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 consent

audio.voice_consents.create(**kwargs) -> VoiceConsent
POST
/audio/voice_consents

Upload a voice consent recording.

Parameters
language: str

The BCP 47 language tag for the consent phrase (for example, en-US).

name: str

The label to use for this consent recording.

recording: FileTypes

The consent 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.

Returns
class VoiceConsent: …

A consent recording used to authorize creation of a custom voice.

id: str

The consent recording identifier.

created_at: int

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

formatunixtime
language: str

The BCP 47 language tag for the consent phrase (for example, en-US).

name: str

The label provided when the consent recording was uploaded.

object: Literal["audio.voice_consent"]

The object type, which is always audio.voice_consent.

Create voice consent

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("OPENAI_API_KEY"),  # This is the default and can be omitted
)
voice_consent = client.audio.voice_consents.create(
    language="language",
    name="name",
    recording=b"Example data",
)
print(voice_consent.id)
200 example
{
  "id": "cons_1234",
  "created_at": 0,
  "language": "language",
  "name": "name",
  "object": "audio.voice_consent"
}
Returns Examples
200 example
{
  "id": "cons_1234",
  "created_at": 0,
  "language": "language",
  "name": "name",
  "object": "audio.voice_consent"
}