python-common-code/README.md

仮想環境

python -m venv venv
.\venv\Scripts\activate

curl https://api.openai.com/v1/audio/transcriptions
-H "Authorization: Bearer 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"
-F "file=@part_001.m4a"
-F "model=gpt-4o-transcribe"
-F "response_format=text"
-F "language=ja"
-o part_001.txt

ffmpeg -i voice.m4a -f segment -segment_time 600 -c copy part_%03d.m4a

フォーマットを揃える