About Oteria

How it started

Oteria began with a scene Jack needed to bring to life.

Jack is an actor. He was directing a short film in which he also plays the lead — opposite an AI therapist. Not a voiceover. Not a background detail. A real character in the scene, with its own voice, its own emotional range, and the ability to respond to him in real time.

He needed expressive voices, delivery he could direct, and cues that followed his lines rather than a fixed recording. The tools he tried did not bring those things together in the way the film needed.

So Jack developed Oteria: an AI scene partner with expressive voices, audio direction tags for whispers, pauses and laughter, and a speech matcher that follows the actor word by word.

What began as a tool for the film became a way to rehearse beyond the set.

Why he’s sharing it

Every actor knows the problem. You have an audition tomorrow. You need to run the scene but there’s nobody around. Your roommate reads the lines off their phone in a monotone. Your friend is busy. You end up reading both parts yourself, imagining the timing, hoping the rhythm lands.

What began as a solution for his film also answered a familiar rehearsal problem: how to work on a scene when no reader is available. Jack is now sharing Oteria through private access so other actors can use it for self-tapes, line learning and table reads without assembling the full cast.

What makes it different

Oteria was built from a performance requirement, not a product roadmap. The AI had to be good enough to appear in a film. That bar shaped every decision — the voice quality, the matching sensitivity, the timing between lines, the way audio direction tags let you sculpt a delivery down to a whisper or a laugh.

The visual interface got the same treatment. Performance mode strips the screen to pure black with a single luminous orb that breathes with the audio — bright when the AI speaks, softly pulsing when it listens. No script text, no prominent controls, no bright UI glow reflecting off your face on camera. It feels like a presence in the room without ever pulling you out of the scene.

Oteria treats the reader as a scene partner. It listens for your line and gives you an expressive cue to respond to. And when the scene is done, it’s ready to go again — no breaks or scheduling.

The voices and listening

Oteria follows English dialogue. Speech recognition uses your browser’s recognition service, which may send audio to its provider for processing. Availability varies by browser. The AI voices come from ElevenLabs. Script cleanup and photo-to-text extraction are handled by Anthropic’s Claude. Check imported text against your original script before rehearsing.

Privacy first

Saved scripts and scenes live in your private account so you can return to them later. We don’t train AI models on your content, and saved scenes are not public by default. With Record performance enabled and microphone permission granted, supported browsers record your voice together with the scene partner. Completed takes are saved in this browser and can be downloaded as an MP3. They do not sync between devices or upload automatically. Download any take you want to keep, as clearing browser data or browser storage cleanup can remove it. For scenes with sharing available, choosing Share uploads the take and its script, cast details and duration. Anyone with the link can listen and read the shared script, without signing in. Project and assigned-scene recordings can be downloaded locally, but cannot be published through Share. Read the full details in our privacy policy.

Created by Jack

Jack developed Oteria around his own experience as an actor and director. The questions behind it are practical: does the voice serve the scene, does the timing feel natural, and can the actor stay focused on the performance? The performance comes first.

Get in touch

We’d genuinely love to hear from you — whether it’s feedback, a partnership idea, or a story about how you used Oteria on a project.