The parts you don't see, built in-house.

Our products depend on infrastructure we run ourselves rather than rent. These are the stages we've already built and measured — not client case studies, and not promises. The numbers are measured, not estimated.

Self-hosted speech recognition and clean-up cluster

The inference backend behind Voicelna, built and operated in-house rather than rented from a speech API. Streaming recognition tuned for sentences that switch language mid-clause, followed by a language-model pass that turns a raw transcript into text worth sending.

Measured behaviour: 144–149 ms server-side from end-of-speech to raw text on a single stream, 8–9 concurrent streams held under 500 ms, and a documented capacity model for scaling past that.

Running our own inference is also what makes the privacy claim real: audio goes to our cluster, not to a third party's API.

  • Streaming ASR
  • LLM post-processing
  • GPU capacity
  • Powers Voicelna

AI search visibility, measured on our own site

Being findable by an AI assistant is not the same problem as ranking in a search engine. We built a way to measure it — what the AI crawlers can actually reach, and what they can actually assert — and applied it to this site first.

What that meant in practice: fifteen AI crawlers named explicitly rather than left to infer permission, a structured-data graph describing the organisation and its products, push-based submission so changes are known in hours rather than weeks, and — the part that actually matters — factual content specific enough for a model to cite.

That last point is the whole lesson. Adjectives cannot be cited. Verifiable statements can. Most sites fail here, and no amount of technical work compensates.

  • Crawler access
  • Structured data
  • IndexNow
  • Measured not asserted

We occasionally take on applied-AI work for other teams when it overlaps with what we're already building. If something here resembles your problem, describe yours by email.

Tell us what you're trying to build.

A product idea, an AI system you need in production, or something in between. We'll tell you honestly if we're the right studio for it.

hello@aivmelna.com

Write in English or Chinese. Tell us what the system has to do and what you're working with — that's enough for a first reply.