MasteringTheatre is an active-dialogue theatre rehearsal app. The AI reads lines with a natural voice, you respond aloud, and the app listens, transcribes, gives you an accuracy score after every line and a word-by-word review at the end of the session.
Three modes: Theatre (script rehearsal), Job Interview (AI recruiter simulation) and Create your scene (custom AI-generated scenes).
The app works on Android and iOS. Your scripts, scores, favourites and voice packs are stored on your device. AI features send the necessary text to our servers and to Google services. No voice recordings pass through our servers.
Four tabs at the bottom of the screen:
The home screen shows:
From the home screen, tap the Theatre card to access features, organized in three sections:
| Feature | Condition | Cost |
|---|---|---|
| Learn my lines | — | — |
| Feature | Condition | Cost |
|---|---|---|
| Audition Training | Blocked (Free) · Pro | 2 |
| Improvisation | Blocked (Free) · Pro | 35 |
| Memorization | Script imported · Free | 0 |
| Diction exercises | Pro | 2 |
| Feature | Condition | Cost |
|---|---|---|
| Reports (your rehearsal report history) | — | — |
| Voice packs | — | — |
Locked features show a padlock icon. Tap them to see how to unlock.
Paste your text, one line per speech: CHARACTER NAME: line. The name must be in UPPERCASE (letters, spaces, full stops, apostrophes or hyphens, 31 characters at most) and end with a colon; a space before the colon is optional. A line whose name contains lowercase letters or a parenthesis ("Romeo: …", "ROMEO (aside): …") is not recognised as a line.
Stage directions: put them in parentheses after the colon, for example "ROMEO: (aside) But soft…". They stay on screen, but the voice does not read them, the score does not count them and the prompter does not show them.
Acts and scenes: a line starting with ACTE, SCÈNE or SCENE (any case), or a --- or === line, creates a selection shortcut. "ACT I" is not recognised.
Tap "Load a sample" to import a demonstration script in your current language. A great way to discover how the app works before importing your own text.
Select a PDF or TXT file. PDF text is extracted on your device, without going through our servers. A scanned (image-only) PDF is sent automatically to OCR Pro (free).
Pro Photograph a script page, then "Add" more pages (up to 6). Press "Extract text": the AI extracts text from all photos in a single pass (free).
Pro Select one or more photos (up to 6), then press "Extract text".
Pro The "AI cleanup" button (free) sends your text to the AI which identifies characters, reformats lines and corrects structure. Useful after an OCR import or a raw paste.
After "Validate lines", every line is selected between a START marker and an END marker:
If acts or scenes are detected, quick buttons select an entire section.
Choose the character you will play. The AI will play all other characters.
The setup screen offers two levels of detail:
In "AI assists you":
The "Partner voices" section lets you record voices and choose a voice pack for a character.
AI partner voice speed: 0.8x to 1.2x on Free, 0.5x (very slow) to 2.0x (very fast) on Pro and Premium.
In Fluid mode: silence duration (0.5 s to 10 s, in 0.5 s steps; 2 s by default) after which the app automatically validates your line.
AI coaching Pro is not a setting: it appears in the summary after each rehearsal.
When it's your turn, the mic activates automatically — the status bar shows "Your turn...". Speak naturally: recognised text appears in the status bar as you speak.
Each line receives an accuracy score (0-100%):
Coloured score badge: green (≥90%), gold (≥70%), red (<70%).
In Step by step: Validate, then the line score with Repeat or Next.
Tap another line in the list (past or upcoming) to resume from there. Scores from that line onward are cleared.
From the summary: "Role" (back to role selection), "Replay" (same scene) or "Back to Theatre". On Pro and Premium, AI coaching appears automatically in the summary (2⚡).
Spoken improvisation scene with an AI partner. Accessible from the Theatre hub — no script needed. Cost: 35⚡ flat fee per session, charged at launch ("Start" button).
Report (1⚡): score /10, summary, best moment, strengths, areas for improvement and tips. Save the report to Downloads or share as PDF.
Complete audition preparation. Cost: 2 per session.
Genre (drama, comedy, tragic, absurd, contemporary), character (any, female or male), age (18-25, 25-45, 45+), duration (30 s, 1, 2, 3 or 5 min), optional theme. The AI generates an original monologue with title, context and emotional arc.
"Rehearse" opens the monologue in rehearsal, split into segments of about 45 words that you say one at a time.
The report is a rehearsal summary: score per segment, missed or changed words, and AI coaching on Pro and Premium.
Save your monologues from the result screen ("Save", up to 20). Find them in "My monologues" with title, character, genre, date and emotional arc; tap one to rehearse it.
Accessible from the Theatre hub. Cost: 2⚡ per set of exercises, including "Regenerate words". Pro
The AI generates targeted tongue twisters based on the phonetic category chosen from 10 sound families:
Three settings:
Built-in voice recognition. "Regenerate words" produces a new set (2⚡).
Available after importing a script. Free for all plans.
Progressive memorization tool — your lines with hidden words:
Partner lines remain visible for context. "Check" reveals the hidden words of the current line; a checked line no longer counts in the "lines without checking" score.
Microphone: "Start" then "Stop": voice recognition transcribes your line and the app shows an accuracy score under it. Nothing is kept when you leave the screen.
Replace the partner's system voice with a real human voice recording.
From the role screen, in Advanced mode ("Partner voices" section):
Voices are stored only on your device.
From the Theatre hub → Voice packs, or Settings → Data → Voice packs: the list of packs (up to 10 on the device) with performer, character and number of recorded lines.
Export a pack in .mtvoice format ("Share this pack") — sendable by message, email or AirDrop. Only packs containing your own voice ("Record my lines for my partners") can be shared. Import: "Import a voice pack (.mtvoice)" in the packs list.
Prepare your interviews with a male AI recruiter. Premium
Accessible from the "Interview" badge on the home screen.
| Feature | Cost | Description |
|---|---|---|
| Simulation | 70-190 | 10, 20 or 30-minute dialogue with an AI recruiter (70, 130 or 180⚡; +10⚡ with a CV). Questions adapted to your answers, optional answer timer |
| Cover letter | 10 | Generated from your CV and interview report |
| Feature | Cost | Description |
|---|---|---|
| Timed Pitch | 3 | Timed pitch of 30 to 120 seconds (60 s by default), with AI analysis |
| Tricky questions | 15 / question | 5 tough questions, one at a time. You answer by voice; score out of 5 and immediate AI feedback after each answer |
If you give no answer, the recruiter rephrases the question. On a second empty answer, a dialog lets you retry or end the simulation and view the report.
Custom AI-generated scenes. Pro
Accessible from the "Create your scene" badge on the home screen.
| Feature | Cost | Description |
|---|---|---|
| New scene | 3 to 20 | Custom scene: 2 to 3 characters and 5 to 10 min on Pro; up to 6 characters and 45 min on Premium. Cost depends on duration |
| New show | 15 | Complete show for a full class Premium |
Genre, era, location, mood, characters (name, gender, trait), performer age, target audience, duration, language level. Premium only: stage directions, emotional density, emotional arc, several moods and teaching tools.
The Stats tab shows:
The bin icon next to "Recent sessions" clears the history.
The Favorites tab shows your saved passages (3 on Free; up to 30 on Pro and Premium, the oldest is replaced beyond that). Each favorite restores the full script, line selection and role.
Exportable PDF documents (all plans):
The rehearsal summary and the improvisation report offer Save (Downloads folder) and Share (native share sheet: WhatsApp, email, Drive…); other documents are sent with Share.
Accessible from the Settings tab:
The app stores all your data locally — scripts, favorites, session history, voice packs, progression. This data is not synced to any cloud server. Backup lets you protect it and transfer it between devices.
From Settings → Data → "Back up my data": the app generates a .mtbackup file (settings, history, favorites, voice packs, annotations, monologues, Create your scene scenes…) and you choose where to save it. "Export my data" sends the same file through the share sheet.
From Settings → Data → "Restore my data". Select a .mtbackup file; the backup date is shown before you confirm. Backup data is added to the data on the device: an item that already exists is not replaced.
To migrate to a new device: back up on the old one, transfer the .mtbackup file (email, AirDrop, USB drive…), then restore on the new one.
From Settings → About → Contact. A built-in form lets you send a message directly from the app:
We respond to every message. Your email address is only used to reply to you.
Required for: HD voice, AI Direction, AI coaching, AI paraphrase, diction, improvisation, Audition Training, OCR and AI cleanup, Create your scene, interview. System voice and scoring work offline.
Microphone permission is requested the first time you use the microphone (rehearsal, improvisation, diction…). Recognition quality depends on your microphone and environment (prefer a quiet place).
Text-based PDFs are extracted on the device, no network needed. Scanned or protected PDFs go automatically through OCR (Pro and Premium, connection required); on Free, paste the text manually.
All data is in the app's local storage. It is lost if you uninstall the app or clear its data. Use the backup (.mtbackup) feature to protect your data.
All AI-generated content passes through a multi-layer safety filter. Sensitive, inappropriate or offensive content is automatically blocked.
On the Free plan: Step by step mode and system voice only, imported text limited to 5,000 characters, memorization level 1, 3 favourites, 10-session history; Audition Training, Improvisation, Create your scene, Interview and AI features are locked. Upgrade to Pro or Premium to unlock all features.
| Feature | Free (€0) | Pro (€2.99/mo) | Premium (€4.99/mo) |
|---|---|---|---|
| Modes | |||
| Theatre | yes | yes | yes |
| Create your scene | — | yes | yes |
| Job Interview | — | — | yes |
| Voice | |||
| System voice | yes | yes | yes |
| HD Cloud voice (WaveNet) | — | yes (3⚡ / line) | yes |
| Gemini TTS | — | — | yes (rehearsal, 6⚡ / line) |
| Voice packs (listen) | — | yes | yes |
| Voice packs (record/share) | yes | yes | yes |
| Theatre — Features | |||
| Voice recognition + score | yes | yes | yes |
| Step by step | yes | yes | yes |
| Fluid mode | — | yes | yes |
| Variable speed | 0.8–1.2 | 0.5–2.0 | 0.5–2.0 |
| Prompter | — | yes | yes |
| AI Direction | — | yes | yes |
| AI Diction | — | yes | yes |
| Memorization | level 1 (free) | 3 levels (free) | 3 levels (free) |
| AI Paraphrase | — | yes | yes |
| AI Coaching | — | yes | yes |
| Free Improvisation | blocked | yes (35⚡) | yes (35⚡) |
| Audition Training | blocked | yes | yes |
| OCR photo script | — | yes | yes |
| PDF export / share | yes | yes | yes |
| Favourites | 3 | 30 | 30 |
| Session history | 10 | 50 | 100 |
| Create your scene | |||
| Max characters | — | 3 | 6 |
| Max duration | — | 10 min | 45 min |
| Stored scenes | — | 10 | unlimited |
| Stage directions / Emotional density | — | — | yes |
| Shows / Pedagogy | — | — | yes |
| Job Interview | |||
| Simulation (10/20/30 min) | — | — | yes |
| With or without CV | — | — | yes |
| Tricky questions | — | — | yes |
| Cover letter | — | — | yes |
| Timed Pitch | — | — | yes |
| CV scan | — | — | yes |
| Recruiter report | — | — | yes |
| Energy | |||
| Points / day | 0 | 50 | 100 |
| Max reserve | 0 | 1,500 | 3,000 |
Each AI feature consumes energy points. Your reserve recharges daily (Pro: 50 pts/day, cap 1,500 — Premium: 100 pts/day, cap 3,000). The Free plan has no points.
| Action | Cost |
|---|---|
| AI Direction | 2 |
| AI Coaching | 2 |
| Diction (per set) | 2 |
| AI Paraphrase (whole batch) | 1 |
| WaveNet HD voice (per line) | 3 |
| Gemini voice (per line, Premium) | 6 |
| Monologue (Audition Training) | 2 |
| Free Improvisation | 35 (flat fee) |
| Improvisation report | 1 |
| Photo OCR and AI cleanup | free |
A voice already generated (same text, same voice) costs nothing.
| Action | Cost |
|---|---|
| Line edit (Regenerate, More dramatic, Shorten, Lengthen) | 1 |
| 5 min scene | 3 |
| 10 min scene | 5 |
| 15 min scene | 8 |
| 20 min scene | 10 |
| 25 min scene | 12 |
| 30 min scene | 15 |
| 35 to 45 min scene | 20 |
| Sequel to a scene | same cost as a scene of the same length |
| Show | 15 |
| Action | Cost |
|---|---|
| Timed Pitch (AI analysis) | 3 |
| Recruiter report | free |
| CV scan | 5 |
| Tricky questions | 15 / question |
| Cover letter | 10 |
| 10 min simulation | 70 |
| 10 min simulation with CV | 80 |
| 20 min simulation | 130 |
| 20 min simulation with CV | 140 |
| 30 min simulation | 180 |
| 30 min simulation with CV | 190 |
Three voice engines, depending on your plan and the feature used:
| Engine | Description | Availability |
|---|---|---|
| System | Built-in device voice, works offline | Free Pro Premium |
| WaveNet (HD) | Natural Cloud voices (3 to 6 per language), requires internet | Pro Premium |
| Gemini TTS | Google Gemini voices (8 voices) | Premium — theatre rehearsal only |
Free plan: system voice only.
Pro: WaveNet in rehearsal, improvisation and interview.
Premium: Gemini in theatre rehearsal (Fluid or Step by step); WaveNet in improvisation and interview.
Diction exercises and memorization do not use synthetic voices.
If an HD voice fails (connection lost, service busy), the app automatically switches to the next engine, then to the system voice, without interrupting the rehearsal.