How TellAcross works

From first word to
translated audio in under 1.5s

Four simple steps. No setup friction. Context-aware translation with industry modes — just a conversation in any language.

01

Create or join a room

No downloads. No plugins. No friction.

Sign up in under 30 seconds and create a private room with one click. Share the 6-character room code — or a direct link — with anyone in the world. They open a browser and join instantly. No software to install, no account required for guests.

  • Rooms are private and ephemeral by default
  • Guests join via link — no sign-up needed
  • Works on Chrome, Edge, Safari, and Firefox
  • Mobile and desktop fully supported

Room created

VB-X7K2

Share this code or link with your caller

02

Pick your languages — or let it detect

60+ languages. One dropdown. Or zero setup.

Each participant selects the language they speak and the language they want to hear — independently. Or use auto-detect: TellAcross identifies what language you're speaking automatically and routes translation accordingly. Switch languages mid-call and it keeps up without interruption.

  • Each participant sets their own language independently
  • Auto language detection — no manual setup needed
  • 60+ languages including all major Indic scripts
  • Accent and dialect awareness built in
  • Language can be changed mid-call without interruption

Participant language setup

🇮🇳ArjunHindi → German
🇩🇪KlausGerman → Hindi
🇧🇷SofiaPortuguese → English
03

Speak naturally

TellAcross handles everything in real time.

The moment you start talking, TellAcross captures your voice, transcribes it with high accuracy, translates it into your partner's language, and plays it back — all in under 1.5 seconds. You just have a conversation. The technology disappears.

  • Sub-1.5s end-to-end latency from speech to translated audio
  • Neural text-to-speech preserves tone and natural flow
  • Best-in-class translation accuracy across all language pairs
  • Filler words and false starts cleaned automatically
A

Arjun spoke in Hindi

हमें अगले हफ्ते की डिलीवरी की तारीख बदलनी होगी।
🔊 Klaus hears: "We'll need to move the delivery date to next week."
Translated in 1.2s
04

Review the full transcript

Everything captured. Nothing missed.

Every word spoken in every language is logged in the scrollable transcript panel with speaker attribution, timestamps, and original + translated text side by side. After the call, export to PDF or copy the full log for meeting notes, auditing, or review.

  • Full dual-language transcript visible live during the call
  • Speaker names and timestamps on every message
  • Export to PDF or plain text after the call (Pro)
  • Transcript stored for 30 days with Pro plan
Arjun09:03

हमें डिलीवरी डेट बदलनी होगी।

→ We need to change the delivery date.

Klaus09:04

Das ist kein Problem, wann passt es?

→ That's no problem — when works?

Arjun09:04

शुक्रवार सबसे बेहतर होगा।

→ Friday would be best.

✈️ No call needed

Quick Translate — for face-to-face situations

Not every conversation happens over a call. Quick Translate lets you translate in real time with someone standing right in front of you — no room code, no second device. One person speaks, the other hears their language, right on the same screen.

  • Airports — immigration questions, boarding gate confusion, lost luggage
  • Hospitals — describe symptoms, understand diagnoses, read discharge notes
  • Courts & legal offices — real-time interpretation without scheduling
  • Hotels & restaurants — order food, ask directions, handle check-in issues
  • Auto language detection — just speak, TellAcross figures out the language
Try Quick Translate free →
Quick Translate — live

🇮🇳 Hindi detected

मुझे अस्पताल जाना है।

→ I need to go to the hospital.

🇯🇵 Japanese detected

右に曲がってください。

→ Please turn right.

No setup · Auto-detects language · Works offline-ready

Why this is hard to build

Speed is easy to promise.
Hard to actually deliver.

Every company says "real-time." Almost none mean it. Here is what we solved that others didn't.

01

The latency problem

Under 1 second, end-to-end

Getting from the last word you speak to translated audio playing in your partner's ear in under one second requires solving dozens of micro-latency problems simultaneously. Most systems buffer, batch, and process in rounds. Ours streams continuously — the moment a sentence completes, the output is already halfway done.

02
🧠

The coherence problem

Conversations, not sentences

Translating one sentence accurately is trivial. Translating a conversation accurately is not. Names mentioned 5 turns ago need to carry into the current sentence. A pronoun said in Hindi needs to resolve correctly in German. Industry vocabulary — medical, legal, financial — needs to hold across every exchange. We built a conversational memory layer that no sentence-by-sentence system can replicate.

03
🎙️

The naturalness problem

Sounds human, not robotic

The final output has to sound like a real person said it — not a machine reading a translation. Speaking pace, emotional tone, the natural rhythm of a sentence in the target language — all of this has to be preserved or reconstructed. A robotic voice breaks trust and makes comprehension harder. We spent significant time on this layer and it shows.

The result: a system that feels less like software and more like having a fluent interpreter in the room.

<1s

latency

60+

languages

8-turn

context memory

Frequently asked questions

How long does translation take?+
End-to-end latency — from you finishing a sentence to your partner hearing the translation — is typically under 1.5 seconds. For most language pairs it's closer to 0.8–1.2s. Fast enough to feel like a natural conversation.
What languages are supported?+
60+ languages including English, Spanish, French, German, Mandarin, Japanese, Korean, Arabic, Hindi, Bengali, Tamil, Telugu, Marathi, Gujarati, Punjabi, Urdu, Portuguese, Italian, Russian, Polish, Dutch, Turkish, and many more.
Can more than two people join a call?+
Yes — TellAcross supports multi-party calls where each participant can have a different language pair. Everyone speaks and hears in their own language simultaneously.
Do guests need an account?+
No. The person who creates the room needs an account, but anyone they invite can join via link without signing up.
Is call audio stored?+
Raw audio is processed in real time and not permanently stored. Transcripts can optionally be saved for 30 days on Pro plans.
How accurate is the translation?+
Very. TellAcross uses state-of-the-art AI models selected per language pair to maximise accuracy and fluency — the goal is that the translated output sounds like something a native speaker would say, not a machine translation.
What are Industry Modes?+
Industry Modes let you tune the translation engine to your context. Medical Mode preserves clinical terminology. Legal Mode keeps exact legal phrasing intact. Business Mode maintains formal professional tone. Education Mode uses clear, accessible language. You set your mode in Settings — it applies across all your calls automatically.
What is Conversation Context Memory?+
TellAcross keeps a rolling memory of up to 8 turns of the conversation with speaker labels for every participant. This means if someone mentions a name in one sentence, the translation of the next sentence will correctly use it — even across different languages. Pronouns resolve naturally. Topics carry through. It behaves like a human interpreter who has been in the room the whole time.
Does TellAcross detect languages automatically?+
Yes. Auto language detection is built in — you don't need to select your language from a menu if you don't want to. TellAcross identifies what language you're speaking in real time and routes translation accordingly. This is especially useful in Quick Translate mode, where you're talking to someone face-to-face and there's no time to configure anything.
What is Quick Translate and when should I use it?+
Quick Translate is TellAcross's in-person mode — no call, no room code, no second device needed. You open the Quick Translate screen, speak, and the translation plays back on the same device. It's designed for situations where you're physically with someone who speaks a different language: airports, hospitals, hotels, courts, restaurants, clinics. Auto language detection means you just speak — TellAcross figures out the rest.

Ready to break the language barrier?

Start free. No credit card required.