API Reference

Audio

Voices

Copy Markdown

Open in Claude

Open in ChatGPT

Open in Cursor

---

Copy Markdown

View as Markdown

Create voice

POST/audio/voices

Creates a custom voice.

Body ParametersForm DataExpand Collapse

audio_sample: file

The sample audio recording file. Maximum size is 10 MiB.

Supported MIME types: audio/mpeg, audio/wav, audio/x-wav, audio/ogg, audio/aac, audio/flac, audio/webm, audio/mp4.

consent: string

The consent recording ID (for example, cons_1234).

name: string

The name of the new voice.

ReturnsExpand Collapse

id: string

The voice identifier, which can be referenced in API endpoints.

created_at: number

The Unix timestamp (in seconds) for when the voice was created.

name: string

The name of the voice.

object: "audio.voice"

The object type, which is always audio.voice.

Create voice

HTTP

HTTP

TypeScript

Python

Java

Go

Ruby

curl https://api.openai.com/v1/audio/voices \
    -H 'Content-Type: multipart/form-data' \
    -H "Authorization: Bearer $OPENAI_API_KEY" \
    -F 'audio_sample=@/path/to/audio_sample' \
    -F consent=consent \
    -F name=name

200 example

{
  "id": "id",
  "created_at": 0,
  "name": "name",
  "object": "audio.voice"
}

Returns Examples

200 example

{
  "id": "id",
  "created_at": 0,
  "name": "name",
  "object": "audio.voice"
}