Skip to content
OniraOnira
AI Orchestration

Multi-Model AI Routing.

Not every layer needs the same AI model. Onira routes stills to Gemini Flash Image, animates them with Pixverse v6, locks narration first with ElevenLabs eleven_v3, and scores each act with ElevenLabs Music.

RouterGeminiPixverseEL v3EL Music
Intelligent routing

The right model for every scene.

Onira's routing engine evaluates scene requirements and selects the optimal AI model. Here's how each model contributes.

Still frames

Gemini Flash Image

Generates the source still frame for every scene. The ImageDirector agent (Gemini 3.1 Pro) reviews each image prompt before generation, ensuring appearance and composition are locked in before motion is planned.

Used for: All scene stills, character portraits, establishing frames

Motion clips

Pixverse v6

Animates every still frame into a 1–14 second motion clip. The VideoDirector agent (Gemini 3.1 Pro) plans the motion prompt separately from the image prompt — appearance and movement are never conflated.

Used for: All video clips, image-to-video animation, scene motion

Narration

ElevenLabs eleven_v3

Generates per-beat narration in 30+ languages. Audio is produced first — narration durations are locked before any visual is generated, so visuals always conform to audio timing.

Used for: Narration per beat, 30+ BCP-47 languages, character voices

Score

ElevenLabs Music

Generates one original soundtrack per act. Genre, tempo, and mood are derived from the video's narrative arc. No stock music — every score is composed fresh for the video.

Used for: Per-act original soundtrack, genre and mood matching

Under the hood

How routing decisions
are made.

01

Scene Analysis

Narration is generated first via ElevenLabs eleven_v3 — beat durations are locked before any visual is planned. The ImageDirector agent then analyzes each scene for appearance and composition.

02

Model Scoring

Gemini Flash Image renders the still frame (Nano Banana 2 is the quota-exhaustion fallback). The VideoDirector agent plans the motion prompt separately — appearance and motion prompts never overlap.

03

Generation & Validation

Pixverse v6 animates each still into a 1–14 second clip. ElevenLabs Music composes one original score per act. Remotion assembles all layers into the finished video.

Benefits

Why multi-model beats
single-model.

No single AI model is the best at everything. Onira's approach ensures every scene gets the best possible result.

Best quality per scene

Gemini Flash Image for stills, Pixverse v6 for motion, ElevenLabs for narration and score. Each layer gets a dedicated specialist. Single-model tools use the same model for everything — Onira orchestrates each layer individually.

Cost optimization

Not every scene needs the most expensive model. Simple transitions use efficient models, while hero shots get premium ones. Smart allocation reduces cost without sacrificing quality.

Future-proof architecture

When new AI models launch - and they launch constantly - Onira integrates them into the routing engine. Your videos automatically benefit from the latest advances.

In practice

Example routing for
a documentary.

A 10-minute deep ocean documentary. Here's how Onira routes different types of scenes.

Scene TypeAssigned ModelReason
Sweeping ocean vistaGemini Flash Image → Pixverse v6Still frame animated into clip
Jellyfish bioluminescenceGemini Flash Image → Pixverse v6Detail still, gentle motion
Submarine descent sequenceGemini Flash Image → Pixverse v6Mechanical motion via Pixverse
Extended coral reef panGemini Flash Image → Pixverse v6Wide still, slow pan motion
Per-beat narrationElevenLabs eleven_v3Audio locked first, 30+ languages
Act soundtrackElevenLabs MusicOriginal score per act
Output

What you actually get.

Routing decisions · Deep Ocean Documentary

Sc. 01–67All stillsGemini Flash ImagePrimary still generator
Sc. 01–67All motion clipsPixverse v6Image-to-video, 1–14s
Sc. beatsNarration per beatElevenLabs eleven_v3Audio-first, 30+ langs
Sc. actsSoundtrack per actElevenLabs MusicOriginal score
Sc. finalAssemblyRemotionRenders finished video

67 scenes routed automatically · Stills → motion clips via Gemini + Pixverse · Narration locked first · Zero manual decisions

Every scene,
the best model.

Experience multi-model AI video production today. Let Onira route every scene to perfection.

From $149/mo · Cancel anytime