Skip to main content

Groq TTS

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

Installation​

Install the Groq-enabled VideoSDK Agents package:

pip install "videosdk-plugins-groq"

Importing​

from videosdk.plugins.groq import GroqTTS

Authentication​

The Groq plugin requires an Groq API key.

Set GROQ_API_KEY in your .env file.

Example Usage​

from videosdk.plugins.groq import GroqTTS
from videosdk.agents import CascadingPipeline

# Initialize the Groq AI TTS model
tts = GroqTTS(
model="playai-tts",
voice="Fritz-PlayAI",
)

# 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 (str): The TTS model to use. Default: "playai-tts"
  • voice (str): The voice to use. Default: "Fritz-PlayAI"
  • speed (float): Speed of speech (0.5 to 5.0). Default: 1.0
  • api_key (str, optional): Groq API key. If not provided, uses GROQ_API_KEY environment variable

Additional Resources​

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

Got a Question? Ask us on discord