Turn what people say into writing that still sounds like them
Dictation that streams as people talk, an AI that asks the right follow-up and then stops, and writing that keeps the user's words instead of replacing them. For journals, memoirs, notes, reflections, coaching, and anything else where the user's voice is the product.
Apps where people speak or write about their own life, work or ideas, and the result has to feel like theirs.
What we can build for you
Six things we can put in your product, each backed by work we have already shipped.
The four tests, for this
Where this kind of feature usually breaks, and what passing each test looks like.
How the two weeks go
€6,000, fixed. Written findings on day five; stop there and pay half. You keep everything either way.
- Days 1 to 4Run your real recordings and prompts through candidate speech and writing models. Measure quality, latency and cost per entry.
- Day 5Findings: the pipeline, the cost per user at launch, and where the writing drifts from the user's voice.
- Days 6 to 9The flow from voice to paragraph working in your app, streaming, with the free tier costed.
- Day 10Handover with an eval set built from the edits your users would ask for.
Where we have done it
Tell us what you are building.
Thirty minutes, no deck. You get a straight answer about whether we are the right people, and we say no when we are not.