recording-transcription

Overview

• The audio is a file the user handed over (phone, voice recorder, on-site capture) or text draft.
• The result goes to memorb-ingest for the impact scan.

The premise

A phone recording is the single-microphone problem in another guise: whoever sits near the phone comes through clearly, whoever sits far away may be muffled or talked over. Do not assume the clear parts are the user speaking. Work out the speaker from the content — question and answer pairs, forms of address, who owns the topic.

For a one-on-one with a manager or a colleague, wording accuracy and timestamps matter more than they do for an ordinary meeting — anything touching commitments, numbers, or dates should be marked uncertain rather than smoothed over by the model into something that merely reads well.

Known environment limits (measured 2026-07-12 — read this before you start)

• This sandbox's network allowlist covers package-ecosystem domains such as pypi.org and github.com, but not huggingface.co. pip install faster-whisper works fine; at run time it wants to fetch model weights from HF and that connection will always fail here. The check command detects this up front, so you do not discover it halfway through a background job.
• Any folder mounted from the real machine is append/overwrite-only — nothing can be deleted. That covers the vault and the outputs scratch folder alike: rm on a file you have already written returns Operation not permitted (the Write/Edit tools carry the same restriction). The only paths you can freely create and delete in are the sandbox's own, e.g. /tmp. So any intermediate file that is supposed to be cleaned up afterwards belongs in /tmp, never in the vault or in outputs — put it there and it becomes garbage you can never remove. The vault holds only what is meant to be permanent: the transcript, the analysis, and (if the user confirms they want it kept) the original audio.
• Together these two facts dictate the paths below: intermediate work files always go to /tmp; only the final transcript, analysis, and audio ever reach the vault.