List Voices

Query the voices available to the current tenant. Voices are uniformly identified by a voice id, referenced by endpoints such as Single-speaker Speech.

GET

/v1/audio/voices

List the voices available to the current tenant. Returns a list object; for security boundaries, voice URLs are not returned.

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

Query	Type	Required	Description
limit	integer	No	Number of results to return; defaults to 20.
offset	integer	No	Offset.
after	string	No	Pagination cursor; use the `next_cursor` returned by the previous page.
status	string	No	Filter by voice status; the exact allowed values are subject to the server.

Request example

curl "https://api.mosi.cn/v1/audio/voices?limit=20&status=ready" \
  -H "Authorization: Bearer $MOSS_API_KEY"

Response fields

Field	Type	Always returned	Description
object	string	Yes	Fixed as `list`.
data[].id	string	Yes	voice id; referenced by the TTS/TTSD/voice-generation endpoints.
data[].object	string	Yes	Fixed as `audio.voice`.
data[].name	string	Yes	Human-readable name; may be an empty string.
data[].created_at	integer	Yes	Creation time, a Unix timestamp in seconds.
has_more	boolean	Yes	Whether there are more voices.
first_id	string	When data is non-empty	The first voice id on the current page.
last_id	string	When data is non-empty	The last voice id on the current page.
next_cursor	string	When there is a next page	Cursor for the next page; can be passed as `after` in the next request.

Response example

{
  "object": "list",
  "data": [
    {
      "id": "<voice_id>",
      "object": "audio.voice",
      "name": "Alice",
      "created_at": 1710000000
    }
  ],
  "first_id": "<voice_id>",
  "last_id": "<voice_id>",
  "has_more": false
}

Next steps

Create Voice

Create or clone a voice from a multipart audio sample.

Single-speaker Speech

Text-to-speech endpoint.