AgentTools.<tool>(tool_name="...", ...) or agent.add_tool.<tool>(tool_name="...", ...). Every tool requires a unique tool_name=. Each entry lists the tool’s configuration parameters. See the Agent reference for attaching and running tools.
ai_image_to_image — Image to Image
Modify and edit images using AI by providing modification instructions
Platform docs: Image to Image
bool
required
Use your personal API key
str
required
Select the model provider.
One of:
google, openaistr
Select the aspect ratio for the output image.
list[str]
Array of input images to modify. Provide 1-3 images for best results.
str
Select the image-to-image model
str
Tell the AI model how you would like it to modify the images. Be as specific as possible. For example, you can instruct the model to change colors, add elements, apply artistic styles, or blend multiple images. Must not be empty.
str
Select the size.
str
required
Input your personal API key from the model provider. Note: if you do not have access to the selected model, the workflow will not run
ai_image_to_text — Image to Text
Generate Text from Image using AI
Platform docs: Image to Text
bool
required
Use your personal API key
bool
required
Return the response as a JSON object
bool
required
Stream the response
str
required
The image to analyze. For agent tool calls, pass an existing file reference such as tool.CALL_ID.OUTPUT_KEY, or $input.NAME; never pass an empty string.
int
The maximum number of tokens to generate
str
Instructions on what you want to analyze from the image.
str
Tell the AI model how you would like it to respond. Be as specific as possible. For example, you can instruct the model on what tone to respond in or how to respond given the information you provide
float
The temperature of the model
float
The top-p value
str
required
The JSON schema to use for the response
str
required
Input your personal API key from the model provider. Note: if you do not have access to the selected model, the workflow will not run
ai_speech_to_text — Speech to Text
Generate Text from Audio using AI
Platform docs: Speech to Text
bool
required
Use your personal API key
str
required
Select the model provider.
One of:
deepgram, openaistr
required
The audio for conversion
str
Select the speech-to-text model
str
Select the tier
str
required
Input your personal API key from the model provider. Note: if you do not have access to the selected model, the workflow will not run
ai_text_to_image — Text to Image
Generate Image from Text using AI
Platform docs: Text to Image
bool
required
Use your personal API key
str
required
Select the model provider.
One of:
flux, openai, stabilityai, xaistr
Select the aspect ratio.
str
Tell the AI model how you would like it to respond. Be as specific as possible. For example, you can instruct the model to use bright colors. Must not be empty.
str
Select the size.
str
required
Input your personal API key from the model provider. Note: if you do not have access to the selected model, the workflow will not run
ai_text_to_speech — Text To Speech
Generate Audio from text using AI
Platform docs: Text To Speech
bool
required
Use your personal API key
str
required
The string input for conversion.
str
Select the text-to-speech model
str
Select the voice
str
required
Input your personal API key from the model provider. Note: if you do not have access to the selected model, the workflow will not run
reducto_extract — Reducto Extract
Extract structured data from documents using Reducto
str
default:"''"
Your personal Reducto API key.
Any
Enable agentic deep extraction for higher accuracy. Uses iterative verification against the source material.
Any
Documents to extract data from (up to 2,500 pages per document).
Any
A JSON schema defining the structure of data to extract. Use descriptive field names.
Any
Instructions for how the AI should extract and verify data from the documents.
bool
default:"False"
Use your own Reducto API key instead of the platform default.
bool
default:"False"
Return citation bounding boxes for extracted fields.