New: AI video tools. Cut, clip, caption and dub your videos. See all video tools →
Voice Creator Pro logoVoice Creator Pro
Try For Free
Design

Stream from saved design voice

POST
/api/v1/generation/design/saved/stream

Start a streaming session using a saved voice design. Cancels any in-progress generation first.

Request Body

application/json
  1. body
voice_id*Voice Id

ID of the saved voice design

target_text*Target Text

Text to generate speech for

language?Language

Target language. Query GET /api/v1/models/active for supported languages per variant.

Default"Auto"
quality?|

Quality/variant tier. Query GET /api/v1/models/active for available tiers.

generation_params?|

Advanced sampling parameters

model_family?|

TTS model to use. If omitted, uses the currently configured model.

Response Body

Successful Response

application/json
  1. response
started*Started

Whether the streaming session was created

session_id*Session Id

Unique session ID for streaming endpoints

queue_position*Queue Position

Position in the generation queue

Example Request
curl -X POST 'http://127.0.0.1:8100/api/v1/generation/design/saved/stream' \  -H 'Content-Type: application/json' \  -d '{  "voice_id": "a1b2c3d4",  "target_text": "This is a test of the saved voice."}'
Example Response
{  "started": true,  "session_id": "a1b2c3d4",  "queue_position": 0}

Generate from saved design voice POST

Generate speech using a previously saved voice design. Validates voice_id exists on disk.

List built-in speakers GET

Return the list of built-in TTS speaker IDs, names, and descriptions. When `model_family` is supplied and valid, returns speakers belonging to that specific model — needed so audiobook callers can list voices compatible with a per-span model override, not just the globally active model.