Multi-Modal nodes

Add these nodes with the pipeline builder: pipeline.add(name="...").<node>(...). Each entry lists the node’s configuration parameters. See the Pipeline reference for add, run, and lifecycle methods.

`ai_audio_operations` — Leverage AI for Audio operations

Leverage AI for Audio operations

pipeline.add(name="node").ai_audio_operations()

Parameters

str

default:"''"

`ai_image_operations` — Leverage AI for Image operations

Leverage AI for Image operations

pipeline.add(name="node").ai_image_operations()

Parameters

str

default:"''"

`ai_image_to_image` — AI Image To Image

Modify and edit images using AI by providing modification instructions

Platform docs: AI Image To Image

pipeline.add(name="node").ai_image_to_image(provider="google", model="gemini-2.5-flash-image", api_key="...", size="1024x1024")

Parameters

bool

default:"False"

Use your personal API key

str

required

Select the model provider. One of: google, openai

str

required

Select the image-to-image model

Show Allowed values

gemini-2.5-flash-image, gemini-3-pro-image-preview, gpt-3.5-turbo, gpt-4, gpt-4-turbo, gpt-4.1, gpt-4.1-mini, gpt-4.1-nano, gpt-image-1.5, gpt-image-2, o1, o3, o3-mini, o4-mini

str

default:"''"

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

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

str

default:"'1:1'"

Select the aspect ratio for the output image.

Show Allowed values

16:9, 1:1, 21:9, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16

AcceptsImageList

Array of input images to modify. Provide 1-3 images for best results.

str

required

Select the size. One of: 1024x1024, 1024x1536, 1024x1792, 1536x1024, 1792x1024, 256x256, 512x512, auto

`ai_image_to_text` — AI Image To Text

Generate Text from Image using AI

Platform docs: AI Image To Text

pipeline.add(name="node").ai_image_to_text(provider="anthropic", model="chatgpt-4o-latest", api_key="...", image=...)

Parameters

bool

default:"False"

Use your personal API key

bool

default:"False"

Return the response as a JSON object

bool

default:"False"

Stream the response

str

required

Select the provider that will be used to analyze image. One of: anthropic, fireworks, google, openai, together, xai

str

required

Select the image analyzing model.

Show Allowed values

chatgpt-4o-latest, claude-3-5-haiku-20241022, claude-3-7-sonnet-20250219, claude-3-haiku-20240307, claude-haiku-4-5-20251001, claude-opus-4-1-20250805, claude-opus-4-20250514, claude-opus-4-5-20251101, claude-opus-4-6, claude-opus-4-7, claude-opus-4-8, claude-sonnet-4-20250514, claude-sonnet-4-5, claude-sonnet-4-6, gemini-2.0-flash-001, gemini-2.0-flash-lite-preview-02-05, gemini-2.5-flash, gemini-2.5-pro, gemini-3-flash-preview, gemini-3-pro-preview, gemini-3.1-flash-lite-preview, gemini-3.1-pro-preview, gemini-3.5-flash, gpt-3.5-turbo, gpt-4, gpt-4-turbo, gpt-4-turbo-2024-04-09, gpt-4.1, gpt-4.1-mini, gpt-4.1-nano, gpt-4o, gpt-4o-2024-08-06, gpt-4o-mini, gpt-5, gpt-5-mini, gpt-5-nano, gpt-5.1, gpt-5.1-codex, gpt-5.1-codex-mini, gpt-5.2, gpt-5.3-codex, gpt-5.4, gpt-5.4-mini, gpt-5.4-nano, gpt-5.5, grok-2-vision, o1, o3, o3-mini, o4-mini

str

default:"''"

Instructions on what you want to analyze from the image.

str

default:"''"

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

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

AcceptsImage

required

The image to analyze. For agent tool calls, pass an existing file reference such as

history.MESSAGE_ID,

tool.CALL_ID.OUTPUT_KEY, or $input.NAME; never pass an empty string.

str

required

The JSON schema to use for the response

SamplingConfig

int

The maximum number of tokens to generate

float

The temperature of the model

float

The top-p value

`ai_speech_to_text` — AI Speech To Text

Generate Text from Audio using AI

Platform docs: AI Speech To Text

pipeline.add(name="node").ai_speech_to_text(provider="deepgram", model="base", api_key="...", audio=...)

Parameters

bool

default:"False"

Use your personal API key

str

required

Select the model provider. One of: deepgram, google, openai

str

required

Select the speech-to-text model

Show Allowed values

base, enhanced, gemini-2.0-flash-001, gemini-2.5-flash, gemini-2.5-pro, gemini-3-flash-preview, gemini-3-pro-preview, gemini-3.1-flash-lite-preview, gemini-3.1-pro-preview, gemini-3.5-flash, gpt-3.5-turbo, gpt-4, gpt-4-turbo, gpt-4.1, gpt-4.1-mini, gpt-4.1-nano, nova, nova-2, nova-3, o1, o3, o3-mini, o4-mini, whisper-1

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

AcceptsAudio

required

The audio for conversion

str

required

Select the tier

Show Allowed values

atc, automotive, conversationalai, drivethru, finance, general, medical, meeting, phonecall, video, voicemail

`ai_text_to_image` — AI Text To Image

Generate Image from Text using AI

Platform docs: AI Text To Image

pipeline.add(name="node").ai_text_to_image(provider="flux", model="Stable Diffusion 1.6", api_key="...", aspect_ratio="16:9")

Parameters

bool

default:"False"

Use your personal API key

str

required

Select the model provider. One of: flux, google, openai, stabilityai, xai

str

required

Select the text-to-image model

Show Allowed values

Stable Diffusion 1.6, Stable Diffusion 3 Large, Stable Diffusion 3 Large Turbo, Stable Diffusion 3 Medium, Stable Diffusion Core, Stable Diffusion Ultra, Stable Diffusion XL, dall-e-2, dall-e-3, flux-dev, flux-pro, flux-schnell, gemini-2.5-flash-image, gemini-3-pro-image-preview, gpt-3.5-turbo, gpt-4, gpt-4-turbo, gpt-4.1, gpt-4.1-mini, gpt-4.1-nano, gpt-image-1.5, gpt-image-2, grok-2-image, o1, o3, o3-mini, o4-mini

str

default:"''"

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

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

str

required

Select the aspect ratio.

Show Allowed values

16:9, 1:1, 21:9, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 9:21

str

required

Select the size. One of: 1024x1024, 1024x1536, 1024x1792, 1536x1024, 1792x1024, 256x256, 512x512, auto

`ai_text_to_speech` — AI Text To Speech

Generate Audio from text using AI

Platform docs: AI Text To Speech

pipeline.add(name="node").ai_text_to_speech(text="...", api_key="...")

Parameters

bool

default:"False"

Use your personal API key

str

default:"'openai'"

Select the model provider. One of: eleven_labs, openai

str

default:"'tts-1-hd'"

Select the text-to-speech model

Show Allowed values

eleven_flash_v2, eleven_flash_v2_5, eleven_monolingual_v1, eleven_multilingual_v1, eleven_multilingual_v2, eleven_turbo_v2, eleven_turbo_v2_5, gpt-3.5-turbo, gpt-4, gpt-4-turbo, gpt-4.1, gpt-4.1-mini, gpt-4.1-nano, o1, o3, o3-mini, o4-mini, tts-1, tts-1-hd

str

required

The string input for conversion.

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

str

default:"'alloy'"

Select the voice

Show Allowed values

Alice, Aria, Bill, Brian, Callum, Charlie, Charlotte, Chris, Daniel, Eric, George, Jessica, Laura, Liam, Lily, Matilda, River, Roger, Sarah, Will, alloy, echo, fable, nova, onyx, shimmer

`image_gen` — image_gen

pipeline.add(name="node").image_gen()

Parameters

str

default:"'gpt-4-1106-preview'"

str

default:"''"

str

default:"'1:1'"

str

default:"'1'"

str

default:"'llmOpenAI'"

str

default:"'512x512'"

`speech_to_text` — speech_to_text

pipeline.add(name="node").speech_to_text(audio=...)

Parameters

str

default:"'OpenAI Whisper'"

One of: Deepgram, OpenAI Whisper

AcceptsAudio

required

str

default:"'nova-2'"

str

default:"'general'"

`tts_eleven_labs` — tts_eleven_labs

pipeline.add(name="node").tts_eleven_labs(text="...", api_key="...")

Parameters

str

default:"'eleven_multilingual_v2'"

str

required

str

required

str

default:"'shimmer'"

`tts_open_ai` — tts_open_ai

pipeline.add(name="node").tts_open_ai(text="...", api_key="...")

Parameters

bool

default:"False"

str

default:"'tts-1-hd'"

str

required

str

required

str

default:"'alloy'"

Get started

Guides

Pipeline

Agent

Knowledge Base

Integrations

Table

Transformation

Session

Analytics

Workspace

`ai_audio_operations` — Leverage AI for Audio operations

`ai_image_operations` — Leverage AI for Image operations

`ai_image_to_image` — AI Image To Image

`ai_image_to_text` — AI Image To Text

`ai_speech_to_text` — AI Speech To Text

`ai_text_to_image` — AI Text To Image

`ai_text_to_speech` — AI Text To Speech

`image_gen` — image_gen

`speech_to_text` — speech_to_text

`tts_eleven_labs` — tts_eleven_labs

`tts_open_ai` — tts_open_ai

​ai_audio_operations — Leverage AI for Audio operations

​ai_image_operations — Leverage AI for Image operations

​ai_image_to_image — AI Image To Image

​ai_image_to_text — AI Image To Text

​ai_speech_to_text — AI Speech To Text

​ai_text_to_image — AI Text To Image

​ai_text_to_speech — AI Text To Speech

​image_gen — image_gen

​speech_to_text — speech_to_text

​tts_eleven_labs — tts_eleven_labs

​tts_open_ai — tts_open_ai

`ai_audio_operations` — Leverage AI for Audio operations

`ai_image_operations` — Leverage AI for Image operations

`ai_image_to_image` — AI Image To Image

`ai_image_to_text` — AI Image To Text

`ai_speech_to_text` — AI Speech To Text

`ai_text_to_image` — AI Text To Image

`ai_text_to_speech` — AI Text To Speech

`image_gen` — image_gen

`speech_to_text` — speech_to_text

`tts_eleven_labs` — tts_eleven_labs

`tts_open_ai` — tts_open_ai