Character AI

This page is auto-generated from model configurations. Last updated: 2026-03-13.

This reference lists all available Character AI video generation models and their parameters. Use these parameter names when calling the Generation API.


Ovi I2V

Ovi can generate videos with audio from image and text inputs

Model ID: model_ovi-i2v

Capabilities: img2video

LLM Markdown: https://app.scenario.com/api/models/model_ovi-i2v/markdown

ParameterTypeRequiredDefaultMinMaxAllowed ValuesDescription
promptstringYes----Prompt for the video
imageUrlfileYes----Input image containing a human subject, face or character.
negativePromptstringNo----Negative prompt for the video
audioNegativePromptstringNo----Negative prompt for the audio
numInferenceStepsnumberNo30150-Number of inference steps.
seednumberNo----Use a seed for reproducible results. Leave blank to use a random seed.

Ovi T2V

A unified paradigm for audio-video generation

Model ID: model_ovi-t2v

Capabilities: txt2video

LLM Markdown: https://app.scenario.com/api/models/model_ovi-t2v/markdown

ParameterTypeRequiredDefaultMinMaxAllowed ValuesDescription
promptstringYes----Prompt for the video
resolutionstringNo992x512--448x1120, 512x960, 512x992, 720x720, 960x512, 992x512, 1120x448Resolution of the video.
negativePromptstringNo----Negative prompt for the video
audioNegativePromptstringNo----Negative prompt for the audio
numInferenceStepsnumberNo30150-Number of inference steps.
seednumberNo----Use a seed for reproducible results. Leave blank to use a random seed.