QUICK NAVIGATION

Find a page.

Use the arrow keys to choose a result, Enter to open it, or Escape to close.

← All case studies

Steve's Computers · Repair shop · Voice ML microservice

Steve's Computers

I built a service that identifies which technician is speaking on a repair shop's shared phone line and reports its confidence.

Delivered with a five-star review. Third engagement with this client since.

What the business needed

Four technicians share one phone line. The shop wanted transcripts tagged by who was actually speaking, without keeping the audio.

What I worked on

  1. 01Built a way to recognize enrolled technicians on the shop's shared phone line and report how confident the match is
  2. 02Handled the phone system's audio format and added a way to improve matching with new examples
  3. 03Deleted recordings after creating the voice representations used for matching
  4. 04Published a reusable version of the code

What the project delivered

9090% confidence for one recorded speaker matchThe system's confidence in that match, not an overall accuracy rate.
1day to deliveryquoted four to five

NEXT STEP

Have a similar problem?

If you're working on something similar, here's how I can help. AI phone assistants

Have a project in mind?

Tell me what you'd like to build or improve. We can talk through what you need and whether I can help.

Book a call with mepatrick@epiphanydynamics.ai