Create Speech

Request Body

application/json

model*string

One of the available TTS models: tts-1 or tts-1-hd

input*string

The text to generate audio for. Maximum length is 4096 characters.

voice*string

The voice to use when generating audio. Supported voices: alloy, echo, fable, onyx, nova, and shimmer.

response_format?string

Defaults to mp3. Supported audio formats: mp3, opus, aac, and flac.

speed?number

Defaults to 1. The speed of the generated audio. Choose a value between 0.25 and 4.0. 1.0 is the default.

Response Body

application/json

curl -X POST "https://loading/v1/audio/speech" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini-tts",
    "input": "The quick brown fox jumped over the lazy dog.",
    "voice": "alloy"
  }'

curl -X POST "https://loading/v1/audio/speech" \  -H "Content-Type: application/json" \  -d '{    "model": "gpt-4o-mini-tts",    "input": "The quick brown fox jumped over the lazy dog.",    "voice": "alloy"  }'

{}

Request Body

Response Body

200application/json

application/json