Feature Overview

Explore the complete feature set of YourVoic Text-to-Speech API.

Core Features

Multiple AI Models

5 models optimized for different use cases - from ultra-fast to premium quality

30 Premium Voices

Diverse male and female voices with unique characteristics and styles

50+ Languages

Global coverage with proper pronunciation for each language

Localized Names

Voice names adapt to each language - Peter becomes Rahul in Hindi

Expression Tags

Add emotions like laughter, sighs, and whispers

Speed & Pitch Control

Fine-tune playback speed and voice pitch

Multiple Formats

Output in MP3, WAV, OGG, FLAC, or AAC

Streaming Support

Real-time audio streaming for low-latency apps

AI Models Comparison

ModelSpeedQualityLanguagesExpressionsBest For
aura-lite Fast Good 50+ Yes Real-time apps, chatbots
aura-prime Medium Excellent 50+ Yes General purpose
aura-max Slower Premium 50+ Yes Audiobooks, professional
rapid-flash Fastest Good 18 No IVR, low latency
rapid-max Fast Very Good 50+ No Speed + quality balance

Expression Tags

Add emotional depth to your audio with expression tags (Aura models only):

TagDescriptionExample
<chuckle>Light laughter"That's funny <chuckle> really!"
<laugh>Full laughter"Ha! <laugh> That's hilarious!"
<sigh>Sighing sound"<sigh> It's been a long day."
<gasp>Surprised gasp"<gasp> I can't believe it!"
<whisper>Whispered speech"<whisper>This is a secret</whisper>"
<yawn>Yawning"I'm so tired <yawn>"

Audio Parameters

Speed Control

Adjust playback speed from 0.5x to 2.0x:

  • 0.5 - Half speed (slow, deliberate)
  • 1.0 - Normal speed (default)
  • 1.25 - Slightly faster
  • 1.5 - Fast
  • 2.0 - Double speed

Pitch Control

Adjust voice pitch from 0.5 to 2.0:

  • 0.5 - Much lower pitch
  • 1.0 - Normal pitch (default)
  • 1.5 - Higher pitch

Output Formats

FormatExtensionBest For
MP3.mp3Web, general use (default)
WAV.wavEditing, highest quality
OGG.oggWeb, open source
FLAC.flacLossless archival
AAC.aacApple devices

Streaming

For real-time applications, use streaming to receive audio chunks as they're generated:

import requests

response = requests.post(
    "https://yourvoic.com/api/v1/tts/generate/stream",
    headers={"X-API-Key": "your_api_key"},
    json={
        "text": "Streaming audio for real-time playback.",
        "voice": "Peter",
        "language": "en-US"
    },
    stream=True
)

# Process chunks as they arrive
for chunk in response.iter_content(chunk_size=4096):
    if chunk:
        # Play or process the audio chunk
        process_audio(chunk)