Skip to main content

​
Generate

POST /api/v1/generate
Not all models support every option beyond the basic request. Check the Model Library for model-specific compatibility. Open Model Library.

​
Base URL

https://app.eigenai.com

​
Authentication

Send your API key in the Authorization header as a Bearer token. 
Authorization: Bearer YOUR_API_KEY

​
Parameters

​
Common

NameTypeRequiredDescription
modelstringRequiredThe model ID to use. Find supported models in the Model Library.

​
Conditional

These options are not supported by every model. Use the Model Library to confirm compatibility.

​
Image Generation (Text Prompt)

Generate an image from a text prompt (availability varies by model).
NameTypeRequiredDescription
promptstringOptionalText prompt describing what to generate.
negative_promptstringOptionalWhat to avoid in the output (if supported).
sizestringOptionalRequested output size (if supported).
seednumberOptionalRandom seed for reproducibility (if supported).

​
Image Editing (Upload or URL)

Transform an input image using an instruction prompt.
NameTypeRequiredDescription
image_filefileOptionalUpload the source image file (if supported).
imagefileOptionalSome request types use image instead of image_file for uploaded images.
image_pathstringOptionalReference to the source image (often an HTTPS URL or an internal path), if supported.
promptstringOptionalInstruction describing the desired transformation.
num_inference_stepsnumberOptionalNumber of inference/denoising steps (if supported).
binary_responsebooleanOptionalWhether to return binary image data directly instead of JSON (if supported).
output_formatstringOptionalOutput image format (if supported).
downsizing_mpnumberOptionalDownsample large images for faster processing (if supported).
lora_strengthnumberOptionalLoRA strength knob (if supported).
ranknumberOptionalEdit complexity/strength knob (if supported).
offloadingbooleanOptionalEnable CPU offloading (if supported).
weightstringOptionalSelect an editing profile (if supported).
true_cfg_scalenumberOptionalGuidance/CFG scale (if supported).
sample_stepsnumberOptionalSampling steps (if supported).
sample_guide_scalenumberOptionalSampling guidance scale (if supported).

​
Audio Transcription (ASR)

Transcribe audio into text.
NameTypeRequiredDescription
filefileOptionalAudio file to transcribe (if supported).
languagestringOptionalSpoken language code (if supported).
response_formatstringOptionalDesired output format (if supported).

​
Text-to-Speech (TTS)

Generate audio from text.
NameTypeRequiredDescription
textstringOptionalText to convert into speech (if supported).
voicestringOptionalVoice preset name (if supported).
voice_idstringOptionalSaved voice ID for voice cloning (if supported).
voice_namestringOptionalSaved voice name (if supported).
voice_urlstringOptionalURL to a voice reference audio sample (if supported).
voice_settingsobjectOptionalVoice settings object (if supported).
samplingobject|stringOptionalSampling controls object (if supported). Some clients send it as a JSON string.
streambooleanOptionalEnable streaming mode (if supported).
language_idstringOptionalLanguage identifier (if supported).
exaggerationnumberOptionalExpressiveness/intensity knob (if supported).
temperaturenumberOptionalControls randomness (if supported).
diffusion_stepsnumberOptionalDiffusion steps for audio generation (if supported).

​
Video Generation

Generate videos or image-to-video outputs (availability varies by model).
NameTypeRequiredDescription
frame_numnumberOptionalNumber of frames to generate (if supported).

​
Storage & Delivery

Control where outputs are stored and how they are returned.
NameTypeRequiredDescription
s3_output_pathstringOptionalOptional output path/bucket override (if supported).

​
Request body types

​
JSON request

Content-Type: application/json Use this when you are not uploading files directly.

​
Multipart request (file upload)

Content-Type: multipart/form-data Use this when you need to upload an image file as part of the request.

​
Examples

​
Image generation (JSON)

Generate an image from a text prompt using a JSON request body. 
# Select a model in the Model Library: https://app.eigenai.com/model-library

curl -X POST https://app.eigenai.com/api/v1/generate \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "YOUR_MODEL",
    "prompt": "A fluffy orange tabby cat in a sunlit garden"
  }'

​
Image editing (multipart upload)

Upload an image file and apply an edit instruction prompt. 
# Select a model in the Model Library: https://app.eigenai.com/model-library

curl -X POST https://app.eigenai.com/api/v1/generate \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "model=YOUR_MODEL" \
  -F "prompt=Replace the bag with a laptop" \
  -F "image_file=@/path/to/source.png" \
  -F "num_inference_steps=15" \
  -F "binary_response=true" \
  --output edited.png

​
Audio transcription (multipart upload)

Upload an audio file and receive a transcription. 
# Select a model in the Model Library: https://app.eigenai.com/model-library

curl -X POST https://app.eigenai.com/api/v1/generate \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "model=YOUR_MODEL" \
  -F "file=@/path/to/audio.mp3" \
  -F "language=en" \
  -F "response_format=json"

​
Text-to-speech (multipart form)

Send text and receive an audio response. 
# Select a model in the Model Library: https://app.eigenai.com/model-library

curl -X POST https://app.eigenai.com/api/v1/generate \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "model=YOUR_MODEL" \
  -F "text=Hello, this is a test of the text-to-speech system." \
  -F "voice=Linda" \
  --output speech.wav