Gemini Omni 1.1 Flash API Pricing

Enum voice ID, used to select a preset voice character. achernar - female, soft, high pitch achird - male, friendly, mid pitch algenib - male, raspy, low pitch algieba - male, easygoing, mid-low pitch alnilam - male, steady, mid-low pitch aoede - female, brisk, mid pitch autonoe - female, bright, mid pitch callirrhoe - female, easygoing, mid pitch charon - male, intellectual, low pitch despina - female, smooth, mid pitch enceladus - male, breathy, low pitch erinome - female, clear, mid pitch fenrir - male, lively, younger pitch gacrux - female, mature, mid pitch iapetus - male, clear, mid-low pitch kore - female, capable, mid pitch laomedeia - female, cheerful, mid-high pitch leda - female, young, mid-high pitch orus - male, steady, mid-low pitch puck - male, cheerful, mid pitch pulcherrima - genderless, forward, mid-high pitch rasalgethi - male, intellectual, mid pitch sadachbia - male, vivid, low pitch sadaltager - male, knowledgeable, mid pitch schedar - male, smooth, mid-low pitch sulafat - female, warm, mid pitch umbriel - male, smooth, low pitch vindemiatrix - female, gentle, mid pitch zephyr - female, bright, mid-high pitch zubenelgenubi - male, casual, mid-low pitch

Voice name. Maximum length: `210` characters.

Voice characteristic description used to define timbre, style, speaking rate, emotion, and other traits. Maximum length: `20000` characters.

Example dialogue, such as "Hello, I am Adam". Maximum length: `120` characters.

Character description used to define the appearance, identity, style, clothing, or personality of the character.

Array of character reference image URLs. Up to 2 images are supported. Index 0 is the portrait image, and index 1 is the body image. The body image is optional, but if provided, the portrait image must be present at index 0. Image limits: - Each image must be no larger than `20MB` - Use a publicly accessible image URL

minItems: 1

maxItems: 2

Array of audio IDs generated by the `gemini-omni-audio` endpoint. These can be used to provide voice traits, tone, or persona guidance for the character.

Character name

The model name used to generate the task. This field is required. This interface must use the `google/gemini-omni-flash-1-1` model.

Values: "google/gemini-omni-flash-1-1"

Default: "google/gemini-omni-flash-1-1"

The callback URL for task completion notifications. This parameter is optional. If provided, the system will send a POST request to this URL when the task is completed, regardless of whether it succeeds or fails. If not provided, no callback notification will be sent.

Input parameters for the multimodal video generation task.

The video prompt, used to describe the visual content, style, cinematography, or character actions of the target video.

maxLength: 20000

An array of image URLs. Multiple reference images can be uploaded to provide references for characters, scenes, styles, or storyboards. Image limitations: - Each file must not exceed `20MB` - Use publicly accessible image URLs - Maximum of 7 images - Note: This field is mutually exclusive with the first-frame image (`first_frame_url`) and cannot be provided at the same time.

The URL of the first-frame image. Used to specify the starting frame of the generated video. Note: This field is mutually exclusive with `image_urls`, `audio_ids`, `video_list`, and `character_ids` and cannot be provided at the same time.

The URL of the last-frame image. Used to specify the ending frame of the generated video. Note: The last-frame image cannot be used alone and must be provided together with the first-frame image (`first_frame_url`).

An array of audio IDs generated by the `gemini-omni-audio` interface. Used to provide narration, dialogue, background music, or sound references for the video. Up to 3 items. Note: This field is mutually exclusive with the first-frame image (`first_frame_url`) and cannot be provided at the same time.

An array of video clips. Each element describes a video asset that can be used for generation and its trimming time range. Video limitations: - Each file must not exceed `100MB` - Video duration must not exceed `30s` - `ends` should be greater than `start` - The difference between the end and start times must not exceed `10s` - Maximum of 1 item, occupying two image slots - Note: This field is mutually exclusive with the first-frame image (`first_frame_url`) and cannot be provided at the same time.

The video URL. Each video file must not exceed `100MB`, and the video duration must not exceed `30s`.

The start time, in seconds.

minimum: 0

The end time, in seconds. It should be greater than `start`. The difference between the end and start times must not exceed 10 seconds.

minimum: 0

An array of character IDs generated by the `gemini-omni-character` interface. Used to provide character appearance, identity, or person references for the video. Up to 3 character IDs. Each uses 1 image slot (2 if created with portrait + body images). Total slots (images + videos × 2 + character slots) ≤ 7. Note: This field is mutually exclusive with the first-frame image (`first_frame_url`) and cannot be provided at the same time.

The duration of the generated video, in seconds. Valid values are 4, 6, 8, and 10. This parameter only takes effect when there is no video input. If video input is used, the output duration is determined by the model, and the `duration` parameter will be ignored. Note: When video input is provided, the output duration is automatically determined by the model. In this case, the `duration` parameter will not take effect.

Values: "4", "6", "8", "10"

The aspect ratio of the generated video. `16:9` is landscape, and `9:16` is portrait.

Values: "16:9", "9:16"

The resolution of the generated video. Valid values are 360p, 720p, 1080p, and 4k.

Values: "360p", "720p", "1080p", "4k"

Default: "720p"

The random seed. Valid range: [0, 2147483647]. If not specified, the system will automatically generate a seed. A fixed seed can improve result reproducibility, but because the model itself is stochastic, results may still vary.