How to use Fluent
Prepare a material, speak along with the model, and let AI analyse your recording. This guide walks through every screen in that loop, and through the level check, the AI class and the AI coach. New here? Read from the top; otherwise jump in from the table of contents.
Contents
/loginGetting started — your account and the free trial
All you need is an email address. Every feature is free for 7 days from the day you press “Start the free trial” — you choose when, and no card is needed.
On the sign-in page choose “No account yet? Create one”, enter your email address and a password (6+ characters), and press “Create account”. “Continue with Google” signs you up with a Google account instead.
If a confirmation email arrives, open the link in it to finish signing in. You can also use “Email me a sign-in link” instead of a password.
After signing in you land in the library. Press “Start the 7-day free trial” in the bar at the top, then “Start” in the dialog. Before that you can look around, but creating or adding materials and the AI features only work once the trial has started.
Every feature is available during the trial, within these limits: 3 AI classes of 5 minutes, the AI coach kickoff (first session, 20 min) plus 15 minutes of voice coaching, the first conversation test and the first comprehensive test, and 10 AI analyses a day. The bar at the top shows the days left; to keep going afterwards, subscribe to a plan (section 13).
The sidebar on the left (the menu at the top on a phone) takes you to every screen, in this order: Library, Create material, Presets, Shadowing practice, Shadowing analysis, Level check, AI class, AI coach, Vocabulary, History & progress, Plan & billing, Settings and Help.
/createPrepare a material — from your own audio
Cut the part you want out of a podcast, a video's audio or any mp3 / m4a (wav works too) and turn it into a material.
Open “Create material” in the sidebar and enter a title. Press “Click to choose a file” or drag & drop the file (up to 80 MB / 30 minutes).
Once the waveform appears, choose the region: drag on the waveform or move the “Start” / “End” sliders. Typing a number of seconds into “Length” (or pressing one of the 15–60 s buttons) sets the end to start + length. Check it with “▶ Play region”. One material can cover up to 5 minutes.
Press “AI transcription” and the region becomes a script within a few dozen seconds. Fix any mistakes directly in the text; per-word timings are estimated automatically.
Optionally add tags (the speaker's country or accent, the show's name…) and press “Save material”. The practice screen opens right away.
/presets/presets/podcastPresets and podcasts
No audio of your own? Start with our original series, read by speakers from many countries and accents, or with parts cut from English podcasts.
Open “Presets” in the sidebar to see “Browse series”: series with cover images, grouped by country or region, filtered by “Country / region”, “Level” and “Progress” (not started, in progress, practised). “See all” lists every series of one country or region.
A series is split into a few short parts. Switch between “Part 1”, “Part 2”… and listen to the model audio; “Practise Part N” adds that part to your library and opens the practice screen (a part you already added opens directly).
The “All parts & search” tab lists every part as a card. Filter by type (monologue / dialogue), level, speed (a WPM band) and the “Accent · Country”, “Genre” and “Topic” tags, listen with “▶ Preview”, then press “Add to my library”. Every clip is a single take at a natural pace; the level comes from the measured WPM (words per minute).
The “Podcast” tab has parts of about 30 seconds cut from English podcasts. Pick a show, then an episode: the page shows the original title, the speed, the opening of the script and the “Credits” with the rights holder, the licence and the original episode. You start practising with “Practise Part N”, as for a series.
Dialogues (two or more speakers) can be practised as role-play on the practice screen (section 5).
/Organise your library
Materials you create and parts you add from the presets or podcasts all land in the library. As it grows, tags and filters keep it easy to find things.
Each card shows the region, word count and language plus the speed (WPM). Analysed materials also show the latest score and a “Results” button.
Press “+ Tag” on a card to add or remove tags (Enter confirms). Click a tag to filter by it.
The filter bar combines a WPM band, tags and the sort order (newest / WPM / score). The filter is kept in the URL, so it survives when you come back.
“Delete” removes the material together with its takes (this cannot be undone).
/practiceShadowing practice
Shadowing means speaking along with the model, a beat behind it. Open a material with “Practice” in the library (“Shadowing practice” in the sidebar opens the one you used last).
“▶ Play” starts the model and “■ Stop” stops it (the space bar works too). With “Loop ON” the region repeats.
“Speed” offers 0.5× to 1.5×. Slow it down when you cannot catch the words, then move back up to 1.0× and beyond. The default lives in Settings.
“Script shown / hidden” hides the text. With “Highlight current word” on, the current word lights up as the audio plays.
“Japanese translation” asks AI for a Japanese translation and shows it under the script (a few seconds the first time). Press again to hide it.
In dialogues, “My role” picks a speaker: you practise only that role's lines and the AI analysis scores only those. Tick “Mute the model during my lines” and the model goes silent on your turn, so it feels like a real conversation.
/practice/analysisShadowing analysis — record a take and let AI analyse it
Your voice is recorded alongside the model and scored word by word on pronunciation, rhythm and intonation. “Shadowing analysis” in the sidebar opens your latest report.
Press “● Record & shadow” on the practice screen. The first time, the browser asks for microphone access — allow it. The model plays once; speak along with it. Recording stops by itself when the model ends.
When the “Take 1” row appears, “Listen to my take” plays it back. Not happy? Record again — the new take replaces it.
Press “Analyse with AI →”. The take is uploaded and the report opens within a few dozen seconds.
Reading the report: the “Overall score” on the left and the three parts “Pronunciation”, “Rhythm & timing” and “Intonation”. Words are colour-coded — green = good, yellow = close, red = needs work (missed words are struck through). Hover a word to see what was heard and how far behind it was.
“Comments from the AI coach” below names the one thing to fix in the next take, from three angles. “What the AI heard” shows the recognised text. When you recorded with a role selected, the report says “Scored: lines of … only”.
/vocabularySave words to the vocabulary book
Save the words and idioms that catch your attention while you practise. AI writes a meaning that fits the context.
In the script on the practice screen, click a word once to save it. Saved words get a dotted underline.
For an idiom (several words), drag from the first word to the last and press the “Save “…” to vocabulary” button that appears.
The meaning, part of speech and an example sentence are generated by AI; words also get meanings per part of speech and an IPA pronunciation (the speaker plays it). “Vocabulary” in the sidebar lists them under Words and Idioms, with a search box.
“Regenerate meaning” retries an item whose meaning failed, “Add dictionary entry” adds parts of speech and pronunciation to an item saved earlier, and “Delete” removes one. Click the source material's title to open its practice screen.
/historyTrack your progress in History
Practice time is recorded automatically and shown as a day-by-day line chart.
Open “History & progress” in the sidebar. The line chart shows practice minutes per day; “Range” switches between 7, 30 and 90 days (30 by default). Above the chart: the total for the range, your streak and the daily average.
Minutes are counted from the time the model played or a take was recorded on the practice screen (practice in the iPhone app included). Hover or touch the chart (or use the ← → keys) to read a day's minutes; today's point shows its value.
“Recent takes” below lists the analysed takes, newest first, with the date, material and overall score. Click a row to open its report; “Open the latest analysis report →” jumps to the most recent one.
/placement/ai/level-checkComprehensive test: PC onlyLevel check — the conversation test and the comprehensive test
“Level check” in the sidebar offers two tests. Both are a guide for your learning, not an official qualification. Their results are kept separately and never merged into one score.
Conversation test (about 6 minutes): “Start” → check the microphone on “Before you start” → “Start the test”. Pick whether the questions come in Japanese or English (you always answer in English); the AI teacher briefly explains the flow, then asks three questions in that language. The result estimates your speaking level; reading and writing are not assessed. It is also in the AI tab of the iPhone app (section 12).
Comprehensive test (web on a PC only; recommended browsers: Google Chrome, Safari): press “Take the comprehensive test” and choose a course — “Quick” (grammar, reading, listening; about 20 minutes), “Standard” (+ writing; about 30) or “Full” (+ speaking; about 40).
Every course starts with 9 grammar items (one from each of the 9 levels A1–C2, easiest first); reading and listening start at the level they show and adjust after each text or clip, and writing and speaking are set at the median of the three. “Before you start” checks the screen width, the keyboard, the microphone (Full) and the test sound; agree to the rules and press “Start the comprehensive test”.
Each section opens with an intro screen, and a button such as “Start Grammar (4 min)” starts its timer. The clock stops between sections, and a finished section cannot be reopened. Answers are saved automatically; choose with the 1–4 / A–D keys and move between questions with ↑↓. Listening clips play twice up to B1 and once from B1+. Speaking is two recorded tasks: prepare, then speak.
The result page shows a level for each skill (a guide on the 9-step ladder A1–C2) with what you can do at it, your strengths and the areas to work on, what to practise next — AI class topics, presets and more — and the listening scripts. Writing and speaking are scored by AI after you submit. When you took the test before, the result is compared with that one; earlier results open from “History”.
/aiAI class
A one-to-one, 5-minute voice class with an AI teacher. Choose what to practise: grammar, vocabulary, reading, listening, writing or speaking. You need a microphone (earphones or a headset recommended).
Open “AI class” in the sidebar. The tiles at the top show “Today's class” (how many you have left) and your “Level check” slot. You get 3 classes in total during the free trial, 4 per renewal period on Starter and one a day on Pro, Pro Plus and Premium (unused classes do not carry over).
Choose how to practise. “Practise with materials” draws on questions written for the class: pick “Today's pick”, “Continue” or “Choose yourself”; under “Choose yourself”, select a skill card (grammar, vocabulary, reading, listening, writing, speaking), then the area and the question mix (Auto / New / Review). “Practise by theme” offers “Auto” (the teacher plans from your recent materials and your last review) and speaking options such as free talk or a theme you choose.
Press the start button (e.g. “Start the 5-minute class: Grammar”), check the microphone on “Before you start” (“Start the class” becomes available once it shows ✓), check the slot, then begin. The teacher first asks whether to explain in Japanese or English: answer out loud, or choose “日本語” or “English” under “Explain in” at the top. You can switch at any time, and next time the teacher checks whether to keep your last choice.
Grammar, vocabulary, reading and listening are drills with one question on screen at a time. Choose an option and press “Answer” (or use the 1–4 / A–D keys and Enter): the teacher says whether it is right with a one-line explanation and moves on until the time is up. “Hint” and “Skip” are there too; a skipped question does not count as wrong. Grammar, reading and listening get a little harder when you keep getting them right and a little easier when you struggle. Vocabulary is a test on TOEIC or TOEFL words: choose the meaning from four options.
For writing, type an English answer to the task and the teacher gives feedback (you may rewrite it once); for speaking, answer out loud. When the class ends its report opens, and “Recent classes” on the class page keeps every report, in tabs for grammar & vocabulary, reading, listening, writing and speaking.
/ai/coachAvailable in the free trialAI coach
The AI coach helps you set a goal, plan each day's study and keep going. It comes with the Premium plan and the free trial (during the trial: the kickoff — your first session, 20 min — chat consultations and 15 minutes of voice coaching; on Premium: 40 minutes of voice coaching per renewal period). Subscribing to another plan during the trial ends your access to it right away.
Open “AI coach” in the sidebar and choose “Use the coach”. “Set a goal (answer a few questions)” asks about your goal, the time you can study and more, one question at a time (you can skip); the coach then drafts a weekly plan. Nothing changes until you check it and press “Use this plan”.
“Goal and study plan” shows your goal and the days to your target date, the minutes planned this week, your current estimated level and the goal level, this week's schedule (minutes per day) and the menu for each day with the reason for it. Plan changes, too, apply only when you review and confirm them.
“Today's study” on the home screen lists today's menu, and “Start today's study” takes you to the material or the AI class. On a busy day, “Make today shorter” switches to the short menu. Study outside the app (books, online lessons…) can be logged as self-reported with “Log study outside the app”.
“Chat with the coach” lets you ask in writing — how to keep going, which material to pick and so on. “Talk by voice” starts a call: choose its length (10 minutes during the free trial, or what is left when that is less). Only the connected time is taken from your voice-coaching minutes. Your first consultation is the kickoff (about 15–20 min): how to use the coach, your level-check results, your goal, study plan and materials, and booking the next session. The kickoff has its own 20 minutes, so your voice-coaching minutes are not used. Consultations are in Japanese by default.
After a consultation a “Coaching record” (an AI-written summary) is made, and you can edit it. “Weekly review” builds this week's review from what was planned and what you did (days and minutes).
iPhone app
A practice-focused app. Sign in with the same account as the web: the materials you made on the PC are right there and your records stay in sync. Five tabs along the bottom: Library, Explore, AI, Records and Manage. Vocabulary is inside Library; study time, practice history, AI classes, the comprehensive test and coaching are under Records.
Sign in with the same account as on the web (email address and password, for example).
The flow is the same as on the web: Library → practice (playback, speed, script / translation toggles, karaoke highlight, your role) → record → AI analysis → report.
The Explore tab offers the same original materials and podcasts as the web; add one and start practising. The AI tab has “Level check”, “Class” and “Coach” for the conversation test, the AI class and the AI coach (the comprehensive test runs on the web on a PC only).
To save vocabulary, tap a word to select it and tap the neighbouring word to extend it to a phrase; “Save to vocabulary” stores it. Vocabulary in the Library tab can regenerate meanings and delete items.
The Manage tab holds your goal and study plan, notifications, plan, and account settings (interface language, sign out, delete account); study time, practice history, AI classes, the comprehensive test and coaching are under the Records tab. Creating materials from your own audio and subscribing to a plan stay on the web.
/billingPlan and billing
After the 7-day free trial, you continue on one of four plans: Starter (¥1,980 a month, tax included), Pro, Pro Plus or Premium. A yearly plan costs ten months of the monthly price. “Plan & billing” shows each plan's price and what it includes.
Open “Plan & billing” in the sidebar to see your state: trial not started, the free trial with the days left, your current plan with the next renewal date, a pending cancellation and so on.
Pick monthly or yearly and press “Subscribe” on a plan to go to Stripe's checkout page. With 48 hours or more of the trial left, billing starts when the trial ends. With less than 48 hours left, or after the trial, you are charged when you subscribe. Subscribing before starting the trial starts it at that moment, so the first 7 days stay free. Subscribing during the trial switches you to that plan's allowances at once, even when billing starts later.
While subscribed, press “Switch to this plan” on another plan to change. The change applies at once and the difference is prorated. Every plan includes materials, presets and podcasts, AI analysis (15 a day), vocabulary and history.
Once subscribed, “Manage billing” lets you change the card, see invoices and cancel. After cancelling you keep access until the end of the period.
Have a coupon code? Enter it under “Coupon code” and press “Apply”. A trial-extension code adds days right away; a discount code is listed under “Discounts waiting for checkout” and applied automatically on the Stripe checkout page the next time you press “Subscribe”. A link of the form fluent-en.com/billing?coupon=CODE opens the page with the code filled in.
/settings/feedbackSettings and feedback
Defaults that fit you, the legal pages and account deletion, and how to reach the developer.
In “Settings” you can change the interface language (Japanese / English), the default playback speed, whether the script is shown when practice starts, and the microphone used for recording. Changes are saved on the spot. The “Account” row signs you out.
The “Legal” row under the settings links to the Terms of Service, the Privacy Policy and the notice under the Specified Commercial Transactions Act.
In “Delete account” at the bottom, type DELETE in the confirmation field and press “Delete my account”: your materials, takes and analyses, vocabulary, practice history, AI class, AI coach and level-check records and your sign-in credentials are erased, and a paid subscription is cancelled immediately (the remaining days are not refunded). This cannot be undone.
Bugs and ideas go through the “Send feedback” button in the top-right corner of every screen: pick a type, write a title and the details, and press “Send”.
For a bug report, the steps to reproduce it and the screen where it happened help a lot.
FAQ and troubleshooting
When something does not work, check here first. If it is still not solved, let us know through feedback.
No microphone prompt / cannot record
Open the site settings from the icon on the left of the address bar, set the microphone to “Allow” and reload the page. For an external microphone, choose the input device under Settings → Microphone. Recording needs an HTTPS connection.
No sound from the model
On iPhone / iPad the silent switch (ring/silent) can mute browser audio: flip it and check the volume. With Bluetooth earphones, make sure the output is routed to them.
The transcription is off / wrong
Edit the script text directly before saving; the per-word timings are re-estimated automatically. Audio with background music or overlapping speakers transcribes worse, so pick a clean region where you can.
The analysis is slow / never finishes
Speech recognition plus the AI coach usually take 20–60 seconds (longer regions take longer). If an error shows up, press “Analyse with AI” again with the same take. Reloading the page discards the take, so record again in that case.
Which browsers are supported?
The latest Chrome, Safari and Edge. The AI class, the conversation test and voice coaching are voice calls through the microphone: use a recent Chrome, Edge, Safari or Firefox and allow the microphone. Phone browsers work too, but recording is more reliable in a desktop browser or the iPhone app.
Can other people hear my recordings?
No. Your audio and recordings are stored in your account only and no other user can access them. For transcription, AI analysis and AI class conversations they are sent to the AI providers we work with (see the Privacy Policy). You can delete materials and recordings at any time.
How do I delete my account?
Open Settings, scroll to “Delete account” at the bottom, type DELETE to confirm and press “Delete my account”. In the iPhone app it is under the Manage tab → Account settings. Your materials, takes, analyses, vocabulary, practice history and your AI class, AI coach and level-check records are erased and a paid subscription is cancelled immediately (the remaining days are not refunded). This cannot be undone.
Can I take the comprehensive test on a phone or in the iPhone app?
No. The comprehensive test needs a wide screen and a keyboard, so it runs on the web on a PC only. The conversation test and the AI class work on the web, and are also in the AI tab of the iPhone app (section 12).
What if the connection drops during an AI class or the conversation test?
The clock only runs while you are connected. Within 30 minutes of the start, “Resume” on the AI class or level check page continues with the time you had left. If it fails before the teacher connects, no class is used.
Is there a limit on AI analyses or new materials?
Yes. AI analysis: 10 a day during the free trial, 15 a day on a paid plan. New materials with AI transcription: 10 a day. The counts reset at midnight Japan time.