Everything you need to know about Oteria — what it is, how it works, and what you get.
Oteria is an AI-powered scene partner for actors. Paste a script, assign voices to the other characters, and rehearse your lines out loud with expressive partner voices and cues that follow your lines.
Unlike a fixed recording, Oteria waits for your line before playing the next cue. You can also advance manually, repeat a line or skip ahead.
Anyone who reads scripted dialogue out loud and needs a partner who’s always available:
Paste text, drop a PDF, or photograph a printed script page with your camera. If the formatting is messy, one click runs AI cleanup to help structure it. Review the result against your original before rehearsing.
Assign AI voices to every character but yours. Curated voices cover a range of characters — warm, authoritative, young, old, American, British, and more. Each with individual speed control.
Speak your lines into the mic. Oteria listens for the words in your script and advances to the next cue. The orb responds to the audio. When it is the partner’s turn, you hear the voice and delivery prepared for that line.
Guide the delivery with short cues inside the dialogue:
DETECTIVE: [softly] I know what you did. SUSPECT: [laughs nervously] You have no idea. DETECTIVE: [whispers] Try me.
Whispers, shouts, laughter, sighs and pauses can give the dialogue character. Listen to the result and adjust where needed; delivery cues guide the voice rather than guarantee an exact performance.
Not a script? Paste any passage — a novel chapter, a textbook section, an article, your own writing — pick a voice, and listen. Oteria doubles as a beautiful audio reader.
The prose reader supports MP3 download. For longer passages, split the text into paragraphs: each generated segment is limited to 8,000 characters, or less if the chosen voice requires it. Text-length limits also apply when you use voices from your own ElevenLabs account.
Private access by invitation. Fair-use allowances apply.
Oteria
Private access
Every rehearsal mode, every curated voice, AI cleanup and direction, local performance recordings, and optional connection to your own ElevenLabs voice library where available on your account.
Oteria is currently available by invitation only. We review each request individually; approval is not guaranteed. Access is temporary, granted at our discretion, and may be withdrawn.
Your Account page shows your usage limits. Your own connected voices use your ElevenLabs credits.
Request access and tell us about your school or organisation and what you are working on. Oteria is currently available by invitation only. We review each request individually; approval is not guaranteed. Access is temporary, granted at our discretion, and may be withdrawn. No subscription or payment is required for approved private access.
Oteria runs in your browser on a phone, tablet or computer. Voice matching depends on your browser and microphone permissions. If listening is unavailable or will not start, you can retry or advance lines manually.
You can connect your own ElevenLabs account using an API key to use voices from your personal library, including cloned voices made with the required consent. Your own voices use your ElevenLabs plan and credits; Oteria's included voices still count towards your Oteria usage limit.
No — curated AI voices are included within your Oteria allowance. But if you want to use your own voices and voice-generation credits, connecting your key is optional. ElevenLabs may charge for your usage under its own plans. Connecting your account is not a separate Oteria subscription.
Yes. If you’ve connected your ElevenLabs account and cloned a voice with the required consent (your scene partner, your director, yourself for reference), it shows up automatically in Oteria’s voice picker.
Oteria uses your microphone to compare what you say with the script. Forgiving mode allows some missed or misheard words; strict mode requires a closer match. It follows words, not just their meaning, and can mishear you. Voice matching currently works with English dialogue.
Yes. Performance mode has a dark screen and dimmed controls to reduce screen reflections. Set the beat between turns, hit record on your phone or camera, and go. Oteria records audio, not video. Follow the audition brief’s requirements about readers and AI tools.
Standard screenplay format, CHARACTER: line format, and character names in CAPS with dialogue underneath. PDFs, pasted text from Google Docs or Word, even photographed printed pages. If it’s messy, AI cleanup helps restructure it. Always review the result.
Inline cues like [whispers], [shouting], [laughs], [sighs] that guide how the voice delivers a line. Listen back and adjust them to suit the scene; the result can vary by voice and passage.
Your personal saved scenes are not public. School groups can share assigned scenes with their members. 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. See our privacy policy for processing and retention details.
Yes. Paste a passage — a novel chapter, textbook section, article — pick a voice, and listen. Oteria includes the prose reader under your account’s usage limits. Choosing a voice from your own connected library uses your ElevenLabs credits. Text-length limits still apply.
Ready to rehearse?
Request Access