Inworld AI TTS

The Inworld AI TTS provider enables your agent to use Inworld AI's high-quality text-to-speech models for generating natural-sounding voice output.

Installation

Install the Inworld AI-enabled VideoSDK Agents package:

pip install "videosdk-plugins-inworldai"

Importing

from videosdk.plugins.inworld import InworldAITTS

Authentication

The Inworld plugin requires an Inworld API key.

Set INWORLD_API_KEY in your .env file.

Example Usage

from videosdk.plugins.inworldai import InworldAITTS
from videosdk.agents import CascadingPipeline

# Initialize the Inworld AI TTS model
tts = InworldAITTS(
    api_key="your-api-key",
    voice_id="Hades",
    model_id="inworld-tts-1"
)

# 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 and other credential parameters from your code.

Configuration Options

• model_id: (str) Inworld TTS model identifier (default: "inworld-tts-1").
• voice_id: (str) Voice identifier to use (default: "Hades").
• temperature: (float) Sampling temperature for variation in prosody (default: 0.8).
• api_key: (str) Inworld API key. Can also be set via the INWORLD_API_KEY environment variable.

Additional Resources

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

• Python package: The videosdk-plugins-inworldai package on PyPI.

• GitHub repo: View the source or contribute to the VideoSDK Inworld AI TTS plugin.

• Inworld AI docs: Inworld AI docs.