DField SolutionsMérnöki stúdió · Budapest
Loading · Töltődik
Skip to content

SimulSpeak

Real-time translated calls in 24 languages · they hear their language, in your voice.

SimulSpeak translates live calls as you speak: you talk in your language, the other side hears theirs, in your cloned voice, with sub-second latency. On the web, via a room link, over a normal phone call, or on one phone in person - the other side installs nothing.

Listen
CASE STUDY · 2026

SimulSpeak. Real-time translated calls in 24 languages.

SimulSpeak translates live calls as you speak: you talk in your language, the other side hears theirs, in your cloned voice, with sub-second latency. On the web, via a room link, over a normal phone call, or on one phone in person - the other side installs nothing.

YEAR·2026STACK·Next.js · TypeScript · WebRTCLIVE·simulspeak.com
Anonymous client

SimulSpeak shipped on time, with the brand and the engineering quality matching what we asked for. Iteration was tight · we kept the cadence weekly and the team responded same-day on production questions.

Anonymous·SimulSpeak · client (under NDA)UNDER NDA
2026Shipped year
3Disciplines
5Stack items
100%Brand match

What's on screen

Frame breakdown
SimulSpeak · real-time translated calls in your own voice
  • 01User surface

    The whole experience the user sees

    This frame shows the live product: real-time translated calls in 24 languages · they hear their language, in your voice. Every component is ours · scope, design, code, deploy.

  • 02Stack behind the screen

    What's powering it: Next.js, TypeScript, WebRTC

    5 stack components run behind this frame · Next.js, TypeScript, WebRTC drive the visible UI; the rest sit in the data layer. All studio-owned.

  • 03What we shipped

    Live voice translation in 24 languages

    Talk to anyone without sharing a language

  • 04Status

    Live · simulspeak.com.

    This isn't a demo · real traffic flows through it, with monitoring + weekly fixes attached.

How it shipped

Timeline
  • 01 · BRIEF

    Scoped on a 30-min call.

    Language barriers stall deals and conversations

  • 02 · ARCHITECTURE

    Stack decisions before any code.

    Decision doc captured the data flow, Next.js, TypeScript, WebRTC, Voice AI role split, and the failure modes we'd handle in v1 vs defer. Cross-service boundaries (where AI ends and the web app begins) were drawn here so neither side leaked into the other later.

  • 02 · BUILD

    Engineering in our studio, no offshore.

    Live voice translation in 24 languages

  • 04 · POLISH

    Performance, accessibility, and observability.

    PSI / a11y / coverage budgets enforced as launch gates. Logging + metrics wired before cut-over · the team can answer 'is it working?' from a dashboard, not a Slack thread. Threat-model checklist signed off before traffic hits the box.

  • 03 · SHIP

    Live, observable, handed back.

    Talk to anyone without sharing a language

What shipped

04
  • 01Build

    Live voice translation in 24 languages

    Talk to anyone without sharing a language

  • 02Stack

    Cloned voice · sounds like you

    You speak every language in your own voice

  • 03UX

    Sub-second latency

    The other side just answers the phone

  • 04Ops

    Web, room link, phone call, in-person mode

    SimulSpeak translates live calls as you speak: you talk in your language, the other side hears theirs, in your cloned voice, with sub-second latency. On the web, via a room link, over a normal phone call, or on one phone in person - the other side installs nothing.

See the live work behind this case studysimulspeak.com
2026YEAR
03SERVICES
05TECHNOLOGIES
LIVESTATUS

THE PROBLEM

  • Language barriers stall deals and conversations
  • Interpreters are expensive; translator apps are clunky and robotic
  • A foreign customer won't install an app to take a call

WHAT THE CLIENT GOT

  • Talk to anyone without sharing a language
  • You speak every language in your own voice
  • The other side just answers the phone

WHAT WE DELIVERED

  • +Live voice translation in 24 languages
  • +Cloned voice · sounds like you
  • +Sub-second latency
  • +Web, room link, phone call, in-person mode

STACK

  • Next.js
  • TypeScript
  • WebRTC
  • Voice AI
  • Twilio

// try it yourself

This work is live. Open it and try it for yourself.

Previous projectautoszoftver.hu Next projectJuriSafe
talk to us

Like what you see? Let's build yours.

Short email or a 30-min call · 24h reply.

Start a project