Integrations OpenAI

OpenAI Integration Guide

Using Kokoro as the Model

You can use Kokoro as the model with OpenAI. Here’s how you can integrate it:

1. Install OpenAI Python Library:

   • If you haven’t already, install the OpenAI Python library:

     pip install openai

2. Use the OpenAI Client:

   • Here is an example of how to use the OpenAI client to generate speech:

     from openai import OpenAI
     
     client = OpenAI(
         base_url="http://localhost:8880/v1", api_key="not-needed"
     )
     
     with client.audio.speech.with_streaming_response.create(
         model="kokoro",
         voice="af_sky+af_bella",  # Single or multiple voicepack combo
         input="Hello world!"
     ) as response:
         response.stream_to_file("output.mp3")

3. Running Kokoro FastAPI as a Docker Container:

   • If you are running Kokoro FastAPI as a Docker container, change the base URL to http://host.docker.internal:8880/v1.

Example Code for Docker Container

Here is an example of how to configure the OpenAI client for a Docker container:

from openai import OpenAI

client = OpenAI(
    base_url="http://host.docker.internal:8880/v1", api_key="not-needed"
)

with client.audio.speech.with_streaming_response.create(
    model="kokoro",
    voice="af_sky+af_bella",  # Single or multiple voicepack combo
    input="Hello world!"
) as response:
    response.stream_to_file("output.mp3")

By following these steps, you can integrate Kokoro with OpenAI and use the OpenAI-Compatible Speech Endpoint effectively.