Speechify TTS

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

Installation

Install the Speechify-enabled VideoSDK Agents package:

pip install "videosdk-plugins-speechify"

Importing

from videosdk.plugins.speechify import SpeechifyTTS

Authentication

The Speechify plugin requires an Speechify API key.

Set SPEECHIFY_API_KEY in your .env file.

Example Usage

from videosdk.plugins.speechify import SpeechifyTTS
from videosdk.agents import CascadingPipeline

# Initialize the Speechify TTS model
tts = SpeechifyTTS(
    voice_id="kristy",
    model="simba-english"
)

# 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

• voice_id: (str) The Speechify voice to use (default: "kristy").
• api_key: (str) Speechify API key. Can also be set via the SPEECHIFY_API_KEY environment variable.
• model: (str) The model variant to use ("simba-base", "simba-english", "simba-multilingual", "simba-turbo"). Default: "simba-english".
• language: (str) Optional ISO language code for multilingual models (e.g., "en", "es").

Additional Resources

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

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

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

• Speechify AI docs: Speechify AI docs.