ChatTTS

Brief: Convert text to speech using the ChatTTS model.

---

Overview

• Method: POST
• Path: /v1/audio/speech
• Content-Type: application/json

Authentication

• Header: Authorization: Bearer <token>
• Optional Header: Accept: */*

---

Request Body Parameters

Parameter	Type	Required	Description
model	string	Yes	Model name, fixed to ChatTTS
input	string	Yes	Text to convert into speech, up to 4096 characters
voice	string	Yes	Voice style, options include alloy, echo, fable, onyx, nova, shimmer
extra_body	object	No	Additional settings for output style and sampling
extra_body.prompt	string	No	Conversational tone level, value range oral_1 to oral_9
extra_body.temperature	number	No	Sampling temperature, range 0.0 to 1.0; higher values produce more random output
extra_body.top_P	number	No	Top-p sampling parameter, range 0.0 to 1.0
extra_body.top_K	number	No	Top-k sampling parameter, range 0 to 20
extra_body.voice_url	string	No	Custom voice file URL, must be .pt format

---

curl Example

curl -X POST "https://api.gpt.ge/v1/audio/speech" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxx" \
  -H "Accept: */*" \
  -d '{
    "model": "ChatTTS",
    "input": "Hello, I am the vapi TTS assistant. Thank you for using our API service!",
    "voice": "alloy",
    "extra_body": {
      "prompt": "oral_1",
      "temperature": 0.2,
      "top_K": 20
    }
  }'

JavaScript (fetch) Example

fetch('https://api.gpt.ge/v1/audio/speech', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': 'Bearer sk-xxxx',
    'Accept': '*/*'
  },
  body: JSON.stringify({
    model: 'ChatTTS',
    input: 'Hello, I am the vapi TTS assistant. Thank you for using our API service!',
    voice: 'alloy',
    extra_body: {
      prompt: 'oral_1',
      temperature: 0.2,
      top_K: 20
    }
  })
}).then(r => r.blob()).then(console.log);

Python (requests) Example

import requests

response = requests.post(
    'https://api.gpt.ge/v1/audio/speech',
    headers={
        'Content-Type': 'application/json',
        'Authorization': 'Bearer sk-xxxx',
        'Accept': '*/*'
    },
    json={
        'model': 'ChatTTS',
        'input': 'Hello, I am the vapi TTS assistant. Thank you for using our API service!',
        'voice': 'alloy',
        'extra_body': {
            'prompt': 'oral_1',
            'temperature': 0.2,
            'top_K': 20
        }
    }
)
print(response.status_code)
print(response.content[:20])

---

Response Example (200)

<binary audio data in the requested format, such as MP3 or WAV>

Note: The response usually returns the audio file content directly in the selected audio format.