Speech

post

Generate a speech completion synchronously using the provided input text and model parameters.

Authorizations

Body

Standard OpenAI speech generation response containing the generated speech and metadata.

modelstring · enumRequiredPossible values:

streambooleanOptionalDefault: false

inputstring · min: 2 · max: 4096Required

voiceany ofOptional

One of default voices: leo, nora or a file_id with purpose voice.

string · enumOptionalDefault: leoPossible values:

or

stringOptional

temperaturenumber · max: 1OptionalDefault: 0.8

exaggerationnumber · max: 1OptionalDefault: 0.5

cfg_weightnumber · max: 1OptionalDefault: 0.5

response_formatstring · enumOptionalDefault: wavPossible values:

Responses

200

Default Response

application/json

400

Default Response

application/json

404

Default Response

application/json

500

Default Response

application/json

post

HTTPcURLJavaScriptPython

POST /v1/audio/speech HTTP/1.1
Host: api.distribute.ai
authorization: YOUR_API_KEY
Content-Type: application/json
Accept: */*
Content-Length: 144

{
  "model": "Chatterbox",
  "stream": false,
  "input": "text",
  "voice": "leo",
  "temperature": 0.8,
  "exaggeration": 0.5,
  "cfg_weight": 0.5,
  "response_format": "wav"
}

[
  {
    "url": "text"
  }
]