Create Voice

Create/clone a new voice from an audio sample. This endpoint supports only multipart/form-data, and the reference audio is provided via the audio_sample file field. The current /v1 does not register GET /v1/audio/voices/{voice_id}.

POST

/v1/audio/voices

Create/clone a voice from an audio_sample reference audio, returning an audio.voice object with a voice id.

Authentication

Add Authorization: Bearer <API_KEY> to the request headers to authenticate. You can generate a key on the console "API Keys" page.

curl https://api.mosi.cn/v1/audio/voices \
  -H "Authorization: Bearer $MOSS_API_KEY"

Request fields

Field	Type	Required	Description
audio_sample	multipart file	Yes	Reference audio file; only multipart supports this field.
name	string	No	Voice name.
description	string	No	Voice description.

Request example

curl -X POST https://api.mosi.cn/v1/audio/voices \
  -H "Authorization: Bearer $MOSS_API_KEY" \
  -F audio_sample=@sample.wav \
  -F name=Alice

Response fields

Field	Type	Always returned	Description
id	string	Yes	voice id; referenced by endpoints such as TTS/TTSD.
object	string	Yes	Fixed as `audio.voice`.
name	string	Yes	Voice name; may be an empty string when `name` is not provided.
created_at	integer	Yes	Creation time, a Unix timestamp in seconds.

Response example

{
  "id": "<voice_id>",
  "object": "audio.voice",
  "name": "Alice",
  "created_at": 1710000000
}

Next steps

Generate Voice

Generate a voice or speech from text and a voice description.

Single-speaker Speech

Text-to-speech endpoint.