Valentina Akpan: Founder of Rellatech, providing administrative and operations support to executives, founders, business owners and teams. Her background combines technical support, customer success, administration and operations.
·
The brief was simple. Fourteen months of weekly coaching clinics were sitting inside Otter.ai, transcribed but unusable. They needed to be in one place, ordered newest to oldest, ready to be searched, referenced, and reused inside the business.
Below is what the finished system looks like, the numbers from the documented run, and why the retrieval problem matters.
The Outcome
A single Word document, ordered newest to oldest, containing every coaching session in clean, readable form. Building the tool and running it for the first time took under two hours of my time in total. The run itself, from login to delivered file, took around ten minutes, unattended. No copy and paste, no manual exports, no cleanup afterwards. The figures below are from the documented run shown in the screenshot further down.
49
Transcripts compiled
2.19M
Characters captured
10 min
Unattended runtime
< 2 hrs
Build and first run
Why It Mattered
Every clinic call had decisions, frameworks, and client breakthroughs in it. Sitting one by one inside Otter.ai, that material was hard to get back to. Nobody was going to scroll through 49 separate recordings to find the one quote, the one explanation, or the one piece of advice a client needed to hear.
In a single document, that same content becomes a reference the business can use. Searchable in seconds and quotable inside emails, proposals, and content. Easy to hand off to a team member, an editor, or a future ghostwriter.
Material stored one recording at a time is hard to search. The problem was retrieval, not the content.
What Got Built
The final piece is a small Streamlit app that lives on the desktop. The owner enters their Otter.ai login, the app fetches every transcript in order, and a polished Word document lands on the desktop. That is the entire user experience.
Underneath, Python is doing the heavy lifting through the open-source otterai-py library and python-docx. The result is a tool the business now owns and can run again at any time with its own Otter.ai login, with no manual export steps and no extra subscription attached.
The Bigger Lesson
This was never really about Otter.ai. It was about a pattern that shows up in almost every knowledge-driven business. There is a lot of useful material sitting inside the tools you already pay for. Recordings, customer notes, support emails, sales calls. Most of it is locked behind interfaces that were never designed for retrieval.
A clean extraction, the right format and a small piece of automation, and the same content becomes something the business can search and reuse. That is the work I love doing.
Need help with similar work?
Tell me which responsibilities or processes need attention, who is involved and any upcoming deadlines. I provide administrative and operations support, including the connected technical work within our agreed scope.
Book a free call