Every feature,
in the order you'll meet it.

Paste or type a script. The import screen ships with a collapsible format guide and a built-in sample script for first-time users.

The parser detects speakers, SFX, music cues, scene markers, and chapter markers across colon (`HOST:`), bracket (`[Host]`), parenthesis (`(Host)`), standalone-name, `[SCENE:]`, `[CHAPTER:]`, `[ACT:]`, and `[PART:]` formats.

Every detected turn shows its speaker with a green / orange / red confidence indicator. Lines that need attention are highlighted; the rest you scroll past.

Add new speakers, merge duplicates, batch-assign unreviewed turns, and give each character a unique color badge for visual distinction.

Use `[SCENE: Title]`, `[CHAPTER: Title]`, `[ACT: Title]`, or `[PART: Title]` tags to structure a script. Scenes appear as collapsible sections, can be added manually, and turns can move between scenes.

Insert dialogue, SFX, or music turns at any point from review. Assign the new turn to a speaker and scene, or delete turns from the context menu.

Edit the raw script after import. An audio-tag reference panel makes inserting SFX and music cues quick. Re-parsing replaces existing speaker assignments and generated audio (with a confirmation warning).

Browse the ElevenLabs catalog with search, category and type filters, and paginated results. Inline play / stop preview on every row.

Map each speaker to a TTS voice. `Cast All Speakers` opens a casting session with speaker progress, visible assignments, auto-advance, and inline AI casting suggestions.

Assign voices to every unvoiced speaker in one tap. flexVox analyzes each speaker's role, generates a search query from an AI archetype suggestion, and selects the best-match voice while preserving manual assignments.

Independent sliders for stability, similarity boost, style exaggeration, and speed, plus a speaker boost toggle. V3 models show a simplified panel.

Per-voice metadata, verified languages, category, and a `Find Similar` feature that analyzes the voice's preview audio and returns related options from the catalog.

Per-project rules for tricky names and technical terms. Alias replacements or phoneme overrides in IPA or CMU Arpabet. Synced to ElevenLabs before generation.

Each speech turn is generated with the assigned voice profile and contextual parameters (previous / next text, request-ID history) for voice continuity. SFX and music turns hit dedicated endpoints.

Batch multiple speech turns into a single multi-speaker call for natural conversational flow. The app respects a 2,000-character and 10-unique-voice limit per batch and splits larger scripts automatically.

Write `[SFX: door slam (2s)]` directly in your script. flexVox generates the effect with a duration clamped between 0.5 and 30 seconds, with optional seamless-loop requests for ambient beds.

Write `[Music: upbeat jazz intro (10s)]` and the app generates it. Duration clamps between 3 seconds and 10 minutes; an instrumental-only flag is available.

Add a background music layer that spans the whole episode. Describe the mood and style; flexVox generates a track sized to the total dialogue duration and gives the project its own volume control.

An animated circular progress ring shows percentage, current turn, estimated time remaining, and elapsed time. Cancel at any point — already-generated audio is preserved.

If generation is interrupted or cancelled, the app detects which turns already have audio and offers a one-tap resume that skips completed turns.

Every generated file is checked for corruption, silence, and minimum duration. Files with detected issues are flagged with a warning badge in post-production.

With no API key configured, a mock TTS service returns silent WAV audio with realistic durations. Every screen — import, review, voices, generate, edit, mix, export — works end to end.

Play each segment individually. Simple and advanced modes are available, with an interactive mini timeline, current playback time, and `Play from Here` for continuous sequential playback.

Swipe a turn or use its context menu to regenerate it. The new take is saved as an additional variant — your previous take is never overwritten.

Each turn can have multiple takes. Browse them, play them back to back, mark one as active, and delete the rest. `Keep Only Active` cleans up across the whole project.

Two levels of control: a project-wide default and per-turn custom pauses dialed in with sliders from 0 to 10 seconds.

Exclude individual turns from the final mix without deleting them. Excluded turns appear with strikethrough text and are skipped during mixing — toggle them back any time.

Edit a turn's dialogue text directly from post-production. After saving, optionally regenerate the audio immediately to match.

Mark music or SFX turns to play underneath dialogue instead of sequentially. Underlay turns live on a dedicated audio track with per-turn volume control.

Underlay and background music automatically lower when dialogue plays, then rise during pauses. Duck depth, attack, and release controls shape the curve.

Mix dialogue, crossfade overlay, ducked underlay, and background music into a single M4A / AAC file with configurable pauses and peak normalization.

The playback screen shows the script with timestamps, speaker badges, active-turn highlighting, auto-scroll, tap-to-seek, and word-level highlighting when alignment data is available.

When a project has completed audio, Script and Production tabs show a compact bar with project name, play / pause, progress, and current time. Tapping it opens Export.

Stream the first ~2,000 characters of dialogue with assigned voices via the ElevenLabs dialogue API. A segment timeline shows colored bars per speaker.

Export from the playback screen or with Cmd+E. Choose Spotify, Apple Podcasts, YouTube, Broadcast, or Custom loudness presets, then share audio plus SRT, VTT, JSON, or plain-text transcripts.

Create, rename, duplicate, and delete projects. The list is searchable and sorted by most recently updated.

Script. Production. Export. A three-step progress bar shows readiness while keeping every tab accessible. Generation progress follows you with a tap-to-view banner.

Deep-copy a project including script, turns, speakers, voice profiles, and pronunciation rules. Audio is intentionally not copied — the duplicate is a fresh starting point.

A pre-populated sample script is one tap away from the empty-state screen.

Start from Interview, Audio Drama, True Crime, Newscast, or Narration templates. The first-launch empty state presents template cards before a blank page.

Enter and store an ElevenLabs API key in the iOS Keychain. Remove it any time. The app clearly displays whether it's running in API or demo mode.

Test the saved key by fetching available voices. Pick the default TTS model from Multilingual v2, Turbo v2.5, Turbo v2, English v1, or v3.

Create ongoing productions with persistent cast, format, tone, narrator mode, episode numbering, and reusable audio identity.

Recurring and guest cast members can carry role, age, biography, personality, speaking style, and optional voice assignment into every new episode.

Define reusable show segments such as Intro, Main Topic, Listener Q&A, and Outro. Segments are reorderable and can include descriptions.

Set a production's default format, tone, narrator mode, intro music, outro music, and transition sounds.

Convert any standalone project into a show from the project list. Speakers, voice assignments, and character profiles become the production cast.

Create new episodes from a production with the show's cast, voice assignments, character profiles, narrator mode, and season numbering already applied.

Generate scripts in-app with OpenAI or Claude. Configure format, tone, speaker count, scenes, chapters, expression tags, SFX, music, and provider before generation.

Speaker profiles feed role, age, biography, personality, and speaking style into AI script generation for more distinct characters.

Upload text reference materials such as research, outlines, and articles. flexVox sends them as context without asking the model to copy them verbatim.

Choose Full Cast, Single Narrator, or Narrator + Cast. The mode affects both AI script generation and voice mapping.

Import reusable M4A, MP3, WAV, and AIFF sound effects or music into a global library that persists across projects.

Tag sounds with comma-separated keywords, search by name or tag, and filter by category.

Assign library sounds to SFX and music turns in post-production. The file is copied into the project's audio assets while the library source remains reusable.

A searchable guide in Settings covers scripts, voices, generation, post-production, shows and series, and advanced topics.

Dismissible tips appear at key workflow points, then stay dismissed once closed.

Settings uses a spacious NavigationSplitView with categories for Subscription, API Keys, Text-to-Speech, AI Writing, Display, Data & Sync, and About.

ElevenLabs, OpenAI, and Claude keys live in one secure section with save, test, status, and remove controls for each provider.

Test ElevenLabs by fetching available voices; test OpenAI and Claude with a round-trip API call. Status appears inline.

Choose the default ElevenLabs model and text normalization settings from a dedicated Text-to-Speech section.

Light taps for selections, medium impacts for state changes, ticks for slider adjustments, notification haptics for generation milestones and errors.

Ephemeral feedback at the top of the screen for assignments, duplications, regeneration completion, and errors. Four styles, matching icons, VoiceOver-accessible.

If the local SwiftData store is corrupted on launch, the app attempts recovery in three tiers: normal open, delete-and-retry, and in-memory fallback. Users are notified of any data reset.

Press Cmd+K to search actions, projects, and shows. Results are grouped and keyboard navigable.

Use Cmd+1/2/3 for workflow tabs, Cmd+G for Production, Cmd+E for Export, Space for playback, arrows for skipping, Cmd+R for regeneration, and M to mute.

No projects, no shows, no sounds, failed searches, and unready tabs share a unified branded empty-state component.

List views use shimmer rows while content is being prepared.

List rows animate in with a staggered fade-and-slide entrance across the app.

Up to three projects, the complete script workflow, voice browsing and assignment, per-turn generation with your own API key, post-production basics, follow-along playback, Podcast export, and demo mode.

Studio unlocks unlimited projects, Shows and Series, Auto-Cast, dialogue generation mode, background music, underlay and auto-ducking, export presets, AI writing, Sound Library, pronunciation dictionary, templates, and pacing reports.

Settings shows subscription status, purchase, restore, and transaction updates through StoreKit 2.

Studio-only features display a small badge and open the upgrade sheet with the relevant feature highlighted.