Cartesia TTS
The Cartesia TTS provider enables your agent to use Cartesia's high-quality, low-latency text-to-speech models for generating natural-sounding voice output.
Installation​
Install the Cartesia-enabled VideoSDK Agents package:
pip install "videosdk-plugins-cartesia"
Importing​
from videosdk.plugins.cartesia import CartesiaTTS
Authentication​
The Cartesia plugin requires a Cartesia API key.
Set CARTESIA_API_KEY
in your .env
file.
Example Usage​
from videosdk.plugins.cartesia import CartesiaTTS
from videosdk.agents import CascadingPipeline
# Initialize the Cartesia TTS model
tts = CartesiaTTS(
# When CARTESIA_API_KEY is set in .env - DON'T pass api_key parameter
api_key="your-cartesia-api-key",
model="sonic-2",
voice_id="794f9389-aac1-45b6-b726-9d9369183238",
language="en"
)
# Add tts to cascading pipeline
pipeline = CascadingPipeline(tts=tts)
When using .env file for credentials, don't pass them as arguments to model instances. The SDK automatically reads environment variables, so omit api_key
and other credential parameters from your code.
Configuration Options​
api_key
: (str) Your Cartesia API key. Can also be set via theCARTESIA_API_KEY
environment variable.model
: (str) The Cartesia TTS model to use (e.g.,"sonic-2"
,"sonic-turbo"
). Defaults to"sonic-2"
.voice_id
: (str) The ID of the voice to use for generating speech.language
: (str) The language of the voice (e.g.,"en"
,"fr"
). Defaults to"en"
.
Additional resources​
The following resources provide more information about using Cartesia with VideoSDK Agents.
-
Python package: The
videosdk-plugins-cartesia
package on PyPI. -
GitHub repo: View the source or contribute to the VideoSDK Cartesia TTS plugin.
-
Cartesia docs: Cartesia TTS docs.
Got a Question? Ask us on discord