Configurable timeouts and minor config fixes

Fixes on record

Merged to main. A stamp counts the issues a fix is linked to.

• #1194 fix: handle YAML null values in session reset policy + configurable API timeout

  merged to main

  files: agent/context_compressor.py, gateway/config.py, hermes_cli/config.py, pyproject.toml, run_agent.py, tests/agent/test_context_compressor.py, tests/tools/test_transcription.py, tools/transcription_tools.py, website/docs/reference/environment-variables.md, website/docs/user-guide/features/tts.md

  Show the diff

  • agent/context_compressor.py

    @@ -132,7 +132,11 @@ def _generate_summary(self, turns_to_summarize: List[Dict[str, Any]]) -> Optiona
                 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 @@ def to_dict(self) -> Dict[str, Any]:
         
         @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),
    -            idle_minutes=data.get("idle_minutes", 1440),
    +            at_hour=at_hour if at_hour is not None else 4,
    +            idle_minutes=idle_minutes if idle_minutes is not None else 1440,
             )
     
     

  • hermes_cli/config.py

    @@ -194,8 +194,13 @@ def ensure_hermes_home():
         },
         
         "stt": {
    -        "enabled": True,
    -        "model": "whisper-1",
    +        "provider": "local",  # "local" (free, faster-whisper) | "openai" (Whisper API)
    +        "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 @@ def _build_api_kwargs(self, api_messages: list) -> dict:
                 "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 @@ def test_none_content_in_system_message_compress(self):
             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.
    -Used by the messaging gateway to automatically transcribe voice messages
    -sent by users on Telegram, Discord, WhatsApp, and Slack.
    +Provides speech-to-text transcription with two providers:
    +
    +  - **local** (default, free) — faster-whisper running locally, no API key needed.
    +    Auto-downloads the model (~150 MB for ``base``) on first use.
    +  - **openai** — OpenAI Whisper API, requires ``VOICE_TOOLS_OPENAI_KEY``.
     
    -Supported models:
    -  - whisper-1        (cheapest, good quality)
    -  - gpt-4o-mini-transcribe  (better quality, higher cost)
    -  - 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")
    @@ -28,142 +29,237 @@
     
     logger = logging.getLogger(__name__)
     
    +# ---------------------------------------------------------------------------
    +# Optional imports — graceful degradation
    +# ---------------------------------------------------------------------------
    +
    +try:
    +    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 STT model -- cheapest and widely available
    -DEFAULT_STT_MODEL = "whisper-1"
    +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)
    -MAX_FILE_SIZE = 25 * 1024 * 1024
    +# Singleton for the local model — loaded once, reused across calls
    +_local_model: Optional["WhisperModel"] = None
    +_local_model_name: Optional[str] = None
     
    +# ---------------------------------------------------------------------------
    +# Config helpers
    +# ---------------------------------------------------------------------------
     
    -def transcribe_audio(file_path: str, model: Optional[str] = None) -> Dict[str, Any]:
    -    """
    -    Transcribe an audio file using OpenAI's Whisper API.
     
    -    This function calls the OpenAI Audio Transcriptions endpoint directly
    -    (not via OpenRouter, since Whisper isn't available there).
    +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 {}
     
    -    Args:
    -        file_path: Absolute path to the audio file to transcribe.
    -        model:     Whisper model to use. Defaults to config or "whisper-1".
     
    -    Returns:
    -        dict with keys:
    -          - "success" (bool): Whether transcription succeeded
    -          - "transcript" (str): The transcribed text (empty on failure)
    -          - "error" (str, optional): Error message if success is False
    +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")
         """
    -    api_key = [redacted:secret-assignment]"VOICE_TOOLS_OPENAI_KEY")
    -    if not api_key:
    -        return {
    -            "success": False,
    -            "transcript": "",
    -            "error": "VOICE_TOOLS_OPENAI_KEY not set",
    -        }
    +    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)
    -    
    -    # Validate file exists
    +
         if not audio_path.exists():
    -        return {
    -            "success": False,
    -            "transcript": "",
    -            "error": f"Audio file not found: {file_path}",
    -        }
    -    
    +        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
    +        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 file format: {audio_path.suffix}. Supported formats: {', '.join(sorted(SUPPORTED_FORMATS))}",
    +            "error": f"Unsupported format: {audio_path.suffix}. Supported: {', '.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)",
    +                "error": f"File too large: {file_size / (1024*1024):.1f}MB (max {MAX_FILE_SIZE / (1024*1024):.0f}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}",
    -        }
    +        return {"success": False, "transcript": "", "error": f"Failed to access file: {e}"}
    +
    +    return None
    +
    +# ---------------------------------------------------------------------------
    +# Provider: local (faster-whisper)
    +# ---------------------------------------------------------------------------
    +
     
    -    # Use provided model, or fall back to default
    -    if model is None:
    -        model = DEFAULT_STT_MODEL
    +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:
    -        from openai import OpenAI, APIError, APIConnectionError, APITimeoutError
    +        # 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 = [redacted:secret-assignment]"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=[redacted:secret-assignment] base_url="https://api.openai.com/v1")
     
             with open(file_path, "rb") as audio_file:
                 transcription = client.audio.transcriptions.create(
    -                model=model,
    +                model=model_name,
                     file=audio_file,
                     response_format="text",
                 )
     
    -        # The response is a plain string when 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))
     
    -        logger.info("Transcribed %s (%d chars)", audio_path.name, len(transcript_text))
    -
    -        return {
    -            "success": True,
    -            "transcript": 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}",
    -        }
    +        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}",
    -        }
    +        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}",
    -        }
    +        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}",
    -        }
    +        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}",
    -        }
    +        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 the configured STT provider.
    +
    +    Provider priority:
    +      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:     Override the model. If None, uses config or provider default.
    +
    +    Returns:
    +        dict with keys:
    +          - "success" (bool): Whether transcription succeeded
    +          - "transcript" (str): The transcribed text (empty on failure)
    +          - "error" (str, optional): Error message if success is False
    +    """
    +    # Validate input
    +    error = _validate_audio_file(file_path)
    +    if error:
    +        return error
    +
    +    # Load config and determine provider
    +    stt_config = _load_stt_config()
    +    provider = _get_provider(stt_config)
    +
    +    if provider == "local":
    +        local_cfg = stt_config.get("local", {})
    +        model_name = model or local_cfg.get("model", DEFAULT_LOCAL_MODEL)
    +        return _transcribe_local(file_path, model_name)
    +
    +    if provider == "openai":
    +        openai_cfg = stt_config.get("openai", {})
    +        model_name = model or openai_cfg.get("model", DEFAULT_OPENAI_MODEL)
    +        return _transcribe_openai(file_path, model_name)
    +
    +    # No provider available
    +    return {
    +        "success": False,
    +        "transcript": "",
    +        "error": (
    +            "No STT provider available. Install faster-whisper for free local "
    +            "transcription, or set VOICE_TOOLS_OPENAI_KEY for the OpenAI Whisper API."
    +        ),
    +    }

  • 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 |
    -|----------|-------|---------|------|
    -| **OpenAI Whisper** | `whisper-1` (default) | Good | Low |
    -| **OpenAI GPT-4o** | `gpt-4o-mini-transcribe` | Better | Medium |
    -| **OpenAI GPT-4o** | `gpt-4o-transcribe` | Best | Higher |
    +| Provider | Quality | Cost | API Key |
    +|----------|---------|------|---------| 
    +| **Local Whisper** (default) | Good | Free | None needed |
    +| **OpenAI Whisper API** | Good–Best | Paid | `VOICE_TOOLS_OPENAI_KEY` |
     
    -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
    -  model: "whisper-1"
    +  provider: "local"           # "local" (free, faster-whisper) | "openai" (API)
    +  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