Murf AI TTS

The Murf AI TTS provider enables your agent to use Murf AI's high-quality text-to-speech models for generating natural, expressive voice output with advanced voice customization.

Installation

Install the Murf AI-enabled VideoSDK Agents package:

pip install "videosdk-plugins-murfai"

Importing

from videosdk.plugins.murfai import MurfAITTS, MurfAIVoiceSettings

Authentication

The Murf AI plugin requires a Murf AI API key.

Set MURFAI_API_KEY in your .env file.

Example Usage

from videosdk.plugins.murfai import MurfAITTS, MurfAIVoiceSettings
from videosdk.agents import CascadingPipeline

# Configure voice settings
voice_settings = MurfAIVoiceSettings(
    pitch=0,
    rate=0,
    style="Conversational",
    variation=1,
    multi_native_locale=None
)

# Initialize the Murf AI TTS model
tts = MurfAITTS(
    # When MURFAI_API_KEY is set in .env - DON'T pass api_key parameter
    api_key="your-murfai-api-key",
    region="US_EAST",
    model="Falcon",
    voice="en-US-natalie",
    voice_settings=voice_settings,
    enable_streaming=True
)

# Add tts to cascading pipeline
pipeline = CascadingPipeline(tts=tts)

note

When using .env file for credentials, don't pass them as arguments to model instances or context objects. The SDK automatically reads environment variables, so omit api_key, videosdk_auth, and other credential parameters from your code.

Configuration Options

• api_key: Your Murf AI API key (can also be set via MURFAI_API_KEY environment variable)
• region: (str) The region code for API deployment (default: "US_EAST")
  • Available regions: "GLOBAL", "US_EAST", "US_WEST", "INDIA", "CANADA", "SOUTH_KOREA", "UAE", "JAPAN", "AUSTRALIA", "EU_CENTRAL", "UK", "SOUTH_AFRICA"
• model: (str) The Murf AI model to use (default: "Falcon")
  • Available models: "Gen2", "Falcon"
• voice: (str) Voice ID to use for audio output (default: "en-US-natalie")
• voice_settings: (MurfAIVoiceSettings) Advanced voice configuration options:
  • pitch: (int) Voice pitch adjustment, range varies by voice (default: 0)
  • rate: (int) Speech rate adjustment, range varies by voice (default: 0)
  • style: (str) Voice style/emotion (default: "Conversational")
  • variation: (int) Voice variation for diversity (default: 1)
  • multi_native_locale: (str) Optional locale for multi-native voices (default: None)
• enable_streaming: (bool) Enable WebSocket streaming for low latency. When False, uses HTTP chunked transfer (default: True)

Additional Resources

The following resources provide more information about using Murf AI with VideoSDK Agents SDK.

• Murf AI docs: Murf AI TTS docs.

SDK Reference

GitHub Repository

Python Package