Text to speech

POST

/audio/speech

curl --request POST \
  --url https://example.com/audio/speech \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{ "input": "Hello there!", "model": "tts-1", "voice": "alloy" }'

OpenAI-compatible TTS. Returns mp3 audio. Served by gpt-4o-mini-tts; OpenAI voices (alloy, echo, fable, nova, shimmer, …) are accepted. Charged per input characters.

Authorizations

• ApiKeyAuth

Request Body^required

Media typeapplication/json

SpeechRequest

object

model

Model

Accepted for compatibility; served by gpt-4o-mini-tts.

string

default: tts-1

input

required

Input

Text to synthesize.

string

voice

Voice

Alloy, echo, fable, nova, shimmer, … (unknown → default).

string

default: alloy

response_format

Any of:

string

string

null

null

speed

Any of:

number

number

null

null

Example

{
  "input": "Hello there!",
  "model": "tts-1",
  "voice": "alloy"
}

Responses

200

Successful Response

Media typeapplication/json

Example^generated

example

422

Validation Error

Media typeapplication/json

HTTPValidationError

object

detail

Detail

Array<object>

ValidationError

object

loc

required

Location

Array

msg

required

Message

string

type

required

Error Type

string

input

Input

ctx

Context

object

Example^generated

{
  "detail": [
    {
      "loc": [
        "example"
      ],
      "msg": "example",
      "type": "example",
      "input": "example",
      "ctx": {}
    }
  ]
}