as e:
+        return {"success": False, "transcript": "", "error": f"API error: {e}"}
+    except Exception as e:
+        logger.error("OpenAI transcription failed: %s", e, exc_info=True)
+        return {"success": False, "transcript": "", "error": f"Transcription failed: {e}"}
+
+# ---------------------------------------------------------------------------
+# Public API
+# ---------------------------------------------------------------------------
 
 
 def transcribe_audio(file_path: str, model: Optional[str] = None) -> Dict[str, Any]:
     """
-    Transcribe an audio file using OpenAI's Whisper API.
+    Transcribe an audio file using the configured STT provider.
 
-    This function calls the OpenAI Audio Transcriptions endpoint directly
+    Provider priority:
-    (not via OpenRouter, since Whisper isn't available there).
+      1. User config (``stt.provider`` in config.yaml)
+      2. Auto-detect: local faster-whisper if available, else OpenAI API
 
     Args:
         file_path: Absolute path to the audio file to transcribe.
-        model:     Whisper model to use. Defaults to config or "whisper-1".
+        model:     Override the model. If None, uses config or provider default.
 
     Returns:
         dict with keys:
@@ -56,114 +235,31 @@ def transcribe_audio(file_path: str, model: Optional[str] = None) -> Dict[str, A
           - "transcript" (str): The transcribed text (empty on failure)
           - "error" (str, optional): Error message if success is False
     """
-    api_key = os.getenv("VOICE_TOOLS_OPENAI_KEY")
+    # Validate input
-    if not api_key:
+    error = _validate_audio_file(file_path)
-        return {
+    if error:
-            "success": False,
+        return error
-            "transcript": "",
-            "error": "VOICE_TOOLS_OPENAI_KEY not set",
-        }
 
-    audio_path = Path(file_path)
+    # Load config and determine provider
-    
+    stt_config = _load_stt_config()
-    # Validate file exists
+    provider = _get_provider(stt_config)
-    if not audio_path.exists():
-        return {
-            "success": False,
-            "transcript": "",
-            "error": f"Audio file not found: {file_path}",
-        }
-    
-    if not audio_path.is_file():
-        return {
-            "success": False,
-            "transcript": "",
-            "error": f"Path is not a file: {file_path}",
-        }
-    
-    # Validate file extension
-    if audio_path.suffix.lower() not in SUPPORTED_FORMATS:
-        return {
-            "success": False,
-            "transcript": "",
-            "error": f"Unsupported file format: {audio_path.suffix}. Supported formats: {', '.join(sorted(SUPPORTED_FORMATS))}",
-        }
-    
-    # Validate file size
-    try:
-        file_size = audio_path.stat().st_size
-        if file_size > MAX_FILE_SIZE:
-            return {
-                "success": False,
-                "transcript": "",
-                "error": f"File too large: {file_size / (1024*1024):.1f}MB (max {MAX_FILE_SIZE / (1024*1024)}MB)",
-            }
-    except OSError as e:
-        logger.error("Failed to get file size for %s: %s", file_path, e, exc_info=True)
-        return {
-            "success": False,
-            "transcript": "",
-            "error": f"Failed to access file: {e}",
-        }
 
-    # Use provided model, or fall back to default
+    if provider == "local":
-    if model is None:
+        local_cfg = stt_config.get("local", {})
-        model = DEFAULT_STT_MODEL
+        model_name = model or local_cfg.get("model", DEFAULT_LOCAL_MODEL)
+        return _transcribe_local(file_path, model_name)
 
-    try:
+    if provider == "openai":
-        from openai import OpenAI, APIError, APIConnectionError, APITimeoutError
+        openai_cfg = stt_config.get("openai", {})
+        model_name = model or openai_cfg.get("model", DEFAULT_OPENAI_MODEL)
+        return _transcribe_openai(file_path, model_name)
 
-        client = OpenAI(api_key=api_key, base_url="https://api.openai.com/v1")
+    # No provider available
-
+    return {
-        with open(file_path, "rb") as audio_file:
+        "success": False,
-            transcription = client.audio.transcriptions.create(
+        "transcript": "",
-                model=model,
+        "error": (
-                file=audio_file,
+            "No STT provider available. Install faster-whisper for free local "
-                response_format="text",
+            "transcription, or set VOICE_TOOLS_OPENAI_KEY for the OpenAI Whisper API."
-            )
+        ),
-
+    }
-        # The response is a plain string when response_format="text"
-        transcript_text = str(transcription).strip()
-
-        logger.info("Transcribed %s (%d chars)", audio_path.name, len(transcript_text))
-
-        return {
-            "success": True,
-            "transcript": transcript_text,
-        }
-
-    except PermissionError:
-        logger.error("Permission denied accessing file: %s", file_path, exc_info=True)
-        return {
-            "success": False,
-            "transcript": "",
-            "error": f"Permission denied: {file_path}",
-        }
-    except APIConnectionError as e:
-        logger.error("API connection error during transcription: %s", e, exc_info=True)
-        return {
-            "success": False,
-            "transcript": "",
-            "error": f"Connection error: {e}",
-        }
-    except APITimeoutError as e:
-        logger.error("API timeout during transcription: %s", e, exc_info=True)
-        return {
-            "success": False,
-            "transcript": "",
-            "error": f"Request timeout: {e}",
-        }
-    except APIError as e:
-        logger.error("OpenAI API error during transcription: %s", e, exc_info=True)
-        return {
-            "success": False,
-            "transcript": "",
-            "error": f"API error: {e}",
-        }
-    except Exception as e:
-        logger.error("Unexpected error during transcription: %s", e, exc_info=True)
-        return {
-            "success": False,
-            "transcript": "",
-            "error": f"Transcription failed: {e}",
-        }

website/docs/reference/environment-variables.md

@@ -131,6 +131,7 @@ All variables go in `~/.hermes/.env`. You can also set them with `hermes config
 | `HERMES_HUMAN_DELAY_MIN_MS` | Custom delay range minimum (ms) |
 | `HERMES_HUMAN_DELAY_MAX_MS` | Custom delay range maximum (ms) |
 | `HERMES_QUIET` | Suppress non-essential output (`true`/`false`) |
+| `HERMES_API_TIMEOUT` | LLM API call timeout in seconds (default: `900`) |
 | `HERMES_EXEC_ASK` | Enable execution approval prompts in gateway mode (`true`/`false`) |
 
 ## Session Settings

website/docs/user-guide/features/tts.md

@@ -67,23 +67,48 @@ Without ffmpeg, Edge TTS audio is sent as a regular audio file (playable, but sh
 If you want voice bubbles without installing ffmpeg, switch to the OpenAI or ElevenLabs provider.
 :::
 
-## Voice Message Transcription
+## Voice Message Transcription (STT)
 
-Voice messages sent on Telegram, Discord, WhatsApp, or Slack are automatically transcribed and injected as text into the conversation. The agent sees the transcript as normal text.
+Voice messages sent on Telegram, Discord, WhatsApp, Slack, or Signal are automatically transcribed and injected as text into the conversation. The agent sees the transcript as normal text.
 
-| Provider | Model | Quality | Cost |
+| Provider | Quality | Cost | API Key |
-|----------|-------|---------|------|
+|----------|---------|------|---------| 
-| **OpenAI Whisper** | `whisper-1` (default) | Good | Low |
+| **Local Whisper** (default) | Good | Free | None needed |
-| **OpenAI GPT-4o** | `gpt-4o-mini-transcribe` | Better | Medium |
+| **OpenAI Whisper API** | Good–Best | Paid | `VOICE_TOOLS_OPENAI_KEY` |
-| **OpenAI GPT-4o** | `gpt-4o-transcribe` | Best | Higher |
 
-Requires `VOICE_TOOLS_OPENAI_KEY` in `~/.hermes/.env`.
+:::info Zero Config
+Local transcription works out of the box — no API key needed. The `faster-whisper` model (~150 MB for `base`) is auto-downloaded on first voice message.
+:::
 
 ### Configuration
 
 ```yaml
 # In ~/.hermes/config.yaml
 stt:
-  enabled: true
+  provider: "local"           # "local" (free, faster-whisper) | "openai" (API)
-  model: "whisper-1"
+  local:
+    model: "base"             # tiny, base, small, medium, large-v3
+  openai:
+    model: "whisper-1"        # whisper-1, gpt-4o-mini-transcribe, gpt-4o-transcribe
 ```
+
+### Provider Details
+
+**Local (faster-whisper)** — Runs Whisper locally via [faster-whisper](https://github.com/SYSTRAN/faster-whisper). Uses CPU by default, GPU if available. Model sizes:
+
+| Model | Size | Speed | Quality |
+|-------|------|-------|---------|
+| `tiny` | ~75 MB | Fastest | Basic |
+| `base` | ~150 MB | Fast | Good (default) |
+| `small` | ~500 MB | Medium | Better |
+| `medium` | ~1.5 GB | Slower | Great |
+| `large-v3` | ~3 GB | Slowest | Best |
+
+**OpenAI API** — Requires `VOICE_TOOLS_OPENAI_KEY`. Supports `whisper-1`, `gpt-4o-mini-transcribe`, and `gpt-4o-transcribe`.
+
+### Fallback Behavior
+
+If your configured provider isn't available, Hermes automatically falls back:
+- **Local not installed** → Falls back to OpenAI API (if key is set)
+- **OpenAI key not set** → Falls back to local Whisper (if installed)
+- **Neither available** → Voice messages pass through with a note to the user