Speed & Pitch Control

Fine-tune playback speed and voice pitch where the selected model and delivery mode support them.

Support Matrix

Speed Control

Adjust how fast the text is spoken. Range: 0.5 to 2.0 (default: 1.0). Best used with Rapid models or Aura streaming.

import requests

# Slower delivery on a Rapid model
response = requests.post(
    "https://yourvoic.com/api/v1/tts/generate",
    headers={"X-API-Key": "your_api_key"},
    json={
        "text": "This is narrated at a comfortable audiobook pace.",
        "voice": "Peter",
        "language": "en-US",
        "model": "rapid-max",
        "speed": 0.9  # Slightly slower
    }
)

# Faster for notifications
response = requests.post(
    "https://yourvoic.com/api/v1/tts/generate",
    headers={"X-API-Key": "your_api_key"},
    json={
        "text": "You have three new messages.",
        "voice": "Emma",
        "language": "en-US",
        "model": "rapid-flash",
        "speed": 1.25  # Faster delivery
    }
)

Pitch Control

Adjust the voice pitch (tone). Range: 0.5 to 2.0 (default: 1.0). Pitch is currently intended for non-streaming Rapid requests and Rapid Flash pseudo-streaming.

# Lower pitch for serious content on Rapid Flash
response = requests.post(
    "https://yourvoic.com/api/v1/tts/generate",
    headers={"X-API-Key": "your_api_key"},
    json={
        "text": "This is an important announcement.",
        "voice": "Peter",
        "language": "en-US",
        "model": "rapid-flash",
        "pitch": 0.9  # Slightly lower, more serious
    }
)

# Higher pitch for friendly tone on Rapid Max generate
response = requests.post(
    "https://yourvoic.com/api/v1/tts/generate",
    headers={"X-API-Key": "your_api_key"},
    json={
        "text": "Hi there! Welcome to our app!",
        "voice": "Emma",
        "language": "en-US",
        "model": "rapid-max",
        "pitch": 1.1  # Slightly higher, more energetic
    }
)

Combining Speed and Pitch

Use both parameters together for fine-tuned control on supported paths such as Rapid Flash and standard Rapid Max generation.

# Audiobook style: slower with normal pitch
audiobook_config = {
    "text": "Chapter One. It was a dark and stormy night...",
    "voice": "Peter",
    "language": "en-US",
    "model": "rapid-max",
    "speed": 0.9,
    "pitch": 1.0
}

# News broadcast style: slightly faster, deeper pitch
news_config = {
    "text": "Breaking news: Scientists discover new species.",
    "voice": "Peter",
    "language": "en-US",
    "model": "rapid-max",
    "speed": 1.1,
    "pitch": 0.95
}

# Children's content: slower, slightly higher pitch
kids_config = {
    "text": "Once upon a time, there was a little bunny.",
    "voice": "Emma",
    "language": "en-US",
    "model": "rapid-flash",
    "speed": 0.85,
    "pitch": 1.15
}

# Urgent notification: faster, normal pitch
urgent_config = {
    "text": "Alert! Your session will expire in 5 minutes.",
    "voice": "Peter",
    "language": "en-US",
    "model": "rapid-flash",
    "speed": 1.3,
    "pitch": 1.0
}

Recommended Settings by Use Case

Tips

• Test with your content - Different text may need different settings
• Consider your audience - Elderly listeners may prefer slower speeds
• Match the mood - Lower pitch for serious, higher for friendly, but only on supported model paths
• Don't overdo it - Extreme values can sound unnatural
• Be consistent - Use the same settings throughout a project