flexVox in print.

flexVox is a podcast production app for iPhone and iPad that transforms written scripts into polished, multi-voice audio. It is designed for solo podcasters, audio drama writers, and educators who need professional-sounding dialogue without hiring voice actors or using desktop editing software.

The workflow starts with a script. Users paste their dialogue into the app, and a built-in parser detects speaker names, sound effect prompts, and music cues across several common script formats. A confidence-scored review screen lets users verify attributions, correct mistakes, and merge duplicate speakers.

Next, users assign AI voices. The app connects to the ElevenLabs voice library, where users can search, filter, and preview voices before mapping them to characters. Each voice profile includes independent controls for stability, similarity boost, style exaggeration, and playback speed. A quick preview streams a sample dialogue with assigned voices before committing to a full generation run.

During generation, the app produces speech audio for every dialogue line, plus sound effects and music from text prompts embedded in the script. A real-time progress screen shows the current turn, completion percentage, and estimated time remaining. If generation is interrupted, users can resume from where it stopped.

Post-production tools let users play each segment individually, regenerate lines that need improvement, compare multiple takes side by side, adjust per-turn pauses, and exclude segments from the final output. When editing is complete, flexVox mixes all active turns into a single M4A file for export via the iOS share sheet.

A built-in demo mode produces silent placeholder audio, allowing users to explore every screen and feature before connecting an ElevenLabs account.