Gemini TTS Series

Brief: Convert text to speech using Gemini TTS models.

---

Overview

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

Authentication

• Header: Authorization: Bearer <token>
• Supports bearer token authentication

---

Request Body Parameters

Parameter	Type	Required	Description
model	string	Yes	Model name, choose gemini-2.5-flash-preview-tts or gemini-2.5-pro-preview-tts
input	string	Yes	Text to convert to speech, up to 10000 characters
voice	string	Yes	Voice style, see official docs for available voices such as achernar, leda, zubenelgenubi
response_format	string	No	Audio format, default wav. Supported values: mp3, opus, aac, flac, wav, pcm
temperature	number	No	Temperature control, range 0 to 2. Lower values produce more consistent speech

Tip: wav or pcm is usually the most efficient format.

---

curl Example

curl -X POST "https://api.gpt.ge/v1/audio/speech" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxx" \
  -d '{
    "model": "gemini-2.5-flash-preview-tts",
    "input": "Hello, I am the v-api TTS assistant. Welcome to our API service!",
    "voice": "leda",
    "response_format": "mp3",
    "temperature": 1.0
  }'

JavaScript (fetch) Example

fetch('https://api.gpt.ge/v1/audio/speech', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': 'Bearer sk-xxxx'
  },
  body: JSON.stringify({
    model: 'gemini-2.5-flash-preview-tts',
    input: 'Hello, I am the v-api TTS assistant. Welcome to our API service!',
    voice: 'leda',
    response_format: 'mp3',
    temperature: 1.0
  })
}).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'
    },
    json={
        'model': 'gemini-2.5-flash-preview-tts',
        'input': 'Hello, I am the v-api TTS assistant. Welcome to our API service!',
        'voice': 'leda',
        'response_format': 'mp3',
        'temperature': 1.0
    }
)
print(response.status_code)
print(response.content[:20])

---

Response Example (200)

<binary audio data returned directly, such as WAV or MP3 file content>

Note: The response typically returns the audio content directly in the selected response_format, and may include usage metadata in response headers such as X-Usage.