Skip to main content
Add these tools with 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

Modify and edit images using AI by providing modification instructions
Platform docs: Image to Image
AgentTools.ai_image_to_image(tool_name="...", use_personal_api_key=True, provider="google", api_key="...")
Parameters
​
use_personal_api_key
bool
required
Use your personal API key
​
provider
str
required
Select the model provider. One of: google, openai
​
aspect_ratio
str
Select the aspect ratio for the output image.
​
images
list[str]
Array of input images to modify. Provide 1-3 images for best results.
​
model
str
Select the image-to-image model
​
prompt
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.
​
size
str
Select the size.
​
api_key
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

Generate Text from Image using AI
Platform docs: Image to Text
AgentTools.ai_image_to_text(tool_name="...", use_personal_api_key=True, json_response=True, stream=True, image="...")
Parameters
​
use_personal_api_key
bool
required
Use your personal API key
​
json_response
bool
required
Return the response as a JSON object
​
stream
bool
required
Stream the response
​
image
str
required
The image to analyze. For agent tool calls, pass an existing file reference such as history.MESSAGEID,history.MESSAGE_ID, tool.CALL_ID.OUTPUT_KEY, or $input.NAME; never pass an empty string.
​
max_tokens
int
The maximum number of tokens to generate
​
prompt
str
Instructions on what you want to analyze from the image.
​
system
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
​
temperature
float
The temperature of the model
​
top_p
float
The top-p value
​
json_schema
str
required
The JSON schema to use for the response
​
api_key
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

Generate Text from Audio using AI
Platform docs: Speech to Text
AgentTools.ai_speech_to_text(tool_name="...", use_personal_api_key=True, provider="deepgram", audio="...", api_key="...")
Parameters
​
use_personal_api_key
bool
required
Use your personal API key
​
provider
str
required
Select the model provider. One of: deepgram, openai
​
audio
str
required
The audio for conversion
​
model
str
Select the speech-to-text model
​
tier
str
Select the tier
​
api_key
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

Generate Image from Text using AI
Platform docs: Text to Image
AgentTools.ai_text_to_image(tool_name="...", use_personal_api_key=True, provider="flux", api_key="...")
Parameters
​
use_personal_api_key
bool
required
Use your personal API key
​
provider
str
required
Select the model provider. One of: flux, openai, stabilityai, xai
​
aspect_ratio
str
Select the aspect ratio.
​
prompt
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.
​
size
str
Select the size.
​
api_key
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

Generate Audio from text using AI
Platform docs: Text To Speech
AgentTools.ai_text_to_speech(tool_name="...", use_personal_api_key=True, text="...", api_key="...")
Parameters
​
use_personal_api_key
bool
required
Use your personal API key
​
text
str
required
The string input for conversion.
​
model
str
Select the text-to-speech model
​
voice
str
Select the voice
​
api_key
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

Extract structured data from documents using Reducto 
AgentTools.reducto_extract(tool_name="...")
Parameters
​
api_key
str
default:"''"
Your personal Reducto API key.
​
deep_extract
Any
Enable agentic deep extraction for higher accuracy. Uses iterative verification against the source material.
​
files
Any
Documents to extract data from (up to 2,500 pages per document).
​
json_schema
Any
A JSON schema defining the structure of data to extract. Use descriptive field names.
​
system_prompt
Any
Instructions for how the AI should extract and verify data from the documents.
​
use_personal_api_key
bool
default:"False"
Use your own Reducto API key instead of the platform default.
​
return_citations
bool
default:"False"
Return citation bounding boxes for extracted fields.