Turn Screenplays into Multi-Voiced Audiobooks

Hear your screenplay come to life with expressive text-to-speech voices. Table reads on demand, whenever inspiration strikes.

100% Free & Open Source

No Data Collection

macOS, Windows & Linux

Everything You Need

Powerful features designed for screenwriters, producers, and content creators.

ElevenLabs, Minimax, OpenAI, and more. Mix providers per character for optimal results.

Easily assign voices to characters with our visual interface. Optional automated suggestions help match voices to character descriptions.

No telemetry, no tracking, no analytics. Your scripts stay on your machine. Only TTS API calls leave your computer.

Resume interrupted generations. Only regenerate changed dialogue. Save time and API costs.

Native desktop apps for macOS, Windows, and Linux. Same great experience everywhere.

MIT licensed. No subscriptions, no limits, no hidden costs. Bring your own API keys.

Premium Voices

Instant table reads, any time you need them. Hear if your script is working before you share it with the world.

Human-like voices with natural inflection, emotion, and timing that bring your characters to life.

Choose from a wide range of voices with different ages, accents, and speaking styles to match your characters.

Professional-grade audio output suitable for podcasts, audiobooks, and production use.

Watch how easy it is to create multi-voiced audiobooks from your screenplays.

Demo video coming soon

Check back for a full walkthrough of the app

Privacy First

Script to Speech is designed with privacy at its core. We never see your content.

Zero tracking, analytics, or usage data collection.

Scripts stay on your machine. Only TTS calls leave (plus optional voice casting features).

Full source code available. Audit it yourself.

Free to download. Bring your own API keys for TTS providers.

All releases are available on GitHub Releases