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

Get loaded model info

GET
/api/v1/model/status

Return whether a TTS model is loaded, and if so its type, quality, and name.

Response Body

Successful Response

application/json
  1. response
loaded*Loaded

Whether a TTS model is currently loaded

type?|

Loaded model type (base, voice_design, custom_voice)

quality?|

Current quality preset (higher_quality, faster)

name?|

Model directory name

Example Request
curl -X GET 'http://127.0.0.1:8100/api/v1/model/status'
Example Response200
{  "loaded": true,  "type": "base",  "quality": "higher_quality",  "name": "Qwen3-TTS"}

Set default agent model PUT

Previous Page

Load TTS model POST

Load or switch the TTS model. **A model must be loaded before any generation endpoint will work.** If the requested mode/quality is already loaded, returns immediately with `status: "already_loaded"`. Otherwise begins async loading — poll `GET /api/v1/model/load/progress` until `status: "complete"`. Switching generation mode (clone / design / tts) requires a different model variant and triggers a reload.