Trinetra Brahmand

Gemini image model for high-fidelity text-to-image and image-guided editing.

from 18 credits / image· resolution tiers

Fast Gemini image model for text-to-image and image-guided edits.

from 6 credits / image· resolution tiers

Google Imagen 4 text-to-image with high photorealism.

from 6 credits / image· resolution tiers

Highest-quality Imagen 4 tier for maximum detail and prompt adherence.

from 8 credits / image· resolution tiers

Low-latency Imagen 4 tier for rapid iteration.

from 3 credits / image· resolution tiers

Google Imagen 3 text-to-image generation.

from 6 credits / image· resolution tiers

Low-latency Imagen 3 tier for rapid iteration.

from 3 credits / image· resolution tiers

Mask-based inpainting: insert new content or remove regions from an image.

6 credits / image

Extend an image beyond its borders using a mask defining the new canvas.

6 credits / image

Replace the background of a subject image from a text prompt.

6 credits / image

Subject- or style-customized generation from reference images.

6 credits / image

Upscale an image 2x or 4x while preserving detail.

8 credits / image

Render a product/garment onto a person image (virtual try-on).

8 credits / image

OpenAI GPT Image 1 text-to-image generation.

from 3 credits / image· quality tiers

Smaller, faster GPT Image 1 variant.

from 2 credits / image· quality tiers

OpenAI GPT Image 2 next-generation text-to-image.

from 3 credits / image· quality tiers

Seedream 5 text-to-image generation.

5 credits / image

Create a reusable Kling "element" from a frontal image plus optional reference images.

7 credits / call

Kling V3 text-to-video and image-to-video generation.

from 19 credits / sec· resolution tiers

Kling V3 Omni video generation with extended duration support.

from 29 credits / sec· resolution tiers

Kling V2.5 text/image-to-video with standard and pro modes.

from 10 credits / sec· resolution tiers

Generate video conditioned on multiple input images.

from 19 credits / sec· resolution tiers

Sync a talking head video to a provided audio track.

13 credits / call

Drive a still image with the motion from a reference video.

20 credits / call

Extend a previously generated Kling video by its video_id.

from 19 credits / sec· resolution tiers

Apply a preset Kling visual effect (single- or dual-image scenes).

from 19 credits / sec· resolution tiers

Google Veo 2 text-to-video and image-to-video generation.

from 46 credits / sec· resolution tiers

Google Veo 3 high-quality video with optional first-frame control and audio.

from 37 credits / sec· resolution tiers

Lower-latency Veo 3 tier with first-frame control and audio.

from 11 credits / sec· resolution tiers

Google Veo 3.1 video generation with first/last frame control and audio.

from 37 credits / sec· resolution tiers

Lower-latency Veo 3.1 tier with first/last frame control and audio.

from 11 credits / sec· resolution tiers

Extend an existing Veo video stored at a gs:// GCS URI.

from 37 credits / sec· resolution tiers

Veo video generation guided by reference images (up to 3).

from 37 credits / sec· resolution tiers

OpenAI Sora 2 text-to-video generation.

13 credits / sec

Higher-quality OpenAI Sora 2 Pro text-to-video tier.

from 39 credits / sec· resolution tiers

Seedance 2 Pro video tier with optional generated audio.

from 17 credits / sec· resolution tiers

Low-latency Seedance 2 tier with optional generated audio.

from 9 credits / sec· resolution tiers

Seedance 1.5 Pro video generation with optional generated audio.

from 17 credits / sec· resolution tiers

Animate a character image with the performance from a driving video.

24 credits / sec

HappyHorse 1 text/image-to-video generation.

from 19 credits / sec· resolution tiers

Sync.so lip-sync: align a video to an audio track with selectable model.

65 credits / call

ElevenLabs text-to-speech with selectable voice and model.

13 credits / 1k chars

Generate audio from a text prompt with Kling.

3 credits / sec

Generate sound effects and/or background music for a video.

4 credits / call

Generate sound effects from a text description.

389 credits / 1k chars

Isolate clean speech from a noisy audio recording.

16 credits / call

Multi-speaker dialogue synthesis from an ordered list of lines.

13 credits / 1k chars

Generate music from a text prompt.

1 credits / sec

Design a new synthetic voice from a description plus preview text.

13 credits / call

Transcribe speech from an audio file to text.

6 credits / call

Convert source audio to a different target voice.

16 credits / call

Create a cloned voice from one or more audio samples.

13 credits / call

Sarvam multilingual Indian-language text-to-speech.

3 credits / 1k chars

Google Cloud Text-to-Speech synthesis.

1 credits / 1k chars

Talking avatar / digital human (planned — needs an external fal/piapi provider).

19 credits / sec

Kling text-to-speech (planned — needs an external fal/piapi provider).

39 credits / 1k chars

Kling voice cloning (planned — needs an external fal/piapi provider).

13 credits / call

Image recognition / understanding (planned — needs an external provider).

2 credits / call

AI multi-shot video sequencing (planned — needs an external provider).

19 credits / sec

Place a product into new scenes (deprecated preview — migrating to gemini-2.5-flash-image).

6 credits / image

Kling Kolors text-to-image (executor coded; awaiting a Kling image resource pack).

6 credits / image

Outpaint/expand an image in any direction (awaiting a Kling image resource pack).

6 credits / image

Render a garment onto a person (awaiting a Kling image resource pack).

6 credits / image

OpenAI DALL-E 3 text-to-image (executor coded; not enabled on this account).

6 credits / image

OpenAI DALL-E 2 text-to-image (executor coded; not enabled on this account).

3 credits / image