---
title: "Unload Model"
method: POST
path: "/models/unload"
---

# Unload Model

`POST /models/unload`

## Request

- Base URL: `https://api.voicelabs.now` (the document declares no server; this is the origin it was published from)
- URL: `https://api.voicelabs.now/models/unload`
- Auth: none declared

Unload a model from memory.

Pass ``{"model_name": "chatterbox-tts"}`` to target a specific engine —
same behaviour as ``POST /models/{model_name}/unload``. Only an absent
``model_name`` unloads the default Qwen TTS model, as it always has; a
supplied-but-empty name is a bad request.

## Request body

- ModelLoadRequest: Request model for loading or unloading a model by name. ``model_name`` is one of the ids returned by ``GET /models/status`` (e.g. ``"kokoro"``, ``"qwen-tts-0.6B"``, ``"whisper-turbo"``). ``model_size`` is the legacy Qwen-only selector, kept so existing ``POST /models/load?model_size=0.6B`` callers keep working.
  - `model_name` string, nullable
  - `model_size` string, nullable

## Response `200`

Successful Response

- unknown

## Other responses

- `422`: Validation Error

---

[API](https://skmtc.dev/voicelabs/apis/voicebox-api.md) · [All operations](https://skmtc.dev/voicelabs/apis/voicebox-api/llms.txt) · [OpenAPI document](https://skmtc.dev/voicelabs/apis/voicebox-api/revisions/a7a37d1fc02f?raw)