Docs
Get an API key

Chatterbox chatterbox

Text-to-speech in 23 languages with a built-in voice and voice cloning from a short clip, with expressiveness and pacing controls.

From the live catalog
View .md
Speech
$0.00028 / second

Limits

What one subscription may send this model. Limits says what happens past them.

Requests a minuteAt once
205

Inputs

InputAccepts
text
max prompt 4,800 characters

Parameters

Streams with stream: true.

ParameterTypeValuesDefault
voicestringdefault, clone
languageany
input_referencesarrayup to 2 items
response_formatstringmp3, opus, flac, wav, pcmmp3
stream_formatstringaudio, sseaudio
speednumber0.25–41
seedinteger
temperaturenumber0–2
top_pnumber0–1
top_kinteger
exaggerationnumber0.25–20.5
cfg_weightnumber0–10.5

Endpoints

A request

curl https://api.vultrinference.com/v1/audio/speech \
  -H "Authorization: Bearer $VULTR_INFERENCE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "chatterbox",
    "input": "Welcome to Vultr Serverless Inference.",
    "voice": "aiden",
    "instructions": "Warm and upbeat, like a radio host."
  }'