The questions
we get most often.

An iOS app that turns multi-speaker scripts into produced podcast audio. Paste a dialogue script, assign AI voices to each character, generate speech and sound effects, then mix and export the result — all on iPhone or iPad.

For real audio generation, yes — flexVox brings your own ElevenLabs API key (a free tier is available at elevenlabs.io). Demo mode works with no account, generating silent placeholder audio so you can explore every feature first.

iPhone and iPad running iOS 26.4 or later.

Script import, parsing, and review work offline. Audio generation requires an internet connection to reach the ElevenLabs API. Demo mode works fully offline.

Colon (`HOST: Welcome`), bracket (`[Host] Welcome`), parenthesis (`(Host) Welcome`), standalone-name lines followed by dialogue, SFX tags, music tags, scene tags, and chapter / act / part tags.

Every detected attribution has a confidence score. Low-confidence turns are highlighted for review. Tap any turn to reassign its speaker, batch-assign unreviewed turns, or merge duplicate speakers.

Yes. The Script Edit sheet lets you modify the raw text and re-parse. Be aware that re-parsing replaces existing speaker assignments and deletes any generated audio for the project.

There's no hard limit on the number of speakers per project. Dialogue generation batches up to 10 unique voices per API call; larger casts are automatically split across multiple batches.

Yes — independent sliders for stability, similarity boost, style exaggeration, and speed, plus a speaker boost toggle. V3 models use a simplified control set.

Sound effects clamp between 0.5 and 30 seconds. Music clamps between 3 seconds and 10 minutes. Set the duration in the script tag, e.g. `[SFX: rain (5s)]`.

Audio that was already generated before the failure or cancellation is preserved. The app offers a `Resume` button that picks up where it left off, skipping turns that already have audio.

Yes. Swipe a turn in post-production or use its context menu. The new take is saved as a variant — your previous take isn't overwritten.

Each turn can have multiple takes. When you regenerate, the new audio is added alongside existing ones. Play each variant, mark one as active, delete the rest.

Two levels: a project-wide default pause set in post-production, and per-turn custom pauses set with the `Adjust Pauses` toggle and individual sliders. Per-turn pauses override the project default for that turn.

The final mix is exported as an M4A (AAC) file. The export sheet includes platform-specific loudness presets and can also export transcripts or captions as SRT, VTT, JSON, or plain text.

A show, also called a production, is a container for related episodes. It stores a persistent cast bible with character profiles and voice assignments, a default format and tone, intro / outro or transition sounds, and an episode template.

No. Standalone projects work on their own. You can promote a project to a series later from the project list, which copies its speakers, voice assignments, and character profiles into a new production.

AI script writing supports OpenAI and Anthropic Claude. You can configure both providers, switch between them at generation time, or copy a detailed prompt to use in another AI tool.

flexVox shows an estimated cost before generation based on prompt length and provider. Provider API charges are paid directly to OpenAI or Anthropic; flexVox itself does not charge for those API calls.

Your ElevenLabs API key is stored in the iOS Keychain — the same secure storage iOS uses for passwords. It is never written to a plain file or sent anywhere other than the ElevenLabs API.

No analytics frameworks, no tracking SDKs, no server-side data collection. Your scripts, audio, and projects stay on your device. The only network calls are to the ElevenLabs API when generating audio or browsing voices.