Text-to-Speech

Implement input text conversion to an output audio file via API interface.

Preparation

Before running the example program, the corresponding model package must be installed on the device. Refer to Model List for the model package installation tutorial.

Before running this example program, please ensure the following preparations have been completed on the LLM device:

1. Install the llm-model-melotts-en-us model package using the apt package management tool.

apt install llm-model-melotts-en-us

2. Install the ffmpeg tool.

apt install ffmpeg

3. After installation, restart the OpenAI service to make the new model take effect.

systemctl restart llm-openai-api

Example

On the PC side, use the OpenAI API to pass in text to implement text-to-speech conversion. Before running the example program, modify the IP part of the base_url below to the actual IP address of the device.

from pathlib import Path
from openai import OpenAI

client = OpenAI(
    api_key="sk-",
    base_url="http://192.168.20.186:8000/v1"
)

speech_file_path = Path(__file__).parent / "speech.mp3"
with client.audio.speech.with_streaming_response.create(
  model="melotts-en-us",
  voice="alloy",
  input="The quick brown fox jumped over the lazy dog."
) as response:
  response.stream_to_file(speech_file_path)

Request Parameters

Response Example

• The audio file data will be saved to the speech_file_path specified in the example program.