LMNT AI TTS

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

Installation

Install the LMNT AI-enabled VideoSDK Agents package:

pip install "videosdk-plugins-lmnt"

Importing

from videosdk.agents.plugins import LMNTTTS

Authentication

The LMNT plugin requires an LMNT API key.

Set LMNT_API_KEY in your .env file.

Example Usage

from videosdk.agents.plugins import LMNTTTS
from videosdk.agents import Pipeline

# Initialize the LMNT TTS model
tts = LMNTTTS(
    voice="ava",
    model="blizzard",
    language="auto",
)

#  Add tts to pipeline
pipeline = Pipeline(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

• api_key: Your LMNT API key (can also be set via LMNT_API_KEY environment variable)
• voice: Voice ID to use for synthesis (default: "ava")
• model: Model to use for synthesis (default: "blizzard")
• language: ISO 639-1 language code or "auto" (default: "auto")
• format: Audio output format. One of "mp3", "pcm_s16le", "pcm_f32le", "ulaw", "webm" (default: "pcm_s16le")
• sample_rate: Output sample rate. One of 8000, 16000, 24000 (default: 24000)
• seed: (int) Optional generation seed for reproducibility (default: None)
• temperature: (float) Sampling temperature, 0.0-1.0 (default: 1.0)
• top_p: (float) Nucleus sampling parameter, 0.0-1.0 (default: 0.8)
• ws_url: Override for the WebSocket endpoint (default: "wss://api.lmnt.com/v1/ai/speech/stream")

Additional Resources

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

• LMNT docs: LMNT API docs.

SDK Reference

GitHub Repository

Python Package