Audio Speech

Synthesize speech from text (TTS) and return an audio file, compatible with the OpenAI Audio Speech API.

Basics

MethodPOST Endpointhttps://koprouter.kopglobal.com/v1/audio/speech AuthenticationAuthorization: Bearer sk-...

Request Parameters

Parameter	Type	Required	Description
`model`	string	Yes	TTS model ID
`input`	string	Yes	Text to synthesize
`voice`	string	Yes	Voice, e.g. `alloy`, `echo`
`response_format`	string	No	Audio format, e.g. `mp3`, `wav`
`speed`	number	No	Playback speed multiplier

Example Request

curl https://koprouter.kopglobal.com/v1/audio/speech \
  -H "Authorization: Bearer sk-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "MODEL_ID",
    "input": "Hello, welcome to KOPRouter.",
    "voice": "alloy"
  }' \
  --output speech.mp3

Response

On success the endpoint returns the raw audio binary stream — write it to a local file to play it.

You are billed per synthesized character, so a longer `input` costs more.