Sign in

v1

latestOpenAPI 3.1.02026-07-22247.2 KB
speech

synthesize speech

synthesize an utterance and return it as a 24 kHz mono WAV file. pass your API key as a bearer token.

post/v1/tts

Request body

textstring required

text to synthesize. up to 2000 characters. for muga, prefix with a tone tag, e.g. [happy].

model'muga' | 'mulberry'

which model to use. muga is steered by a tone tag in the text; mulberry is steered by a natural-language description.

descriptionstring

required for mulberry. natural-language voice/style description. the voice is built from this. send it on every mulberry request, including when speaker is set. not used by muga.

speaker'emma' | 'mia' | 'sophia' | 'ava' | 'ira' | 'siya' | 'aisha' | 'zoya' | 'lucas' | 'noah' | 'theo' | 'adam'

mulberry only. optional named voice. emma, mia, sophia, ava, ira, siya, aisha and zoya are female; lucas, noah, theo and adam are male. case-insensitive. omit and a voice is generated from description. description is required either way.

temperaturenumber

sampling temperature.

top_pnumber

nucleus sampling.

top_kinteger

top-k sampling.

repetition_penaltynumber

penalize repeated tokens.

max_new_tokensinteger

output length cap. for mulberry, if long text comes back truncated, raise this above the default 2048 (up to 8192).

Example request

{
  "text": "[happy] Namaste! Kaise hain aap?",
  "description": "a female 30s hindi voice, smooth timbre, conversational pacing, like a podcast host",
  "speaker": "siya"
}

Response

synthesized audio as a 24 kHz mono WAV.