Appearance
Multimodal
Image, video, speech, and diagram generation tools.
| Tool | Extra | Description |
|---|---|---|
generate_image_stability | base | Generate images with Stability AI. |
image_reader | base | Analyze local image files. |
generate_image | base | Generate images with Amazon Bedrock. |
nova_reels | base | Create short videos with Nova Reels on Bedrock. |
speak | base | Text-to-speech via macOS say or Amazon Polly. |
diagram | diagram | Render cloud architecture and UML diagrams. |
chat_video | twelvelabs | Q&A about video content via TwelveLabs. |
search_video | twelvelabs | Semantic search over video libraries. |
generate_image_stability
Generate images with Stability AI.
python
from elsai_tools.generate_image_stability import generate_image_stability| Parameter | Type | Required | Description |
|---|---|---|---|
prompt | str | Yes | Image prompt |
width | int | No | Image width |
height | int | No | Image height |
style | str | No | Style preset |
seed | int | No | Random seed |
image_reader
Analyze local image files.
python
from elsai_tools.image_reader import image_reader| Parameter | Type | Required | Description |
|---|---|---|---|
image_path | str | Yes | Path to image file |
prompt | str | No | Analysis prompt |
generate_image
Generate images with Amazon Bedrock.
python
from elsai_tools.generate_image import generate_image| Parameter | Type | Required | Description |
|---|---|---|---|
prompt | str | Yes | Image prompt |
negative_prompt | str | No | Negative prompt |
width | int | No | Image width |
height | int | No | Image height |
seed | int | No | Random seed |
nova_reels
Create short videos with Nova Reels on Bedrock.
python
from elsai_tools.nova_reels import nova_reels| Parameter | Type | Required | Description |
|---|---|---|---|
action | str | Yes | create, status, or list |
text | str | No | Video prompt |
image_path | str | No | Source image |
s3_bucket | str | No | Output S3 bucket |
fps | int | No | Frames per second |
dimension | str | No | Video dimensions |
speak
Text-to-speech via macOS say or Amazon Polly.
python
from elsai_tools.speak import speak| Parameter | Type | Required | Description |
|---|---|---|---|
text | str | Yes | Text to speak |
voice | str | No | Voice ID |
engine | str | No | TTS engine |
diagram
Render cloud architecture and UML diagrams.
python
from elsai_tools.diagram import diagramExtra: diagram
| Parameter | Type | Required | Description |
|---|---|---|---|
diagram_type | str | Yes | Diagram type |
nodes | List[Dict[str, str]] | No | Node definitions |
edges | List[Dict[str, Union[str, int]]] | No | Edge definitions |
output_format | str | No | Output format (default png) |
title | str | No | Diagram title |
elements | List[Dict[str, str]] | No | UML elements |
chat_video
Q&A about video content via TwelveLabs.
python
from elsai_tools.chat_video import chat_videoExtra: twelvelabs
| Parameter | Type | Required | Description |
|---|---|---|---|
video_id | str | Yes | TwelveLabs video ID |
prompt | str | Yes | Question about the video |
conversation_id | str | No | Conversation ID for follow-ups |
search_video
Semantic search over video libraries.
python
from elsai_tools.search_video import search_videoExtra: twelvelabs
| Parameter | Type | Required | Description |
|---|---|---|---|
query | str | Yes | Search query |
index_id | str | No | Video index ID |
max_results | int | No | Max results |