New: AI video tools. Cut, clip, caption and dub your videos. See all video tools →
Model

Get active model capabilities

GET
/api/v1/models/active

Get the active TTS model's capabilities.

Query Parameters

mode?|

Generation mode to resolve the per-mode model preference for

Response Body

Successful Response

application/json
  1. response
model_family*Model Family

Model family identifier

display_name*Display Name

Human-readable model name

supports_clone*Supports Clone

Whether the model supports voice cloning

supports_design*Supports Design

Whether the model supports voice design

supports_custom_voice*Supports Custom Voice

Whether the model supports custom voice speakers

supports_streaming*Supports Streaming

Whether the model supports streaming generation

supports_emotional_clone?Supports Emotional Clone

Whether the model can clone with an emotion and intensity

Defaultfalse
supports_design_reference?Supports Design Reference

Whether voice design can be conditioned on a saved reference voice

Defaultfalse
design_takes_target_text?Design Takes Target Text

False when design mode has no text to speak (the model writes the words)

Defaulttrue
sample_rate*Sample Rate

Output audio sample rate in Hz

ref_min_sec?Ref Min Sec

Shortest reference audio the model accepts, in seconds

Default1.5
ref_min_speech_sec?Ref Min Speech Sec

Least speech the reference must contain, in seconds

Default3
ref_max_sec?Ref Max Sec

Longest reference audio the model uses, in seconds

Default10
custom_voice_speakers*array<string>

Available predefined speakers

generation_params*array<>

Available generation parameters with ranges

variants*array<>

Available model variants/quality tiers

studio_only?Studio Only

True if the model is only offered in the Studio audiobook tools

Defaultfalse
loading?|

True when switching started a background model load

Example Request
curl -X GET 'http://127.0.0.1:8100/api/v1/models/active'
Example Response
{  "model_family": "string",  "display_name": "string",  "supports_clone": true,  "supports_design": true,  "supports_custom_voice": true,  "supports_streaming": true,  "supports_emotional_clone": false,  "supports_design_reference": false,  "design_takes_target_text": true,  "sample_rate": 0,  "ref_min_sec": 1.5,  "ref_min_speech_sec": 3,  "ref_max_sec": 10,  "custom_voice_speakers": [    "string"  ],  "generation_params": [    {}  ],  "variants": [    {}  ],  "studio_only": false,  "loading": true}