SRT conversion previously rejected otherwise valid word timestamps when a
start preceded the previous word's start. Clamp regressing starts to the
preceding nonempty word's start and extend ends only when necessary.
Preserve transcript order and the original response while continuing to
reject malformed timestamps. Document the adjustment and cover regressions,
cue boundaries, blank words, and invalid input.
Test Plan:
- python3 -B -m unittest -v: all eight tests passed.
- CLI conversion of a synthetic regressing response: passed.
- git diff --cached --check: passed.
- Actual recording verification blocked by unavailable 1Password auth.
Convert the normalized audio to mono 16 kHz MP3 at 64 kbps with
FFmpeg's libmp3lame encoder instead of uncompressed WAV. This reduces
request payload size before base64 encoding and submitting to OpenRouter.
Update README documentation accordingly.
Convert audio and video audio tracks to mono 16 kHz WAV with FFmpeg,
then submit them to OpenRouter's MAI-Transcribe-2 endpoint. Read the API
key from the environment and print the transcript to stdout for easy
redirection. Store request payloads in temporary files to avoid shell
argument size limits, and document dependencies and usage.
Test Plan:
- bash -n transcribe and shellcheck transcribe passed.
- All eight documented formats passed local FFmpeg conversion and mocked
API request/response checks, including WAV rate and channel validation.
- git diff --cached --check passed.
- No live API request was made.
ddidderr