POST
/
audio
/
speech
node.js
const result = await suonora.audio.speech({
  input: "Welcome to Suonora TTS!",
  model: "legacy-v2.5",
  voice: "axel",
  style: "cheerful",
  styleDegree: 1.2
});

// Save to file
const fs = require('fs');
fs.writeFileSync("output.mp3", result);
"Binary MP3 data (not shown in documentation)"

Authorizations

​
Authorization
string
header
required

Your API key as a Bearer token

Body

application/json
​
input
string
required

Text to synthesize (up to 5,000 characters)

Example:

"Welcome to Suonora TTS!"

​
model
string
required

Name of the synthesis model

Example:

"legacy-v2.5"

​
voice
string
required

Voice ID from the voice gallery

Example:

"axel"

​
pitch
string

Pitch adjustment from -100% to +100%

Example:

"+0%"

​
style
enum<string>

Emotional speaking style

Available options:
neutral,
cheerful,
calm,
angry,
sad,
excited,
whispering
Example:

"calm"

​
styleDegree
number

Intensity of the selected style

Required range: 0.5 <= x <= 2
Example:

1.5

​
lang
string

BCP-47 language code

Example:

"en-US"

Response

Successful response with binary audio data

Raw MP3 audio data as binary blob