API key supports for backends like oMLX & README improvement for uv

README.md

@@ -106,6 +106,17 @@ bash swift/build.sh
 uv sync --extra all
 ```
 
+When installed from source, the `ownscribe` command lives inside the project's
+virtual environment, so run it with `uv run` from the repo directory:
+
+```bash
+uv run ownscribe          # equivalent to the bare `ownscribe` used below
+```
+
+Alternatively, activate the environment once (`source .venv/bin/activate`) and
+then call `ownscribe` directly. The examples in [Usage](#usage) use the bare
+`ownscribe` form, which works after activation or via `uvx ownscribe`.
+
 ## Usage
 
 ### Record, transcribe, and summarize a meeting
@@ -147,14 +158,16 @@ ownscribe --silence-timeout 0                 # disable silence auto-stop
 ownscribe devices                  # list audio devices (uses native CoreAudio when available)
 ownscribe apps                     # list running apps with PIDs for use with --pid
 ownscribe warmup                   # prefetch WhisperX/pyannote models before a meeting
-ownscribe transcribe recording.wav # transcribe an audio file (saves alongside the input)
+ownscribe transcribe recording.wav # transcribe an audio or video file: wav/mp3/mp4/mov/mkv (saved alongside)
 ownscribe summarize transcript.md  # summarize a transcript (saves alongside the input)
-ownscribe resume ./2026-02-20_1736 # resume a failed/partial pipeline in a directory
+ownscribe resume ./2026-02-20_1736 # resume a partial run, or process a folder's audio/video recording
 ownscribe ask "question"           # search your meetings with a natural-language question
 ownscribe config                   # open config file in $EDITOR
 ownscribe cleanup                  # remove ownscribe data from disk
 ```
 
+> **Video files work too.** Anywhere ownscribe accepts an audio file it also accepts a video container (mp4, mov, mkv, m4v) — it extracts the audio track via ffmpeg. To turn a recording into full notes, drop it in a folder and run `ownscribe resume ./that-folder/` (transcript + summary); use `ownscribe transcribe meeting.mp4` for a transcript only.
+
 Use `warmup` ahead of time to avoid first-run model download delays while recording:
 
 ```bash
@@ -209,6 +222,7 @@ enabled = true
 backend = "local"         # "local" (built-in, no server needed), "ollama", or "openai"
 model = "phi-4-mini"      # local: "phi-4-mini", path to GGUF, or hf:owner/repo/file.gguf; ollama/openai: model name
 # host = "http://localhost:11434"  # only for ollama/openai backends
+# api_key = ""            # only for openai backend; required by servers like oMLX (or set OPENAI_API_KEY)
 # template = "meeting"    # "meeting", "lecture", "brief", or a custom name
 # context_size = 0        # 0 = auto-detect from model; set manually for OpenAI-compatible backends
 
@@ -223,7 +237,7 @@ format = "markdown"       # "markdown" or "json"
 keep_recording = true     # false = auto-delete WAV after transcription
 ```
 
-**Precedence:** CLI flags > environment variables (`HF_TOKEN`, `OLLAMA_HOST`) > config file > defaults.
+**Precedence:** CLI flags > environment variables (`HF_TOKEN`, `OLLAMA_HOST`, `OPENAI_API_KEY`) > config file > defaults.
 
 ## Summarization Templates
 

src/ownscribe/config.py

@@ -38,6 +38,7 @@
 backend = "local"         # "local" (built-in, no server needed), "ollama", or "openai"
 model = "phi-4-mini"      # local: "phi-4-mini", path to GGUF, or hf:owner/repo/file.gguf; ollama/openai: model name
 # host = "http://localhost:11434"  # only for ollama/openai backends
+# api_key = ""            # only for openai backend; required by servers like oMLX (or set OPENAI_API_KEY)
 # template = "meeting"    # built-in: "meeting", "lecture", or "brief"
 # context_size = 0        # 0 = auto-detect from model; set manually for OpenAI-compatible backends
 
@@ -87,6 +88,7 @@ class SummarizationConfig:
     backend: str = "local"
     model: str = "phi-4-mini"
     host: str = "http://localhost:11434"
+    api_key: str = ""
     template: str = ""
     context_size: int = 0
 
@@ -132,6 +134,8 @@ def load(cls) -> Config:
             config.diarization.hf_token = hf_token
         if ollama_host := os.environ.get("OLLAMA_HOST"):
             config.summarization.host = ollama_host
+        if api_key := os.environ.get("OPENAI_API_KEY"):
+            config.summarization.api_key = api_key
 
         return config
 

src/ownscribe/pipeline.py

@@ -508,15 +508,18 @@ def _do_transcribe_and_summarize(
 
 
 _AUDIO_EXTENSIONS = {".wav", ".mp3", ".m4a", ".flac", ".ogg", ".webm"}
+# Video containers whose audio track ffmpeg/WhisperX can decode (e.g. meeting recordings).
+_VIDEO_EXTENSIONS = {".mp4", ".m4v", ".mov", ".mkv"}
+_MEDIA_EXTENSIONS = _AUDIO_EXTENSIONS | _VIDEO_EXTENSIONS
 
 
 def _find_audio(directory: Path) -> Path | None:
-    """Find an audio file in directory, preferring 'recording.wav'."""
+    """Find an audio or video file in directory, preferring 'recording.wav'."""
     recording = directory / "recording.wav"
     if recording.exists():
         return recording
     for f in directory.iterdir():
-        if f.is_file() and f.suffix.lower() in _AUDIO_EXTENSIONS:
+        if f.is_file() and f.suffix.lower() in _MEDIA_EXTENSIONS:
             return f
     return None
 

src/ownscribe/summarization/openai_summarizer.py

@@ -15,11 +15,13 @@ class OpenAISummarizer(Summarizer):
     def __init__(self, config: SummarizationConfig, templates: dict | None = None) -> None:
         self._config = config
         self._templates = templates or {}
-        # For local servers, no API key needed — use a dummy
         base_url = config.host
         if not base_url.endswith("/v1"):
             base_url = base_url.rstrip("/") + "/v1"
-        self._client = openai.OpenAI(base_url=base_url, api_key="not-needed")
+        # Most local servers ignore the key; servers that require auth (e.g. oMLX)
+        # read it from config.api_key or the OPENAI_API_KEY env var.
+        api_key = config.api_key or "not-needed"
+        self._client = openai.OpenAI(base_url=base_url, api_key=api_key)
 
     def chat(
         self, system_prompt: str, user_prompt: str,

tests/test_find_audio.py

@@ -0,0 +1,36 @@
+"""Tests for media-file discovery in _find_audio (audio + video containers)."""
+
+from __future__ import annotations
+
+from ownscribe.pipeline import _find_audio
+
+
+def _touch(directory, *names):
+    for name in names:
+        (directory / name).write_bytes(b"")
+
+
+class TestFindAudioVideo:
+    def test_finds_mp4_when_no_recording_wav(self, tmp_path):
+        _touch(tmp_path, "meeting.mp4")
+        assert _find_audio(tmp_path) == tmp_path / "meeting.mp4"
+
+    def test_finds_mov(self, tmp_path):
+        _touch(tmp_path, "meeting.mov")
+        assert _find_audio(tmp_path) == tmp_path / "meeting.mov"
+
+    def test_finds_mkv(self, tmp_path):
+        _touch(tmp_path, "meeting.mkv")
+        assert _find_audio(tmp_path) == tmp_path / "meeting.mkv"
+
+    def test_prefers_recording_wav_over_video(self, tmp_path):
+        _touch(tmp_path, "meeting.mp4", "recording.wav")
+        assert _find_audio(tmp_path) == tmp_path / "recording.wav"
+
+    def test_case_insensitive_extension(self, tmp_path):
+        _touch(tmp_path, "Meeting.MP4")
+        assert _find_audio(tmp_path) == tmp_path / "Meeting.MP4"
+
+    def test_ignores_unrelated_files(self, tmp_path):
+        _touch(tmp_path, "notes.txt", "slides.pdf")
+        assert _find_audio(tmp_path) is None