Skip to content
For the complete documentation index, see llms.txt. Markdown versions of documentation pages are available by appending .md to the page URL.
Primary navigation

Suggested
Overview Models Agents Tools Audio & voice Production API reference

Create voice

$ openai audio:voices create
POST/audio/voices

Create a custom voice you can use for audio output (for example, in Text-to-Speech and the Realtime API). This requires an audio sample and a previously uploaded consent recording.

Send name, audio_sample, and the consent recording ID as multipart form data. The optional type defaults to audio_sample.

Returns the saved voice’s metadata. See the custom voices guide for requirements and best practices. Custom voices are limited to eligible customers.

ParametersExpand Collapse
--audio-sample: file path

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.

--name: string

The name of the new voice.

--type: optional "audio_sample"

The voice creation method. Defaults to audio_sample when omitted.

ReturnsExpand Collapse
voice: object { id, created_at, name, 2 more }

A custom voice that can be used for audio output.

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.

type: "audio_sample"

How the voice was created.

Create voice

openai audio:voices create \
  --api-key 'My API Key' \
  --name x \
  --audio-sample 'Example data' \
  --consent consent
{
  "id": "id",
  "created_at": 0,
  "name": "name",
  "object": "audio.voice",
  "type": "audio_sample"
}
Returns Examples
{
  "id": "id",
  "created_at": 0,
  "name": "name",
  "object": "audio.voice",
  "type": "audio_sample"
}