dynaspark 1.2.2.3

A Python client for the DynaSpark API - Free AI text generation, text-to-speech, and image generation

DynaSpark Python Client

A powerful, free Python client for the DynaSpark API - No API key required!

Features

Feature	Description
Free Usage	No API key required - uses free key by default
Text Generation	Generate text responses with customizable parameters including temperature, top_p, and more
Image Generation	Create high-quality images with various models, resolutions, and watermark options
Audio Generation	Convert text to speech with multiple voice options
OpenAI Compatible	Use as a drop-in replacement for OpenAI API
Streaming Support	Get responses as they're generated with real-time streaming
Rate Limiting	Built-in rate limit handling with usage statistics
Error Handling	Comprehensive error handling with specific exception types
Easy to Use	Simple and intuitive Python interface
Secure	Built-in validation and privacy controls

Installation

pip install dynaspark

Note: Requires Python 3.7 or higher.

Authentication

No API key is required to get started - the client uses a free key by default. However, you can specify your own API key if needed:

from dynaspark import DynaSpark

# Use with default free API key
ds = DynaSpark()

# Or specify your own API key
ds = DynaSpark(api_key="your_api_key")

Advanced Text Generation

Generate text with fine-grained control over the output:

# Advanced text generation with various parameters
response = ds.generate_response(
    "Write a technical article about AI",
    model="mistral",
    temperature=0.8,
    top_p=0.9,
    presence_penalty=0.6,
    frequency_penalty=0.6,
    system="You are a technical writer with expertise in AI",
    stream=True,  # Enable streaming
    private=True,  # Keep generation private
    seed=42,       # For reproducible results
    json=False     # Return as JSON
)

Advanced Image Generation

Create custom images with various options:

# Generate high-quality images with custom settings
image_url = ds.generate_image(
    "A futuristic city with flying cars and neon lights",
    width=1024,      # Image width (64-2048)
    height=768,      # Image height (64-2048)
    model="flux",    # Options: flux, turbo, gptimage
    nologo=True,     # Exclude watermark
    wm="MyApp"       # Custom watermark text
)

Advanced Audio Generation

Convert text to speech with multiple voice options:

# Generate speech with different voices
voices = ["alloy", "echo", "nova", "shimmer", "fable", "onyx"]
for i, voice in enumerate(voices):
    audio_data = ds.generate_audio_response(
        f"This is the {voice} voice",
        voice=voice
    )
    ds.save_audio(audio_data, f"{voice}_demo.mp3")

Quick Start

Text Generation

from dynaspark import DynaSpark

ds = DynaSpark()

# Basic text generation
response = ds.generate_response("What is artificial intelligence?")
print(response.get('response', ''))

# Advanced usage with parameters
response = ds.generate_response(
    "Write a poem about technology",
    model="mistral",          # Model to use
    temperature=0.8,         # Controls randomness (0.0 to 3.0)
    top_p=0.9,              # Controls diversity (0.0 to 1.0)
    presence_penalty=0.6,    # Penalizes repeated tokens (-2.0 to 2.0)
    frequency_penalty=0.6,   # Penalizes frequent tokens (-2.0 to 2.0)
    json=True,              # Return JSON response
    system="You are a poet", # Custom system prompt
    stream=False,           # Stream the response
    private=False,          # Keep generation private
    seed=42                 # For reproducible results
)

Image Generation

# Generate an image
image_url = ds.generate_image("A beautiful sunset over mountains")

# Advanced image generation with parameters
image_url = ds.generate_image(
    "A futuristic city with flying cars",
    width=1024,         # Image width (64-2048)
    height=768,         # Image height (64-2048)
    model="flux",       # Model to use (flux/turbo/gptimage)
    nologo=True,        # Exclude watermark
    wm="DynaSpark"      # Custom watermark text
)
print(f"Generated image: {image_url}")

Audio Generation

# Generate audio from text
audio_data = ds.generate_audio_response("Hello, this is a test!")

# Save audio to file
ds.save_audio(audio_data, "response.mp3")

# With different voice
audio_data = ds.generate_audio_response(
    "This is a test with a different voice.",
    voice="nova"  # Options: alloy, echo, fable, onyx, nova, shimmer
)

OpenAI Compatibility

DynaSpark is compatible with the OpenAI Python package! Simply set the base URL to the DynaSpark OpenAI-compatible endpoint:

from openai import OpenAI

# Configure OpenAI client
client = OpenAI(
    base_url="https://dynaspark.onrender.com/openai",
    api_key="any_string_here",  # API key is not required but required by the client
)

# Use it like regular OpenAI API
completion = client.chat.completions.create(
    model="openai",
    messages=[
        {"role": "user", "content": "What is the meaning of life?"}
    ]
)

print(completion.choices[0].message.content)

Error Handling

The client provides custom exceptions for better error handling:

from dynaspark import DynaSpark, DynaSparkError

ds = DynaSpark()

try:
    response = ds.generate_response("Hello")
    print(response.get('response', ''))
except DynaSparkError as e:
    print(f"API Error: {e}")
except ValueError as e:
    print(f"Invalid Parameter: {e}")
except Exception as e:
    print(f"Unexpected Error: {e}")

Common Exceptions

Exception	Description
DynaSparkError	Base exception for API errors
RateLimitError	Raised when rate limit is exceeded
AuthenticationError	Raised for authentication issues
ValidationError	Raised for invalid parameters

Rate Limiting

The API implements rate limiting to ensure fair usage. The client provides information about your current usage:

# Get rate limit information
rate_limit = ds.get_rate_limit()
print(f"Remaining requests: {rate_limit.remaining}")
print(f"Reset time: {rate_limit.reset_time}")

Streaming Responses

For long text generations, you can use streaming to get responses as they're generated:

# Stream a response
for chunk in ds.generate_response(
    "Write a long story about artificial intelligence",
    stream=True
):
    print(chunk, end='', flush=True)

Examples

Text Generation Examples

# Chat completion
response = ds.generate_response(
    "You are a helpful assistant. Explain quantum computing.",
    model="mistral",
    temperature=0.7
)
print(response['response'])

# Code generation
response = ds.generate_response(
    "Write a Python function to sort a list of dictionaries by a key",
    model="qwen-coder",
    temperature=0.2
)
print(response['response'])

Image Generation Examples

# Basic image generation
image_url = ds.generate_image(
    "A cute cat playing with yarn",
    model="flux"
)

# High-resolution image
image_url = ds.generate_image(
    "A detailed landscape of mountains at sunset",
    width=1024,
    height=768,
    model="turbo"
)

Audio Generation Examples

# Basic audio generation
audio_data = ds.generate_audio_response(
    "Welcome to DynaSpark! This is a test of the audio generation.",
    voice="alloy"
)
ds.save_audio(audio_data, "welcome.mp3")

# Multiple voices
voices = ["alloy", "echo", "nova"]
for i, voice in enumerate(voices):
    audio_data = ds.generate_audio_response(
        f"This is voice {voice}",
        voice=voice
    )
    ds.save_audio(audio_data, f"voice_{i}.mp3")

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Support

For support, please open an issue in the GitHub repository.