How blablabla handles your scripts

Actors work with confidential material. Some scenes are under NDA, some are pre-release, some you just don't want floating around. We get it — one of us used to be one of you.

This page tells you exactly what happens to your data when you use blablabla. No marketing language, no vague reassurances. Just the facts.

What stays on your phone

The following data never leaves your device. It's stored in the app's sandbox, encrypted with iOS file protection (AES-256), and inaccessible when your phone is locked:

• Your saved scene files (JSON)
• All generated audio (cached for offline rehearsal)
• Rehearsal history and accuracy scores
• App preferences and settings

We can't access any of this. Apple's app sandbox means no other app can either. Delete the app and it's all gone.

What passes through the cloud

Two things require cloud processing when you're signed in:

Scene parsing

When you import a scene, the text gets sent to our server, which forwards it to Anthropic (Claude) for parsing into structured dialogue. OpenAI is used as a fallback. The parsed result comes back to your device. We don't store the text on our server.

Anthropic and OpenAI do receive the text to process it. What they do with it afterward is governed by their own data policies: Anthropic, OpenAI.

Voice generation

Dialogue lines get sent to ElevenLabs through our server for text-to-speech. The audio comes back and is cached on your device for offline use. We don't store the text or the audio on our server.

ElevenLabs receives the dialogue text to generate speech. Their handling of that data is governed by their privacy policy.

What's stored on our servers

• Account info (name, email) if you sign in with Google or Apple
• Scene backups (synced for cross-device access, deletable anytime)
• Usage logs (character counts for billing — no script content)

Delete your account in Settings and all of this is removed from our servers.

The fully offline path

If you use blablabla without signing in, nothing leaves your phone. Scenes are parsed on-device using native format parsers (Fountain, FDX, PDF text extraction). Voices use Apple's built-in speech synthesis. No network requests, no third-party services, no data sent anywhere.

You lose premium voices and cloud-powered parsing for unstructured scripts, but your data stays entirely on your device.

No training

None of the services we use (Anthropic, OpenAI, ElevenLabs) train on data sent through their API. We've confirmed this with each provider's API terms. Your scenes are not used to improve anyone's AI.

What we're building

We're not satisfied with the current setup. Even though scene text is processed and not stored on our end, we'd rather it never left your phone at all.

We're working on on-device voice generation to replace the cloud TTS dependency. The goal is a pipeline where scenes can be parsed and voiced entirely on your phone — no server, no third party, nothing to worry about.

That's not ready yet. When it is, we'll update this page.

Questions

If you work under NDA and need specifics about how blablabla handles your material, email elias.munk@gmail.com. Happy to walk through it. For the full legal version, see our privacy policy.