Quickstart Guide

Get started with YourVoic Speech APIs in under 5 minutes. Generate speech from text or transcribe audio with just a few lines of code.

⚡ 5-Minute Setup
From zero to your first API call in under 5 minutes. No complex setup required - just grab your API key and start!

Step 1: Get Your API Key #

Visit yourvoic.com/api/user and create a free account
Go to your Dashboard → API Keys → Create New Key
Copy your API key - it starts with yv_

🎁 Free Tier Includes: Credits to get started, access to all models, 99+ languages, no credit card required.

Step 2: Choose Your API #

🔊 Text-to-Speech

Convert text into natural-sounding speech

1000+ Premium Voices
50+ Languages
Real-time Streaming

🎙️ Speech-to-Text

Transcribe audio to accurate text

99+ Languages
Real-time Streaming
Speaker Diarization

Text-to-Speech Quick Start #

Generate speech from text with a simple API call:

cURL

Generate Speech

curl -X POST "https://yourvoic.com/api/v1/tts/generate" \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Hello world! Welcome to YourVoic.",
    "voice": "Peter",
    "model": "aura-prime"
  }' --output output.wav

Python

import requests

response = requests.post(
    "https://yourvoic.com/api/v1/tts/generate",
    headers={"X-API-Key": "YOUR_API_KEY"},
    json={
        "text": "Hello world! Welcome to YourVoic.",
        "voice": "Peter",
        "model": "aura-prime"
    }
)

with open("output.wav", "wb") as f:
    f.write(response.content)
print("✅ Audio saved to output.wav")

📚 Learn more: TTS Getting Started Guide →

Speech-to-Text Quick Start #

Transcribe audio files with high accuracy:

cURL

Transcribe Audio

curl -X POST "https://yourvoic.com/api/v1/stt/transcribe" \
  -H "X-API-Key: YOUR_API_KEY" \
  -F "file=@audio.mp3" \
  -F "model=cipher-fast"

Python

import requests

with open("audio.mp3", "rb") as f:
    response = requests.post(
        "https://yourvoic.com/api/v1/stt/transcribe",
        headers={"X-API-Key": "YOUR_API_KEY"},
        files={"file": f},
        data={"model": "cipher-fast"}
    )

result = response.json()
print(result["text"])

Response

{
  "text": "Hello world, this is a test transcription.",
  "language": "en",
  "duration": 5.2,
  "model": "cipher-fast",
  "provider": "cipher",
  "credits_used": 10
}

📚 Learn more: STT Getting Started Guide →

Available Models #

Text-to-Speech Models

Model	Quality	Best For
`aura-lite`	Good	High volume, fast generation
`aura-prime`	Better	Balanced quality & speed
`aura-max`	Best	Premium quality output
`rapid-flash`	Fast	Ultra-low latency streaming
`rapid-max`	HD	High-definition audio

Speech-to-Text Models

Model	Credits/sec	Best For
`cipher-fast`	2	Fast batch transcription
`cipher-max`	2	Maximum accuracy
`lucid-mono`	3	Single language streaming
`lucid-multi`	3	Multilingual streaming
`lucid-agent`	3	Voice assistants

Authentication #

All API requests require your API key in the X-API-Key header:

Header Authentication

X-API-Key: yv_live_xxxxxxxxxxxxxxxx

Keep it Secret: Never expose your API key in client-side code or public repositories.

Next Steps #

🔊 TTS Guide

Complete Text-to-Speech documentation

🎙️ STT Guide

Complete Speech-to-Text documentation

🎉 You're All Set!
Need help? Chat with us on WhatsApp or email support@yourvoic.com