Skip to content
API Feature

Natural Text-to-Speech for Your Apps

Convert text to lifelike speech with AI. Multiple voices, emotions, and languages.

Vydra's Text-to-Speech API provides access to ElevenLabs' industry-leading neural TTS models. Generate natural, expressive speech from any text in seconds.

Choose from multiple pre-built voices or use custom voice IDs. Control stability, similarity, and output format for perfect results every time.

Why Use Our Text-to-Speech API

Natural Sounding

Neural TTS produces speech that's nearly indistinguishable from human voices.

Multiple Voices

Pre-built voices for different use cases: narration, casual, professional, and more.

Fast Generation

Generate minutes of audio in seconds. Low latency for real-time applications.

Customizable

Control stability, similarity boost, and output format for precise results.

Use Cases

See how developers and businesses use our text-to-speech api to build amazing products.

Video Voiceovers

Add professional narration to videos without recording.

Audiobooks

Convert written content to audio format at scale.

App Notifications

Generate voice feedback and alerts for mobile apps.

Podcasts

Automate intro/outro generation or create AI-hosted segments.

Simple API Integration

Get started with just a few lines of code.

cURLPOST
curl -X POST https://vydra.ai/api/v1/models/elevenlabs/tts \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Welcome to Vydra. The easiest way to create AI videos.",
    "voice": "adam",
    "stability": 0.5,
    "similarity_boost": 0.75
  }'
JavaScript
const response = await fetch('https://vydra.ai/api/v1/models/elevenlabs/tts', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    text: 'Welcome to Vydra. The easiest way to create AI videos.',
    voice: 'adam',
    stability: 0.5,
    similarity_boost: 0.75,
  }),
});

const { audioUrl } = await response.json();
Python
import requests

response = requests.post(
    'https://vydra.ai/api/v1/models/elevenlabs/tts',
    headers={'Authorization': 'Bearer YOUR_API_KEY'},
    json={
        'text': 'Welcome to Vydra. The easiest way to create AI videos.',
        'voice': 'adam',
        'stability': 0.5,
        'similarity_boost': 0.75,
    }
)

audio_url = response.json()['audioUrl']

Frequently Asked Questions

What voices are available?

We offer preset voices including adam (deep male), rachel (calm female), josh (energetic male), and bella (soft female). Custom ElevenLabs voice IDs are also supported.

What's the maximum text length?

Up to 10,000 characters per request. For longer content, split into multiple requests.

What audio formats are supported?

MP3 (various bitrates) and PCM audio. Default is mp3_44100_128 for high-quality output.

How is pricing calculated?

TTS costs 10 credits per 1,000 characters. Shorter texts are rounded up to the nearest unit.

Ready to Get Started?

Sign up for free and get 100 credits to try our text-to-speech api.