Ovi
A unified paradigm for audio-video generation
Header parameters
AuthorizationstringRequiredExample:
sk-yOm1Vc3raDjQluBttyAwSdbVxtWFEAPCbtAZ2uF3yST1xNCYBody
modelstringRequiredExample:
model is the model name
ovi-text-to-videopromptstringRequiredExample:
prompt is the prompt.
A cute baby sea otter.resolutionstring · enumOptionalDefault:
Resolution of the generated video in W:H format. One of (512x992, 992x512, 960x512, 512x960, 720x720, or 448x1120). Default value: "992x512"
Possible enum values: 512x992, 992x512, 960x512, 512x960, 720x720, 448x1120, 1120x448
992x512Example: 992x512Possible values: negative_promptstringOptionalDefault:
Negative prompt for video generation. Default value: "jitter, bad hands, blur, distortion"
jitter, bad hands, blur, distortionExample: jitter, bad hands, blur, distortionnum_inference_stepsintegerOptionalDefault:
The number of inference steps. Default value: 30
30Example: 30audio_negative_promptstringOptionalDefault:
Negative prompt for audio generation. Default value: "robotic, muffled, echo, distorted"
robotic, muffled, echo, distortedExample: robotic, muffled, echo, distortedseedintegerOptional
Random seed for reproducibility. If None, a random seed is chosen.
output_formatstring · enumOptionalDefault:
output_format indicate the output format, default value is url.
urlExample: urlPossible values: Responses
200Success
application/json
post
/v1/videos/generations200Success
Last updated