Manage Voices

A cloned voice belongs to the workspace rather than the member who created it, and access follows the caller’s workspace role and API-key scopes exactly as for any other voice: voices scopes to list it, audio scopes to synthesize with it, and the content-management permission plus a write scope on the key to delete it. This page covers the lifecycle after creation - creating one is the Voice Cloning API page.

List voices

Cloned voices appear in the voices list alongside Speechify’s built-in catalog:

from speechify import Speechify
client = Speechify(
    token="YOUR_TOKEN_HERE",
)
client.voices.list(
    locale="en",
    model="simba-3.2",
    project_id="proj_01arz3ndektsv4rrffq69g5fav",
)

{
  "next_cursor": "string",
  "has_more": true,
  "voices": [
    {
      "display_name": "string",
      "gender": "male",
      "locale": "string",
      "id": "string",
      "models": [
        {
          "languages": [
            {
              "locale": "string",
              "preview_audio": "string"
            }
          ],
          "name": "simba-english"
        }
      ],
      "type": "shared",
      "avatar_image": "string",
      "preview_audio": "string",
      "project_id": "proj_01kwxwcbyb6wk952swa0432cf1",
      "can_manage": true,
      "staff_pick_rank": 1,
      "tags": [
        "string"
      ]
    }
  ]
}

Each voice’s models array reflects what your workspace can actually synthesize with it, so branch on that rather than assuming model support.

Get a voice

Fetch a single voice by its id:

from speechify import Speechify
client = Speechify(
    token="YOUR_TOKEN_HERE",
)
client.voices.get(
    voice_id="voice_id",
)

Download the sample

The audio sample a clone was built from is retrievable as WAV:

from speechify import Speechify
client = Speechify(
    token="YOUR_TOKEN_HERE",
)
client.voices.download_sample(
    voice_id="voice_id",
)

Delete a voice

Remove voices you no longer need:

from speechify import Speechify
client = Speechify(
    token="YOUR_TOKEN_HERE",
)
client.voices.delete(
    voice_id="voice_id",
)

Deletion is immediate: synthesis requests that name the deleted voice’s id fail from that point on.

Next steps