Speak a new language.
From day one.

Parlonto is a voice-first language learning app that teaches you to hold real conversations. Every word is introduced in a scenario you'd actually use it in, and you practice by speaking — not tapping.

Built for iOS · Works offline · Your voice never leaves your device

Meeting Someone · Stage 5
Marie · Paris café
Bonjour ! Je m'appelle Sophie.
0:02
✓ Greeted · ✓ Gave name

Flashcards don't teach you to talk.

You learn words, not conversations.

Most apps test vocab in isolation, so you freeze the moment someone actually speaks to you.

You tap, you don't speak.

Reading and recognizing feels productive, but production is where fluency lives.

Every session looks the same.

Artificial "streaks" reward showing up, not improving.

Parlonto is different. You talk to a person who talks back — in the language you're learning — from the very first lesson.

Five stages, one arc.

From recognition to real conversation.

1

Introduction

Pronunciation check

You're shown a new word with a native-speaker audio clip and a quick explanation. Tap to listen, tap the mic, say it back. That's how you meet every new word.

Examplebonjour — "The standard French greeting, used from morning through afternoon."
2

Recognition

Quick translation matching

Lock in meaning with quick recall.

ExampleWhat does enchanté mean?
3

Comprehension + Production

Hear it, respond to it

You hear a snippet of a realistic conversation, then respond.

ExampleA waiter says "¿Qué desea ordenar?" — now order a coffee.
4

Guided Roleplay

Scripted multi-turn with fading hints

A scripted multi-turn conversation with hints that gradually fade. You speak every learner turn. The on-device model grades you against specific criteria.

ExampleJulien says "Bonsoir, je suis Julien." → "Greet and introduce yourself." You say "Bonsoir, je m'appelle Alex."
5

Free Roleplay

Open-ended, goal-tracked

An open-ended conversation with an AI character that stays in role, speaks only the target language, and responds to what you actually said. Goals are displayed above the input bar and get checked off in real time.

Example"You're at a café in central Paris. A friendly local named Marie points to the empty chair next to you and asks if it's free." Goals: confirm the seat is free, introduce yourself, say you're American, say you like Paris.

You don't pick your stage — the app picks it for you, per word, based on how well you actually know each one.

What makes it work.

Voice-first practice.

Every answer is spoken, not typed. Built-in iOS speech recognition handles transcription.

Adaptive difficulty per word.

A modified FSRS spaced-repetition algorithm schedules every word individually — easy words get spaced out, hard ones come back tomorrow.

Realistic scenarios, not drills.

Every lesson is built from three generated conversations set in a real context, so you're practicing exchanges you'd actually have.

On-device AI tutor.

A fine-tuned language model runs locally and grades your responses against explicit criteria — feedback that understands context, not just keywords.

Session-capped sessions.

Each session is bounded (target mastery gain or 15 questions max) — no infinite scroll, no streak anxiety.

Warm, deliberately calm.

Earthy olive and cream palette. Built to be the anti-gamified app.

Private by design. Offline by default.

No servers between you and your next conversation.

On-device LLM

A fine-tuned 2B-parameter language model runs entirely on your iPhone. It evaluates your responses, plays the character in roleplays, and checks your pronunciation — all without a network call.

No account required

No sign-up. No email (except the optional waitlist). No account to delete. Your vocabulary, your progress, your recordings — everything lives on your phone.

Offline from install onward

Each unit's audio is downloaded once when you add it. After that, everything works in airplane mode: lessons, roleplays, grading, progress tracking.

Languages at launch.

🇪🇸

Spanish

At launch

native-speaker voices via Voxtral

🇫🇷

French

At launch

native-speaker voices via Voxtral

🇯🇵

Japanese

At launch

native-speaker voices via Qwen 3 TTS

More languages coming after launch — join the waitlist to vote on which.

Can't find the scenario you need? Write it yourself.

Describe any situation in plain English — "haggling at a market in Tokyo," "explaining a software bug to a French colleague," "telling a Spanish doctor about a back injury" — and Parlonto generates a full unit: three realistic conversations, a vocabulary list, a full ladder of exercises, and native-speaker audio.

$1 per custom unit. Generated in a minute or two. Yours forever.

Parlonto is free.

All core content, all languages, all features. No subscription. No ads during practice (future ads, if any, will only appear at session-end summary screens). The only paid action is optional custom unit generation at $1 apiece.

Be the first to try it.

Parlonto launches on the App Store June 1st, 2026. Drop your email and we'll send you one message when it's ready — that's it. No newsletter, no drip campaign.

Questions.