Skip to main content
Use POST /v1/audio/speech when you want audio output instead of generated text. This endpoint returns streamed audio bytes, not a JSON text response.

​
Required fields

FieldRequiredNotes
modelYesText-to-speech model
inputYesText to synthesize
voiceYesVoice preset
response_formatNoOutput audio format such as mp3 or wav

​
Request Example

from pathlib import Path
from openai import OpenAI

client = OpenAI(
    base_url="https://api.naga.ac/v1",
    api_key="YOUR_API_KEY",
)

speech_file = Path("speech.mp3")

with client.audio.speech.with_streaming_response.create(
    model="gpt-4o-mini-tts",
    input="Welcome to NagaAI. Your job finished successfully.",
    voice="alloy",
    response_format="mp3",
) as response:
    response.stream_to_file(speech_file)

​
Important Difference From Text APIs

This endpoint does not return generated text JSON. It returns streamed audio bytes with a media type such as audio/mpeg, audio/opus, or audio/wav.

​
Response Formats

Supported output formats include:
  • mp3
  • opus
  • aac
  • flac
  • wav
  • pcm

​
Common mistakes

  • expecting a normal JSON response instead of binary audio
  • forgetting to write the response to a file or audio buffer
  • choosing a response format your playback pipeline does not handle

​
Reference