Skip to content
GEN API

All Generation Types

Every cell or layer generation declares a generation_type and a data object. This page lists every valid combination in one place. See the Creation Cards section for per-type deep dives with examples.

Quick index

Section titled “Quick index”
generation_typeProducesKey models
texttextgemini_2_0_flash, gemini_2_5_pro, gpt_4o, gpt_4o_mini, o3_mini, o4_mini, claude_sonnet_4
image_from_textimagegemini_image, gemini_pro_image, midjourney
video_from_textvideoveo_3, veo_3_fast, veo_3_1, veo_3_1_fast, sora_2, kling_1_6, seedance_pro, seedance_pro_1_5
video_from_imagevideokling_2_1, kling_2_6, veo_3, veo_3_1, sora_2, seedance_lite, seedance_pro, seedance_pro_1_5
video_from_ingredientsvideopika, kling_1_6, seedance_lite, veo_3_1, veo_3_1_fast
speech_from_textaudio(voice_method: my_voices, design_voice, clone_voice)
lipsyncvideosync_so, gen
captionscaption datagemini
mediapass-through upload—
rendercomposite video(no model — uses layer stack)

Text

Section titled “Text”
{
  "generation_type": "text",
  "data": {
    "prompt": "Write a 12-second TikTok hook for {{topic}}",
    "model": "gemini_2_5_pro",
    "variables": { "topic": "San Antonio tacos" }
  }
}

Variables substitute {{key}} in the prompt. Output lives in the cell’s value as a plain string.

Image from Text

Section titled “Image from Text”
{
  "generation_type": "image_from_text",
  "data": {
    "prompt": "a neon-lit street food stall at night, handheld feel",
    "model": "midjourney",
    "aspect_ratio": "9:16",
    "variables": { }
  }
}

Aspect ratios: 1:1, 9:16, 16:9, 4:3, 3:4. Output is a content resource (image).

Video from Text

Section titled “Video from Text”
{
  "generation_type": "video_from_text",
  "data": {
    "prompt": "San Antonio taco truck at golden hour, steam rising, handheld camera",
    "model": "veo_3",
    "aspect_ratio": "9:16",
    "duration": 10,
    "negative_prompt": "no text overlays, no logos"
  }
}

Aspect ratios: 1:1, 9:16, 16:9. Duration: 5 or 10 (model-dependent).

Video from Image

Section titled “Video from Image”
{
  "generation_type": "video_from_image",
  "data": {
    "image_resource_id": 4821,
    "image_tail_resource_id": 4822,
    "prompt": "zoom in slowly, handheld feel",
    "model": "kling_2_6",
    "aspect_ratio": "9:16",
    "duration": 5
  }
}

image_tail_resource_id optional — provides a target end frame for the video.

Video from Ingredients

Section titled “Video from Ingredients”
{
  "generation_type": "video_from_ingredients",
  "data": {
    "prompt": "combine these 3 products in a tabletop pan-around shot",
    "model": "pika",
    "asset_resource_ids": [4821, 4822, 4823],
    "aspect_ratio": "9:16",
    "duration": 5
  }
}

Use when you want the generator to composite multiple uploaded assets.

Speech from Text

Section titled “Speech from Text”

Three voice methods:

my_voices (use a saved voice)

Section titled “my_voices (use a saved voice)”
{
  "generation_type": "speech_from_text",
  "data": {
    "script": "Welcome to Santiago's taco tour...",
    "voice_method": "my_voices",
    "voice_id": "21m00Tcm4TlvDq8ikWAM",
    "enhance_voice": true,
    "speed": 1.0
  }
}

design_voice (voice from a text description)

Section titled “design_voice (voice from a text description)”
{
  "generation_type": "speech_from_text",
  "data": {
    "script": "Welcome to Santiago's taco tour...",
    "voice_method": "design_voice",
    "language": "en",
    "gender": "male",
    "enhance_voice": true
  }
}

clone_voice (voice cloned from audio)

Section titled “clone_voice (voice cloned from audio)”
{
  "generation_type": "speech_from_text",
  "data": {
    "script": "Welcome to Santiago's taco tour...",
    "voice_method": "clone_voice",
    "audio_resource_id": 5921
  }
}

Lipsync

Section titled “Lipsync”
{
  "generation_type": "lipsync",
  "data": {
    "model": "sync_so",
    "video_resource_id": 6001,
    "audio_resource_id": 5921
  }
}

Models: sync_so, gen.

Captions

Section titled “Captions”
{
  "generation_type": "captions",
  "data": {
    "model": "gemini",
    "source_resource_id": 6001
  }
}

Works from either audio or video source. Returns caption timing data usable as a caption layer.

Media (pass-through upload)

Section titled “Media (pass-through upload)”
{
  "generation_type": "media",
  "data": {
    "content_resource_id": 7000
  }
}

No AI generation — just attaches an uploaded asset to the cell. Useful for background music, uploaded b-roll, etc.

Render (composite)

Section titled “Render (composite)”
POST /v1/autocontentengine/:id/cells/:cell_id/render?agent_id=

No generation_type in the body — the render endpoint is dedicated. It composites all layers on the cell in order into one final video. Output lives in the cell’s output_resources.