dd support for OpenAI / LocalAI TTS endpoint

[zhy844694805]

If it is compatible with the OpenAI API, integrating other applications will become incredibly convenient.
Example of using the OpenAI API:

curl https://api.openai.com/v1/audio/speech
-H "Authorization: Bearer $OPENAI_API_KEY"
-H "Content-Type: application/json"
-d '{
"model": "tts-1",
"input": "The quick brown fox jumps over the lazy dog.",
"voice": "alloy"
}'
--output speech.mp3

Reference documentation: OpenAI API Reference - Authentication