About the 25MB size limit

About the 25MB size limit: I struggled to set up this project for a long time, only to find out that there was a size limit of 25MB when I ran it myself. So why didn't I just call the official API? I thought your project would automatically split and upload the audio, and then merge the results (to get the best performance, we suggest that you avoid breaking the audio up mid-sentence as this may cause some context to be lost). But the result was disappointing. I had to handle the process myself.

The issue names no files, tests, or entry points; start by locating the audio upload and transcription flow and confirming how the 25MB limit is enforced. Clarify the expected splitting and merging behavior with maintainers before implementation, since the issue does not define acceptance criteria.

索引モデルが issue の本文から書いたものです。