Observed since 20 Oct, 16:42 UTC
No superseded metadata states collected. Unchanged observations do not create new revisions.
A unified wrapper for various reverse-engineered AI provider APIs, aiming for OpenAI compatibility.
A unified, professional Python wrapper for various reverse-engineered AI provider APIs, designed to be OpenAI-compatible and easy to use.
Install directly from PyPI:
pip install -U a4f-local
from a4f_local import A4F
client = A4F()
try:
audio_bytes = client.audio.speech.create(
model="tts-1", # Model name (currently informational)
input="Hello from a4f-local!",
voice="alloy" # Choose a supported voice
)
with open("output.mp3", "wb") as f:
f.write(audio_bytes)
print("Generated output.mp3")
except Exception as e:
print(f"An error occurred: {e}")
The following voice names are supported (mapped to OpenAI's official voices):
alloyechofableonyxnovashimmerUse one of these as the voice parameter in your TTS requests.
A4F client just like OpenAI's Python SDK.client.audio.speech.create()), it routes the request to the appropriate provider.See the LICENSE file for details. This software is not open source in the traditional sense. Please review the license terms carefully before use.
This package uses reverse-engineered, unofficial APIs. These may break or change at any time. Use at your own risk.
More detailed documentation, tutorials, and examples will be published here and on PyPI.
For now, refer to the example above and the source code for guidance.
Download counts and popularity will appear here as the collector receives them.
| Version | Published | Direct dependencies | Open version |
|---|---|---|---|
| 0.1.1 | 13 Apr 2025 | 8 |
This describes our collected data; it is not a security assessment.
Observed since 20 Oct, 16:42 UTC
No superseded metadata states collected. Unchanged observations do not create new revisions.
package:e6f02d45e505c819b953a191ef7e26e881c0feab54fd9147524522c5c6d82090