From 45cab5c38dc089935416a89d36b461d9127094ac Mon Sep 17 00:00:00 2001
From: Craig Jennings <c@cjennings.net>
Date: Tue, 4 Nov 2025 14:35:50 -0600
Subject: feat: Add complete async audio transcription workflow
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Implemented full transcription system with local Whisper and OpenAI API
support. Includes comprehensive test suite (60 tests) and reorganized
keybindings for better discoverability.

Features:
- Async transcription (non-blocking workflow)
- Desktop notifications (started/complete/error)
- Output: audio.txt (transcript) + audio.log (process logs)
- Modeline integration showing active transcription count
- Dired integration (press T on audio files)
- Process management and tracking

Scripts:
- install-whisper.sh: Install Whisper via AUR or pip
- uninstall-whisper.sh: Clean removal with cache cleanup
- local-whisper: Offline transcription using installed Whisper
- oai-transcribe: Cloud transcription via OpenAI API

Tests (60 passing):
- Audio file detection (16 tests)
- Path generation logic (11 tests)
- Log cleanup behavior (5 tests)
- Duration formatting (9 tests)
- Active counter & modeline (11 tests)
- Integration workflows (8 tests)

Keybindings:
- Reorganized gcal to C-; g submenu (s/t/r/c)
- Added C-; t transcription submenu (t/b/k)
- Dired: T to transcribe file at point

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
---
 scripts/oai-transcribe | 45 +++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 45 insertions(+)
 create mode 100755 scripts/oai-transcribe

(limited to 'scripts/oai-transcribe')

diff --git a/scripts/oai-transcribe b/scripts/oai-transcribe
new file mode 100755
index 00000000..f64a8122
--- /dev/null
+++ b/scripts/oai-transcribe
@@ -0,0 +1,45 @@
+#!/usr/bin/env bash
+# oai-transcribe - Transcribe audio files using OpenAI Whisper API
+# Usage: oai-transcribe <audio-file> [language]
+#
+# Requires: OPENAI_API_KEY environment variable
+# Language: en, es, fr, etc. (default: en)
+
+set -euo pipefail
+
+# Parse arguments
+AUDIO="${1:-}"
+LANG="${2:-en}"
+
+# Validate arguments
+if [[ -z "$AUDIO" ]]; then
+  echo "Usage: oai-transcribe <audio-file> [language]" >&2
+  echo "Example: oai-transcribe meeting.m4a en" >&2
+  exit 1
+fi
+
+if [[ ! -f "$AUDIO" ]]; then
+  echo "Error: Audio file not found: $AUDIO" >&2
+  exit 1
+fi
+
+# Check API key is set
+if [[ -z "${OPENAI_API_KEY:-}" ]]; then
+  echo "Error: OPENAI_API_KEY environment variable not set" >&2
+  echo "Set with: export OPENAI_API_KEY='sk-...'" >&2
+  exit 1
+fi
+
+# Check curl is available
+if ! command -v curl &> /dev/null; then
+  echo "Error: curl command not found" >&2
+  exit 1
+fi
+
+# Call OpenAI API
+curl -s -X POST "https://api.openai.com/v1/audio/transcriptions" \
+  -H "Authorization: Bearer $OPENAI_API_KEY" \
+  -F "model=whisper-1" \
+  -F "response_format=text" \
+  -F "language=${LANG}" \
+  -F "file=@${AUDIO}"
-- 
cgit v1.2.3