Skip to main content

Deepgram TTS

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

Installation

Install the Deepgram-enabled VideoSDK Agents package:

pip install "videosdk-plugins-deepgram"

Importing

from videosdk.plugins.deepgram import DeepgramTTS

Authentication

The Deepgram plugin requires an Deepgram API key.

Set DEEPGRAM_API_KEY in your .env file.

Example Usage

from videosdk.plugins.deepgram import DeepgramTTS
from videosdk.agents import CascadingPipeline

# Initialize the Deepgram TTS model
tts = Deepgram(
# When DEEPGRAM_API_KEY is set in .env - DON'T pass api_key parameter
api_key="your-deepgram-api-key",
model="aura-asteria-en",
encoding="linear16", # linear16, mulaw, alaw, opus, mp3, flac, aac
sample_rate=24000
)

# 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

  • model : The Deepgram model to use (e.g., "aura-asteria-en", "aura-luna-en")
  • api_key: Your Deepgram API key (can also be set via environment variable)
  • encoding : (str) Encoding allows you to specify the expected encoding of your audio output (default : "linear16")
  • sample_rate: (int) Sample rate for output (default: 24000)

Additional Resources

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

Got a Question? Ask us on discord