Capture the Language.
Connect Sound to Image.
Learn from Real Human Voices.
A dedicated audio recording studio and sound-to-image flashcard lab designed for learners working with language nurturers, native tutors, and immersion hosts. 100% offline, zero subscriptions.
Food & Immersion
café au lait
Coffee with steamed hot milk
Swipe left/right to change card • Tap card to 3D flip
“Language Is Caught, Not Programmed.”
Traditional language apps rely on robotic synthetic text-to-speech engines and disconnected multiple-choice drills. Coursi was engineered for learners who immerse themselves directly in the living language.
Language Is Caught in Living Context
Fluency is built in connection, not isolation. Whether you learn through the Growing Participator Approach (GPA) with a community nurturer or study 1-on-1 with a private tutor, real comprehension starts by recording authentic spoken voices you know and trust.
- Record in-situ during live sessions without breaking conversation flow
- Preserve real dialect inflections, cultural cadence, and local idioms
- Replace disconnected multiple-choice drills with genuine human connection
Sound-to-Image Before Forced Reading
Children understand spoken phrases long before they learn phonics and alphabet grammar. Coursi attaches native audio directly to photos, physical realia, and hand-drawn scenes—bypassing the mental exhaustion of translation dictionaries.
- Connect spoken sounds immediately to whiteboard photos and objects
- Train the auditory cortex to discern subtle vowel lengths and tones
- Eliminate the robotic, synthetic text-to-speech (TTS) engines used in generic apps
Your Living, Personalized Curriculum
Standard language curriculums teach irrelevant tourist trivia. Coursi captures the exact words and phrases you encounter in your daily immersion, your market visits, your church or community, and your field assignments.
- Organize decks by date, lesson topic, or village/neighborhood context
- Capture specialized vocabulary: medical, theological, regional dialects
- Never lose a fleeting pronunciation note or chalkboard diagram again
Tactile Cognitive AnchorsSound-to-Image Hand Sketches
Direct cognitive connection without grammatical translation dictionaries.
Living ImmersionIn-Situ Live Capture
Capture natural cadence and spontaneous dialect expressions.
Designed for GPA Practitioners, Tutors & Field Immersion
Whether you practice the Growing Participator Approach (GPA) with a language nurturer, meet with tutors on iTalki and Preply, or navigate in-person immersion abroad, Coursi gives you a personal audio laboratory to capture authentic living speech and anchor it to memory.
An Audio Studio & Visual Lab in Your Pocket
Every feature in Coursi was constructed to solve the friction of real-life language tutoring sessions.
Live Session Recording & Waveform Metering
Zero-friction phrase capture in real time.
Never scramble to write down notes while your tutor or host is speaking. Hit record in one tap to capture the teacher’s phrase, attach a chalkboard photo, and label details later.
- Real-time 60-bucket envelope waveform meter ensures optimal pickup distance
- Instant tap-to-record with automatic phrase indexing and timestamps
- Multimodal card builder: native audio, whiteboard photos, IPA, and notes
Built-in Studio DSP Audio Engine
Automatic acoustic cleanup right on your mobile device.
Classrooms, cafes, and living rooms are filled with air conditioning rumble and chair rustle. Coursi includes studio-grade signal processing that cleans speech instantly.
- Classroom Denoise: 2nd-order Butterworth 85 Hz high-pass filter cuts AC and traffic rumble
- Smooth Noise Gate: Intelligently attenuates background murmur between spoken phrases
- Dynamic Gain Ceiling: Normalizes quiet and loud voices to −1 dB with soft tanh saturation
- Precision Waveform Trimmer: Dual boundary drag handles crop dead air to the millisecond
Sound-to-Image Flashcard Review
Multimodal focus mode engineered for rapid acquisition.
Review your tutor’s voice with interactive tactile flashcards designed to simulate natural memory recall.
- Front of Card: High-resolution photo/realia + one-tap native pronunciation playback
- Back of Card: Tap to 3D flip and reveal IPA transcription, translation, and nurturer notes
- Full-Screen Focus Mode: Distraction-free interface with session progress indicators
- Smooth Horizontal Swiping: Natural gestures (swipe left for next, right for previous)
- Pitch-Preserved Speed: Slow down to 0.5x, 0.75x, 1.0x, or 1.25x without chipmunk distortion
Directory Organization & Multi-Language Shell
Keep multiple languages completely sandboxed.
Studying French in the morning and Tunisian Arabic in the afternoon? Coursi isolates vocabulary, decks, and audio files for each language you study.
- Strict per-language isolation shells with regional flag indicators
- Quick sorting: Newest, Oldest, Recently Modified, or Alphabetical (A–Z / Z–A)
- Organize entries by textbook chapter, tutor session, or situational topic
- Drag-and-drop phrase reordering to mirror lesson flow
100% Offline & Private (Zero Telemetry)
Your personal recordings never leave your device.
Your voice recordings, tutor sessions, and field notes are confidential. Coursi requires no logins, has no tracking trackers, and stores all assets in an encrypted local sandbox.
- 100% functional offline: practice on airplanes, rural villages, or offline retreats
- Zero user accounts, zero analytics SDKs, zero third-party AI training pipelines
- Single-file .coursi (ZIP) open container export with SHA-256 integrity verification
- Seamless backup/restore via iCloud Files, Google Drive, AirDrop, or USB cable
Interactive A/B Student Voice Comparison
Visually match your voice against the native speaker.
Wondering why your pronunciation sounds foreign? Record your voice directly alongside your tutor’s and compare waveform peaks side-by-side.
- Dual-track A/B playback: Alternate instantly between tutor and student clips
- Visual amplitude matching reveals where accent stress and liaison cadence deviate
- Looping audio drills cement articulatory muscle memory for difficult phonemes
On-Device DSP: Turning Room Clatter into Studio Speech
Raw phone recordings captured in cafes and classrooms are difficult to study. Coursi runs a 4-stage DSP chain locally on your device:
High-Pass Filter
2nd-order Butterworth filter attenuating low-end air conditioning hum, traffic rumble, and desk thumps.
Smooth Noise Gate
Intelligently suppresses background room murmur during natural silences and pauses between spoken words.
Tanh Normalization
Boosts quiet whisper phrases up to optimal listening levels while soft-clipping peaks to eliminate harsh distortion.
Waveform Trimmer
Visual multi-bar amplitude visualizer lets you drag start and end handles to eliminate dead air down to the millisecond.
Permanent Tools, Not Recurring Rent.
We believe fundamental study tools should be permanent personal assets. Pay once, learn forever.
Evaluation Version
Test the complete workflow in your next tutoring or immersion session.
- Up to 20 recorded phrases across all lessons
- Full DSP audio cleanup & noise gate studio
- High-resolution whiteboard photo attachments
- Interactive 3D flashcard study mode
- .coursi ZIP container backup & restore
- 100% Ad-Free, zero tracking telemetry
Lifetime App Unlock
Pay once, own forever. Family sharing supported.
- UNLIMITED phrases, recordings, and lessons
- UNLIMITED language isolation shells
- Interactive A/B student voice comparison lab
- Pitch-preserved variable playback speeds (0.5x – 1.25x)
- Lifetime app updates & zero subscriptions forever
Technical Specifications
Architecture & Audio Engineering Standards
Test Coursi on iOS & Android Today
We are actively inviting language students, GPA practitioners, SIL linguists, mission workers, and independent polyglots to test the beta. Scan a QR code or tap the store links below.
Android Beta
Download the official Android release directly from the Google Play Store on your phone or tablet.
Scan with cameraApple iOS Beta
Join our public TestFlight program on iPhone or iPad to test active weekly builds and submit feedback.
Scan with cameraHave feedback, audio bug reports, or feature requests? Contact our team directly at:learn@lancercommunities.com
Growing Participator Approach (GPA) & Relational Sound-to-Image Acquisition
Coursi is architected around Greg Thomson's Growing Participator Approach (GPA) methodology. Rather than relying on mechanical rote translation tables or robotic synthetic text-to-speech engines, Coursi connects raw human audio recorded live with a language nurturer directly to high-resolution realia, chalkboard notes, and tactile visual memory anchors. This ear-before-eye acquisition trains auditory phoneme discrimination before the cognitive strain of reading orthography.
On-Device Digital Signal Processing (DSP) Speech Specifications
Coursi records 44.1 kHz 16-bit uncompressed PCM WAV audio streaming. Acoustic enhancement is performed entirely on-device with zero cloud telemetry using a 4-stage pipeline: a 2nd-order Butterworth 85 Hz high-pass filter eliminating room HVAC rumble and traffic low-end; a smooth noise gate suppressing room murmur between spoken phrases; soft tanh saturation normalizing speech to -1 dB without harsh digital clipping; and a millisecond-precision waveform trimmer.
Offline Data Integrity & Privacy Architecture
Coursi operates with zero user accounts, zero analytics SDKs, and zero cloud uploads. Decks are packaged into standard open-format .coursi ZIP containers holding uncompressed WAV recordings, metadata JSON, and JPEG photos, secured with SHA-256 integrity checksums for lifelong student ownership.