Any device, any jack
Radios, radio headsets, intercoms, PA, consoles and handsets.
Feed your models
Any conversation on that line streams to your backend as it happens.
Two-way audio
Mic and speaker both. It listens to the line and talks back on it.
Display + USB-C
On-device display for battery, link and channel. Rechargeable belt-clip unit.
Your AI
Configurable endpoint, device behaviour tuned per use case from the console. Built to embed in the voice AI project you already have.
Puts anything with an audio jack onto your voice AI, starting with your radios
QuickComm Bridge Node v3 · SKU QC-BN-V3
Line total
$250
Volume pricing
A development kit for engineers, developers and builders. Ships pre-flashed and streams to the endpoint you configure from the console: point it at your own backend, run your own stack, and it slots into the voice AI project you already have, with no per-channel fees and no lock-in.
The same path on all three devices. Only where the microphone sits changes.
On an ear, on a desk, or on a radio line: someone presses to talk. Nothing is captured until they do, and the buffer keeps the first syllable from being clipped.
16 kHz mono, framed by the push-to-talk press, over Wi-Fi. Silence is never transmitted, so airtime and running costs stay low.
The audio arrives at your endpoint as clean, framed utterances, ready for whatever speech-to-text you run.
Your agent, your rules. Classify it, answer it, act on it: this part is your code, running on your infrastructure.
A task raised, an answer spoken back, a record kept: whatever you built it to do, fed by the device in real time.
Ships pre-flashed, provisioned with the QR card, configured for your use case from the console.
The stream endpoint is configurable. Take the audio at step 2 and run your own speech, models and logic on it.
PLUGS INTO ANY AUDIO JACK: not just walkie-talkies. Radios, radio headsets, handsets, intercoms, PA systems, desk phones, control-room consoles: if it has an audio port, the Bridge Node can sit on it.
TWO-WAY BY DESIGN: microphone and speaker both, so it listens to the line and talks back on it. Audio flows in both directions rather than being tapped one way.
ANY CONVERSATION, STRAIGHT TO YOUR STACK: whatever comes over that jack streams to the endpoint you configure, as clean push-to-talk-framed audio your models can work with.
WHATEVER YOU NEED IT TO BE: the audio lands on your backend as structured data. Transcription, translation, summarisation, alerting: anything you have built, fed by a jack.
NO RIP-AND-REPLACE: nothing gets replaced and nobody learns a new handset. The equipment your team already uses stays exactly as it is.
EVERYTHING THE OTHER TWO DO: same radio, codec, provisioning and console as the Earpiece and Table Top, so a mixed fleet behaves as one.
AN ON-DEVICE DISPLAY: battery, link and channel state are readable on the unit itself, so nobody opens a dashboard to find out whether it is working.
BELT-CLIP BODY: rechargeable over USB-C with its own microphone and speaker, so it works inline without disabling the host device's own audio.
BUILD YOUR OWN VOICE AI ON IT: off-the-shelf hardware you can make your own. Point the audio at your own backend, run your own models, and tune how the device behaves from the console. It is built to embed in the project you already have.
THE FASTEST WAY TO PILOT: the lowest-friction path from analogue audio to your voice AI, one jack at a time.
| Connector | 3.5 mm + 2.5 mm two-pin audio plug |
|---|---|
| Works with | Any device with a compatible audio port: two-way radios, radio headsets, handsets, intercoms, PA systems, desk phones, control-room consoles |
| Direction | Two-way: microphone in and speaker out on the same connection |
| Mode | Inline, so the host device's own audio path stays live |
| Push-to-talk | On-device PTT button plus host-side keying |
| Battery | Integrated rechargeable LiPo |
|---|---|
| Charging | USB-C |
| Power control | Physical power button |
| Buttons | Power button and QuickComm action button |
|---|---|
| Display | On-device display showing battery, link and channel state |
| Status | Indication LED |
| Audio out | Integrated speaker |
| Audio in | Integrated microphone |
| Form factor | Belt-clip dongle |
|---|---|
| Housing | Matte soft-touch polymer |
| Wi-Fi | 802.11 b/g/n, 2.4 GHz, integrated antenna |
|---|---|
| Bluetooth | Bluetooth 5.2 (BLE) |
| Stream transport | QuickComm udp-v1 push-to-talk wire protocol |
| Packet resilience | Self-describing packets, per-boot session keys, loss tolerant |
| Provisioning | QR-code pairing with MAC-based device identity |
| Microphone | Digital MEMS microphone |
|---|---|
| Audio codec | 24-bit ADC/DAC |
| Capture format | 16 kHz PCM, mono |
| Gating | Push-to-talk framed. Silence is never streamed |
| Pre-roll buffer | Yes. The first syllable of a transmission is never clipped |
| Edge processing | On-device voice activity detection and wake handling |
| Flash memory | 8 MB |
|---|---|
| Firmware updates | Over-the-air, staged rollouts from the fleet console |
| Remote management | Remote commands, health telemetry, offline detection |
| Backend | Yours: the stream endpoint is configurable from the console |
|---|---|
| Firmware | Ships pre-flashed; device behaviour is configured per use case from the console |
| Voice AI stack | Bring your own STT, LLM, wake word and TTS |
| On-device logic | 8 MB flash with on-device voice activity detection built in |
| Hardware platform | Standard, well-documented parts, with no proprietary ASIC to design around |
| Warranty | 12 months limited hardware warranty |
|---|---|
| Designed & engineered | Dubai, UAE (in5 Tech, Dubai Design District) |
| Manufacturer | Quickgen Technologies |
| IP status | Patent pending |
Custom hardware for any voice AI application
Every QuickComm Bridge Node is customisable hardware for any voice AI application. Point it at your own backend, run your own models, and tune how the device behaves for your use case from the console.
The stream endpoint is configurable. Point the device at your own infrastructure instead of ours and the audio goes where you send it.
Bring your own speech-to-text, models, wake word and text-to-speech. Nothing about the hardware locks you to a particular provider.
Every unit ships pre-flashed with QuickComm firmware. How it behaves for your use case is configured from the console, so nothing is ever reflashed in the field.
8 MB of flash and on-device voice activity detection keep capture clean before a single byte leaves the device.
Firmware updates ship through a staged over-the-air pipeline, with fleet health telemetry behind them.
Answered by the QuickComm engineering team.
Something not covered here? Ask us directly. We answer hardware questions before you buy, not after.
QC-EP-V3
$350
per unit
A wearable voice AI terminal for the assistant, agent or comms project you are building. Press to talk, so it listens when you ask it to and not before.
Best for: Team communication, meeting capture and personal assistant projects
QC-TT-V3
$200
per unit
Rechargeable desk or wall unit for room capture and note taking, with an on-device status display and a 1000 mAh battery so it keeps working away from a socket.
Best for: Control rooms, front desks, briefings and note taking
