AlleAI Python SDK
A Python SDK for interacting with the AlleAI platform, providing seamless access to state-of-the-art AI models for image generation, audio processing, and video creation.
Features
- Chat Completions API – Generate conversational responses using multiple AI models such as GPT-5 and Claude Sonnet 4.6. Optional
toolsand tool follow-up viarequest_log_id+tool_result. - Embeddings API – Create vectors with
cohere-embed-v4. Alle-AI does not store embeddings. - Tools API – Execute built-in file tools (
generate_pdf,generate_docx,generate_pptx,generate_xlsx,generate_chart). - Image Generation & Editing API – Create and manipulate high-quality images using various AI models like Grok-2 and DALL·E 3.
- Audio API – Multi-model support for:
- Text-to-Speech (TTS): Convert text into natural-sounding audio.
- Speech-to-Text (STT): Transcribe spoken audio into text.
- Audio Generation: Create unique audio content using generative AI.
- Video Generation API – Generate AI-powered videos with customizable parameters, backed by multiple AI models.
Installation
Install the package using pip:
pip install alle-ai-sdk
Quick Start
Environment Setup
Create a .env file in your project root:
ALLEAI_API_KEY=your_api_key_here
Initialize Client
from alleai.core import AlleAIClient
from dotenv import load_dotenv
import os
# Load environment variables
load_dotenv()
# Get API key
api_key = os.getenv("ALLEAI_API_KEY")
# Initialize client
client = AlleAIClient(api_key=api_key)
Usage Examples
Chat Completions
# Chat completion example
chat = client.chat.completions({
"models": ["gpt-5", "claude-sonnet-4-6"],
"messages": [
{
"system": [
{
"type": "text",
"text": "You are a helpful assistant."
}
]
},
{
"user": [
{
"type": "text",
"text": "tell me about photosynthesis?"
}
]
}
],
"temperature": 0.7, # Controls randomness (0.0 to 1.0)
"max_tokens": 2000, # Maximum response length
"top_p": 1, # Controls diversity
"frequency_penalty": 0.2, # Penalizes repeated tokens
"presence_penalty": 0.3, # Penalizes new tokens
"stream": False # Enable streaming responses
})
print(chat)
Image Generation
# Generate an image
image_response = client.image.generate({
"models": ["grok-2-image", "dall-e-3"],
"prompt": "futuristic city, flying cars, robotic pedestrians.",
"model_specific_params": {
"grok-2-image": {
"n": 1,
"height": 1024,
"width": 1024
}
},
"n": 1,
"height": 1024,
"width": 1024,
"seed": 8 # For reproducible results
})
print(image_response)
Image Editing
# Edit an existing image
response = client.image.edit({
"models": ["nova-canvas"],
"image_file": "path/to/image.jpg",
"prompt": "Replace the sky with a sunset"
})
print(response)
Text-to-Speech
# Convert text to speech
tts_response = client.audio.tts({
"models": ["elevenlabs-multilingual-v2", "gpt-4o-mini-tts"],
"prompt": "Hello! You're listening to a test of a text-to-speech model...",
"voice": "nova",
"model_specific_params": {
"gpt-4o-mini-tts": {
"voice": "alternative-voice"
}
}
})
print(tts_response)
Speech-to-Text
# Transcribe audio
stt_response = client.audio.stt({
"models": ["whisper-v3"],
"audio_file": "path/to/your/audio.mp3"
})
print(stt_response)
Audio Generation
# Generate Audio
response = client.audio.generate({
"models": ["lyria"],
"prompt": "Create a relaxing ambient track"
})
print(response)
Video Generation
# Generate a video
video = client.video.generate({
"models": ["nova-reel"],
"prompt": "robotic arm assembling a car in a futuristic factory",
"duration": 6, # Video length in seconds
"loop": False, # Enable looping
"aspect_ratio": "16:9", # Video aspect ratio
"fps": 24, # Frames per second
"dimension": "1280x720", # Video dimensions
"resolution": "720p", # Output resolution
"seed": 8 # For reproducible results
})
print(video)
Video Status Check
# Check video generation status
response = client.video.get_video_status({
"requestId": "your-request-id"
})
print(response)
Embeddings
vectors = client.embeddings.create({
"input": ["Alle-AI embeddings", "second document"],
"model": "cohere-embed-v4",
"input_type": "search_document",
})
print(vectors)
Tools
pdf = client.tools.execute({
"tool_name": "generate_pdf",
"arguments": {
"filename": "report",
"title": "Q3 Report",
"content": [{"type": "heading", "text": "Summary", "level": 1}],
},
})
print(pdf)
Error Handling
from alleai.core.exceptions import InvalidRequestError
try:
response = client.image.generate({
"models": ["nova-canvas"],
"prompt": "Your prompt here"
})
except InvalidRequestError as e:
print(f"Error: {e.message}")
print(f"Error Code: {e.code}")
Requirements
- Python 3.8 or higher
- Valid AlleAI API key
requestslibrary (automatically installed with the package)
Support
For technical support and inquiries:
- Open an issue in our GitHub repository
- Contact our support team at contact@alle-ai.com
License
This project is licensed under the MIT License - see the LICENSE file for details.
Security
Metadata
Release files for alle-ai-sdk 2.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| alle_ai_sdk-2.1.0.tar.gz | 18.6 kB | Without provenance | Details for alle_ai_sdk-2.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| alle_ai_sdk-2.1.0-py2.py3-none-any.whl | Python 2, Python 3 | none | any | Details for alle_ai_sdk-2.1.0-py2.py3-none-any.whl |
Total release size: 43.7 kB
Release files / alle_ai_sdk-2.1.0.tar.gz
| Download URL | alle_ai_sdk-2.1.0.tar.gz |
|---|---|
| Size | 18.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
0b4434b9e693ee1a2ff893b5fb574e33f699b3555cc20de7cba721067207be54
|
|
BLAKE2b-256 checksum How to use checksums |
ab7eaa7eb6c062df1900e5b4478fde74a140f069f583e8aab606ed35509c57bb
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.14.2
|
Release files / alle_ai_sdk-2.1.0-py2.py3-none-any.whl
| Download URL | alle_ai_sdk-2.1.0-py2.py3-none-any.whl |
|---|---|
| Size | 25.2 kB |
| Tags | Python 2 Python 3 |
|
SHA-256 checksum How to use checksums |
1d30f28b05e79ce8cd685b1ad364769ac7e43ad2b2ec136126bb9827b5b634e7
|
|
BLAKE2b-256 checksum How to use checksums |
bf84f2b27bcc891a45d3aa742818133ef7e87fd27abdcc9378f76566a4c2e9a0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.14.2
|
Security for alle-ai-sdk 2.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.