Sample - OpenAI API
POST/audio/voices

Create a custom voice

Creates a custom voice from a name, sample audio file, and consent recording. Send the required fields as multipart/form-data; audio_sample must use a supported audio MIME type and must not exceed 10 MiB.

  • RetriesRetries up to 2×, 500ms backoff, 30s timeout.

3 body fields

Multipart form data containing the custom voice name, sample audio recording, and consent recording identifier.

namestringrequired
The name of the new voice.
audio_samplestringrequired
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`.
consentstringrequired
The consent recording ID (for example, `cons_1234`).

1 status code
200Returns the created voice object with its identifier, name, `audio.voice` object type, and Unix creation timestamp.
objectstringrequired
The object type, which is always `audio.voice`.
Allowed:audio.voice
idstringrequired
The voice identifier, which can be referenced in API endpoints.
namestringrequired
The name of the voice.
created_atintegerrequired
The Unix timestamp (in seconds) for when the voice was created.

Error handling

name, audio_sample, and consent are required. audio_sample must be no larger than 10 MiB and must use one of the supported MIME types: audio/mpeg, audio/wav, audio/x-wav, audio/ogg, audio/aac, audio/flac, audio/webm, or audio/mp4.