DeepFellow DOCS

Create Speech

Generate audio from the input text.

POST
/v1/audio/speech
AuthorizationBearer <token>

In: header

Header Parameters

OpenAI-Organization?Openai-Organization
OpenAI-Project?Openai-Project
inputInput

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

Lengthlength <= 4096
modelModel

One of the available TTS models.

voiceVoice

The voice to use when generating the audio.

instructions?Instructions

Control the voice of your generated audio with additional instructions.

Default""
format?Format

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

Default"mp3"
Value in"mp3" | "opus" | "aac" | "flac" | "wav" | "pcm"
speed?Speed

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

Default1
Range0.25 <= value <= 4
stream_format?Stream Format

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

Default"audio"
Value in"sse" | "audio"

Response Body

curl -X POST "https://loading/v1/audio/speech" \
  -H "OpenAI-Organization: 5eb7cf5a86d9755df3a6c593" \
  -H "OpenAI-Project: 5eb7cf5a86d9755df3a6c593" \
  -H "Content-Type: application/json" \
  -d '{
    "input": "string",
    "model": "string",
    "voice": "string"
  }'
null
{
  "detail": [
    {
      "loc": [
        "string"
      ],
      "msg": "string",
      "type": "string"
    }
  ]
}

We use cookies on our website. We use them to ensure proper functioning of the site and, if you agree, for purposes such as analytics, marketing, and targeting ads.