Instruction in audio call

[Gabri94x]

Hi there i saw openai official api offers istruction for the audio generation is it possible to upodate the speech request adding the new paramater?

this is the code snippet i saw in the official documentation.

curl https://api.openai.com/v1/audio/speech \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini-tts",
    "input": "Today is a wonderful day to build something people love!",
    "voice": "coral",
    "instructions": "Speak in a cheerful and positive tone.",
    "response_format": "wav"
  }' | ffplay -i -

thank you for this library it is amazing!

[StephenHodgson]

Sorry didn't mean to convert this. This is a valid enhancement issue.

[StephenHodgson]

I'll add this in the next updates :)