Skip to main content
POST
/
v1
/
audio
/
speech
Text to Speech
curl --request POST \
  --url https://api.neospeech.io/v1/audio/speech \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "input": "<string>",
  "voice": "<string>",
  "model": "<string>",
  "pitch": "<string>",
  "style": "<string>",
  "styleDegree": "<string>",
  "lang": "<string>"
}
'
Generate high-quality audio from text using our neural TTS models. This endpoint returns a complete MP3 file after processing your text.

​
Request

Here’s the simplest way to generate speech: 
curl -X POST "https://api.neospeech.io/v1/audio/speech" \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "input": "Hello, welcome to NeoSpeech",
    "voice": "lyra",
    "model": "aurora-4"
  }' \
  --output speech.mp3

​
Parameters

​
Authorization
string
required
Bearer token: Bearer sk-your-api-key
​
input
string
required
The text to convert to speech (max 5,000 characters)
​
voice
string
required
Voice identifier like lyra, kai, or zara. See all voices
​
model
string
required
Audio model: aurora-4 (premium), aurora-3.5 (high quality), turbo-3 (fast), or mini-2 (lightweight)
​
pitch
string
Adjust voice pitch from -50% to +50%. Default: +0%
​
style
string
Speech emotion: calm, excited, cheerful, or sad. Default: calm
​
styleDegree
string
Style intensity from 0.5 to 2.0. Default: 1.5
​
lang
string
Language code like en-US, en-GB, fr-FR. Default: en-US

​
Response

Returns binary MP3 audio data with these headers: 
Content-Type: audio/mpeg
X-Character-Count: 28
X-Model-Used: aurora-4
X-Voice-Used: Lyra

​
Common patterns

​
Save to file

const response = await fetch('https://api.neospeech.io/v1/audio/speech', {
  method: 'POST',
  headers: {
    'Authorization': `Bearer ${process.env.NEOSPEECH_API_KEY}`,
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    input: 'Your text here',
    voice: 'lyra',
    model: 'aurora-4'
  })
});

const buffer = Buffer.from(await response.arrayBuffer());
fs.writeFileSync('output.mp3', buffer);

​
Add emotion

const response = await fetch('https://api.neospeech.io/v1/audio/speech', {
  method: 'POST',
  headers: {
    'Authorization': `Bearer ${apiKey}`,
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    input: 'This is exciting news!',
    voice: 'kai',
    model: 'aurora-4',
    style: 'excited',
    styleDegree: '1.8'
  })
});

​
Handle errors

try {
  const response = await fetch('https://api.neospeech.io/v1/audio/speech', {
    method: 'POST',
    headers: {
      'Authorization': `Bearer ${apiKey}`,
      'Content-Type': 'application/json'
    },
    body: JSON.stringify({ input, voice, model })
  });

  if (!response.ok) {
    const error = await response.json();
    throw new Error(error.message);
  }

  return await response.blob();
} catch (error) {
  console.error('Speech generation failed:', error.message);
  throw error;
}