Skip to content
Docs menu

Video models

Gemini Omni

On this page

Gemini Omni — high-quality AI video generation.

modelIdgemini-omni-video, gemini-omni-character, gemini-omni-audio
Modalityvideo
PricingSee this model on the Pricing page for the current per-call price (with your markup).

Operations

OperationmodelIdEndpointRequired input
Gemini Omni Videogemini-omni-videoPOST /api/v1/generateprompt
Gemini Omni Charactergemini-omni-characterPOST /api/v1/generateimage_urls, descriptions
Gemini Omni Audiogemini-omni-audioPOST /api/v1/generateaudio_id, name
Poll taskGET /api/v1/task/{id}?model=gemini-omni-video

Gemini Omni Video — gemini-omni-video

FieldTypeRequiredValues / example
promptstringYesDescribe the image you want to generate. Max 20000 characters. (example: Create a 4-second 16:9 advertising loop from the uploaded photo. Hold the framing and add only believable ambient motion: steam rising, fabric settling, light… — full value in the request example)
image_urlsstring[]NoReference images. The base limit is 7; a video uses 2 image slots and each character_id uses 1 image slot. (image URL)
video_liststringNoOptional video input. Only 1 video is allowed and it uses 2 image slots.
durationstringNoNote: when video input is provided, the output duration is determined by the model automatically. This duration parameter will not take effect. (options: 4 | 6 | 8 | 10) (default: 4)
aspect_ratiostringNoVideo ratio (options: 16:9 | 9:16) (default: 16:9)
resolutionstringNoOutput video resolution. Valid values: 720P(default), 1080P, 4k. (options: 720p | 1080p | 4k) (default: 720p)
bash
curl -X POST https://you.bot/api/v1/generate \
  -H "Authorization: Bearer $YOUBOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"modelId":"gemini-omni-video","input":{"prompt":"Create a 4-second 16:9 advertising loop from the uploaded photo. Hold the framing and add only believable ambient motion: steam rising, fabric settling, light drifting slowly across the surface. Keep every product edge and any label text exactly as uploaded. One soft key light, gentle falloff, muted palette. Seamless loop, no cuts, no camera shake. Ultra-realistic commercial cinematography. No logos, no brand references, no watermark, no people.","image_urls":["https://you.bot/examples/grok-imagine-text-to-image.jpg"],"video_list":"example","duration":"4","aspect_ratio":"16:9","resolution":"720p"}}'

Gemini Omni Character — gemini-omni-character

FieldTypeRequiredValues / example
character_namestringNoInput description Max 100 characters.
image_urlsstring[]YesUpload an image file to use as input for the API (image URL)
audio_idsstringNoAudio ID list. Up to 1 IDs are allowed.
descriptionsstringYesCharacter Description Max 20000 characters. (default: Place the provided subject on a windswept coastal clifftop at golden hour, hair and clothing caught in the sea breeze, warm rim light glowing along their edges with a vast shimmering ocean horizon behind.)
bash
curl -X POST https://you.bot/api/v1/generate \
  -H "Authorization: Bearer $YOUBOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"modelId":"gemini-omni-character","input":{"character_name":"example","image_urls":["https://you.bot/examples/grok-imagine-text-to-image.jpg"],"audio_ids":"example","descriptions":"Place the provided subject on a windswept coastal clifftop at golden hour, hair and clothing caught in the sea breeze, warm rim light glowing along their edges with a vast shimmering ocean horizon behind."}}'

Gemini Omni Audio — gemini-omni-audio

FieldTypeRequiredValues / example
audio_idstringYesThe voice to speak the dialogue.
namestringYesInput description Max 210 characters.
voice_descriptionstringNoTextarea description Max 20000 characters. (default: Listen to this street recording and identify the city sounds, from rattling trams to buskers and cafe chatter, then describe the neighborhood and time of day they paint.)
example_dialoguestringNoInput description Max 120 characters.
bash
curl -X POST https://you.bot/api/v1/generate \
  -H "Authorization: Bearer $YOUBOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"modelId":"gemini-omni-audio","input":{"audio_id":"example","name":"example","voice_description":"Listen to this street recording and identify the city sounds, from rattling trams to buskers and cafe chatter, then describe the neighborhood and time of day they paint.","example_dialogue":"example"}}'