Built for actors who
take their craft seriously

Everything you need to know about Oteria — what it is, how it works, and what you get.

What is Oteria?

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 a partner that listens to every word you say and delivers cues with real voices, real timing, and real emotion.

It’s not a teleprompter. It’s not playback. You speak, Oteria listens, and the scene moves forward — just like working with another actor.

Who is this for?

Anyone who reads scripted dialogue out loud and needs a partner who’s always available:

  • Actors learning lines for stage, screen, or audition
  • Students rehearsing for drama school or showcases
  • Coaches running remote line sessions
  • Writers hearing their dialogue performed
  • Anyone who wants a passage read aloud beautifully

How it works

1

Bring your script

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 structure it perfectly.

2

Cast the voices

Assign AI voices to every character but yours. Over 50 curated voices across every archetype — warm, authoritative, young, old, American, British, and more. Each with individual speed control.

3

Perform

Speak your lines into the mic. Oteria’s speech matcher listens and advances the scene in real time. The orb — your visual partner — reacts to every word. When it’s the AI’s turn, it delivers with the voice and emotion you chose.

Rehearsal modes

Forgiving mode
Advances on roughly 65% word match. Paraphrase is fine. Best for early read-throughs when you're still finding the character.
Strict mode
Requires ~80% word-perfect match. For memorization and when every word counts.
Hide my lines
Your line text is hidden during your turn. Deliver from memory; the matcher confirms you got it right.
Performance mode
Minimal UI. Dark screen. Just the orb, with dimmed controls when needed. Built for recording audition tapes with fewer reflections off your face on camera. Strict matching is enforced.

Audio direction tags

Control how the AI delivers each line with inline tags:

DETECTIVE: [softly] I know what you did.
SUSPECT: [laughs nervously] You have no idea.
DETECTIVE: [whispers] Try me.

Whispers, shouts, laughter, sighs, pauses — your scene partner doesn’t just read. It performs.

Prose reader

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.

With BYOK connected, the prose reader supports audiobook-length content and MP3 download within your ElevenLabs plan limits.

Plans

Two plans. One unlock. Try free with usage caps.

Standard

$12.99/mo

Everything you need to start rehearsing. Premium AI voices, all modes, full script support. Monthly usage allowance on our shared voice engine.

  • 50+ premium AI voices
  • All rehearsal modes
  • Photo OCR + AI script cleanup
  • Audio direction tags
  • Performance mode
  • Short-form prose reader
  • Monthly usage allowance
Request early access

Pro

$29.99/mo

For serious rehearsal. Generous usage, priority voice engine, and the option to use your own ElevenLabs key for custom voices, languages, and usage under your own plan.

  • Everything in Standard
  • Higher monthly usage allowance
  • Priority voice generation
  • Longer prose reader passages
Request early access
Premium unlock

Pro + BYOK

$29.99/mo

Connect your ElevenLabs key — no extra Oteria charge

Already on Pro? Connect your own ElevenLabs API key when BYOK is available and TTS runs on your account, governed by your ElevenLabs plan limits. If your key expires, you fall back to Pro seamlessly.

  • Usage governed by your ElevenLabs plan
  • Your cloned + custom voices
  • Audiobook-length prose reader within your plan limits
  • Full MP3 download
  • Streaming TTS for long content
  • Any ElevenLabs model
Request early access

Launch plans include a free trial with usage caps.
ElevenLabs starts at $5/month — enough for daily rehearsal.

FeatureStdProPrem
Price$12.99/mo$29.99/mo$29.99/mo
Free trial
Premium AI voices (50+)
Forgiving mode
Strict mode
Hide my lines
Performance mode
Photo OCR
AI script cleanup
Audio direction tags
Prose readerShortLongerElevenLabs plan
Monthly usageCappedHigher capElevenLabs plan
Priority voice engine
Personal / cloned voices
Audiobook mode
Full MP3 download
Streaming TTS
Any ElevenLabs model

Frequently asked questions

Is there a free trial?

Yes. Launch plans include a one-time free trial — enough to run 3–5 scenes and feel what Oteria is like with a real script. No credit card required to start. When your trial scenes are used, pick the plan that fits.

What browser works best?

Chrome on desktop or Android. Oteria uses the Web Speech API for microphone input, and Chrome has the most reliable implementation. Safari works but can be inconsistent. Firefox and Edge have limited speech recognition support.

What is BYOK?

Bring Your Own Key. If you’re on the Pro plan, connect your personal ElevenLabs API key when BYOK is available and you unlock Premium: your custom/cloned voices, audiobook-length prose, and usage governed by your ElevenLabs plan limits. No extra Oteria charge. Voice generation runs through your ElevenLabs account instead of ours.

Do I need an ElevenLabs account?

No — both Standard and Pro include premium AI voices out of the box. But if you’re on Pro and want custom voices, audiobook mode, or usage governed by your own ElevenLabs plan, connecting your key unlocks all of that at no extra Oteria charge. ElevenLabs starts at $5/month.

Can I use my own cloned voices?

Yes — with BYOK. If you’ve cloned a voice in ElevenLabs with the required consent (your scene partner, your director, yourself for reference), it shows up automatically in Oteria’s voice picker.

How does the speech matcher work?

Oteria uses your microphone to listen as you speak. It runs a fuzzy matching algorithm that compares what you said against the script line. In forgiving mode, ~65% word match advances the scene. In strict mode, you need ~80%. It handles contractions, paraphrases, and natural speech patterns.

Can I use Oteria to record an audition tape?

Yes — that’s what Performance mode is for. Dark screen, minimal UI, just the orb. No reflections off your face on camera. Set the beat between turns, hit record on your phone or camera, and go. Use the up arrow to redo any take.

What script formats work?

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 restructures it in one click.

What are audio direction tags?

Inline cues like [whispers], [shouting], [laughs], [sighs] that tell the AI voice how to deliver a line. They’re passed directly to the voice engine — so the AI doesn’t just read the words, it performs them with the emotion you specified.

Is my data private?

Your scripts and scene settings are stored in your account on the server. Generated audio files are cached locally in your browser and are not uploaded back to our servers. Oteria does not record or store your microphone audio. If you connect a BYOK key, it’s encrypted at rest and never exposed after you save it. Sign in is via Google OAuth — no passwords stored.

Can I use Oteria as an audiobook reader?

Yes. Paste any text — a novel chapter, textbook section, article — pick a voice, and listen. Standard and Pro include a prose reader for shorter passages. With BYOK connected on Pro, you can use audiobook-length chapters with streaming playback and MP3 download, subject to your ElevenLabs plan limits.

Ready to rehearse?

Request early access