API Reference

Audio

Speech

Copy Markdown

Open in Claude

Open in ChatGPT

Open in Cursor

---

Copy Markdown

View as Markdown

Create speech

client.Audio.Speech.New(ctx, body) (*Response, error)

POST/audio/speech

Generates audio from the input text.

Returns the audio file content, or a stream of audio events.

ParametersExpand Collapse

body AudioSpeechNewParams

Input param.Field[string]

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

maxLength4096

Model param.Field[SpeechModel]

One of the available TTS models: tts-1, tts-1-hd, gpt-4o-mini-tts, or gpt-4o-mini-tts-2025-12-15.

string

type SpeechModel string

One of the following:

const SpeechModelTTS1 SpeechModel = "tts-1"

const SpeechModelTTS1HD SpeechModel = "tts-1-hd"

const SpeechModelGPT4oMiniTTS SpeechModel = "gpt-4o-mini-tts"

const SpeechModelGPT4oMiniTTS2025_12_15 SpeechModel = "gpt-4o-mini-tts-2025-12-15"

Voice param.Field[AudioSpeechNewParamsVoiceUnion]

The voice to use when generating the audio. Supported built-in voices are alloy, ash, ballad, coral, echo, fable, onyx, nova, sage, shimmer, verse, marin, and cedar. You may also provide a custom voice object with an id, for example { "id": "voice_1234" }. Previews of the voices are available in the Text to speech guide.

string

type AudioSpeechNewParamsVoiceString string

One of the following:

const AudioSpeechNewParamsVoiceStringAlloy AudioSpeechNewParamsVoiceString = "alloy"

const AudioSpeechNewParamsVoiceStringAsh AudioSpeechNewParamsVoiceString = "ash"

const AudioSpeechNewParamsVoiceStringBallad AudioSpeechNewParamsVoiceString = "ballad"

const AudioSpeechNewParamsVoiceStringCoral AudioSpeechNewParamsVoiceString = "coral"

const AudioSpeechNewParamsVoiceStringEcho AudioSpeechNewParamsVoiceString = "echo"

const AudioSpeechNewParamsVoiceStringSage AudioSpeechNewParamsVoiceString = "sage"

const AudioSpeechNewParamsVoiceStringShimmer AudioSpeechNewParamsVoiceString = "shimmer"

const AudioSpeechNewParamsVoiceStringVerse AudioSpeechNewParamsVoiceString = "verse"

const AudioSpeechNewParamsVoiceStringMarin AudioSpeechNewParamsVoiceString = "marin"

const AudioSpeechNewParamsVoiceStringCedar AudioSpeechNewParamsVoiceString = "cedar"

type AudioSpeechNewParamsVoiceID struct{…}

Custom voice reference.

ID string

The custom voice ID, e.g. voice_1234.

Instructions param.Field[string]optional

Control the voice of your generated audio with additional instructions. Does not work with tts-1 or tts-1-hd.

maxLength4096

ResponseFormat param.Field[AudioSpeechNewParamsResponseFormat]optional

The format to audio in. Supported formats are mp3, opus, aac, flac, wav, and pcm.

const AudioSpeechNewParamsResponseFormatMP3 AudioSpeechNewParamsResponseFormat = "mp3"

const AudioSpeechNewParamsResponseFormatOpus AudioSpeechNewParamsResponseFormat = "opus"

const AudioSpeechNewParamsResponseFormatAAC AudioSpeechNewParamsResponseFormat = "aac"

const AudioSpeechNewParamsResponseFormatFLAC AudioSpeechNewParamsResponseFormat = "flac"

const AudioSpeechNewParamsResponseFormatWAV AudioSpeechNewParamsResponseFormat = "wav"

const AudioSpeechNewParamsResponseFormatPCM AudioSpeechNewParamsResponseFormat = "pcm"

Speed param.Field[float64]optional

The speed of the generated audio. Select a value from 0.25 to 4.0. 1.0 is the default.

minimum0.25

maximum4

StreamFormat param.Field[AudioSpeechNewParamsStreamFormat]optional

The format to stream the audio in. Supported formats are sse and audio. sse is not supported for tts-1 or tts-1-hd.

const AudioSpeechNewParamsStreamFormatSSE AudioSpeechNewParamsStreamFormat = "sse"

const AudioSpeechNewParamsStreamFormatAudio AudioSpeechNewParamsStreamFormat = "audio"

ReturnsExpand Collapse

type AudioSpeechNewResponse interface{…}

Create speech

Go

HTTP

TypeScript

Python

Java

Go

Ruby

package main

import (
  "context"
  "fmt"

  "github.com/openai/openai-go"
  "github.com/openai/openai-go/option"
)

func main() {
  client := openai.NewClient(
    option.WithAPIKey("My API Key"),
  )
  speech, err := client.Audio.Speech.New(context.TODO(), openai.AudioSpeechNewParams{
    Input: "input",
    Model: openai.SpeechModelTTS1,
    Voice: openai.AudioSpeechNewParamsVoiceUnion{
      OfString: openai.String("string"),
    },
  })
  if err != nil {
    panic(err.Error())
  }
  fmt.Printf("%+v\n", speech)
}

Returns Examples