Skip to content
AV production and rental

An NDI source with a real alpha channel, not a web page on a spare monitor

This page is for whoever already knows what a luma key is and why it matters. Almost every AI translation system ends at a full-screen web page you have to bring in on a capture card. This one does not.

What the others make you do

What this one does

  1. It outputs NDI with a genuine alpha channel

    The background is transparent in the frame itself. vMix, TriCaster, OBS or your switcher composite it over programme like any other input.

  2. Or full-screen HDMI with a chroma key

    When the room is not behind a switcher.

  3. The engine runs on your machine

    Video output is local. The internet carries audio and text, not your show, so the room does not depend on a browser tab staying open.

  4. It is driven from a physical button

    There is a local control API with a real on-air tally: Bitfocus Companion, plus Crestron, AMX or Q-SYS over TCP or HTTP.

Production control

Up to four simultaneous microphones

Each with its own colour, screen position and speaker name.

Captions hide without touching anything else

For an event running on the interaction layer alone. They still reach the audience phones.

The vocabulary is loaded before the event

Proper nouns, brands and acronyms pinned in advance — which is where accuracy is actually won: before you start, not during.

It fails clean, never frozen

If the connection drops the output fades to transparent. Never a stale caption on the big screen.

And for the end client

Video captions in SRT or VTT

Ready for next-day delivery.

AI minutes of the event

One more deliverable to invoice, with no extra work.

An audience report

How many followed, and in which languages.

Why this is channel, not just a customer

It does not change your workflow

It adds a line to your invoice. It comes out over NDI into what you already have.

Driven from the surface you already use

The Companion module’s command list is generated from the application’s own table, so a button never does something other than what it says.

Published price, direct purchase

Quote an event without waiting for a call back.

Your client preps their own event

Send them a signed room link and they write the questions and the votes themselves, days ahead. No document handed over the night before, and no sharing your password: that link opens that room and nothing else — not your billing, not your other rooms, not your other clients.

Let us talk about reselling

If you build congresses, this fits your quote as one more line. Write to us.

Recommended plan

Broadcast Multi-Mic

Four simultaneous microphones, a season’s worth of hours and priority support. Event Pro if you work with two.

See pricing

Frequently asked questions

Do I have to hand over my account so the client can prepare the questions?

No. There are two signed links and neither needs an account. The room link is for whoever organises the event: it opens the audience QR, the questions and votes, the AI minutes, and the results afterwards. The moderation link is narrower, for whoever holds the tablet on the day. Both work for one room only, both stop working the moment you release the code, and neither reaches your billing or your other rooms.

Is it real alpha or a chroma key?

Real alpha in the NDI frame. It is verified against the NDI runtime on every release: the panel plate measures opaque and the rest of the frame measures transparent.

Windows or Mac?

Both, and both are signed: the Mac build carries a Developer ID signature and is notarised by Apple, and the Windows installer has carried a Certum OV certificate since 1.7.31. SmartScreen now names the publisher instead of saying "unknown", though it may still warn until the installer accrues downloads — an OV certificate gives identity, not instant reputation.

What if the venue network profile is "Public"?

Windows blocks inbound mDNS discovery for every application, not just ours. The app detects it and warns you, which is more than anyone else does.

How much latency does it add?

The product target is under 1.5 seconds from audio to NDI out for untranslated captions, and under 2.5 seconds for a translated one. Measured, not estimated.

Other solutions

Run your next event free

One hour of full-featured captioning and translation, no expiry, no card — enough to prove it on your own rig before you pay.