LMNT

LMNT is a text-to-speech plugin. It turns the LLM’s reply into audio the caller hears.

Setup

Set your LMNT API key in the worker environment. Generate a key from the LMNT dashboard:

export LMNT_API_KEY=<key>

Usage

Import the plugin and pass it to the pipeline’s tts slot.

from zrt.plugins import LMNTTTS

tts = LMNTTTS()

# Pipeline(tts=tts, ...)

Parameters

Parameter	Type	Default	Description
`api_key`	`str \| None`	`None`	LMNT API key. Falls back to the `LMNT_API_KEY` environment variable when unset.
`voice`	`str`	`"ava"`	Voice ID to use for synthesis. LMNT provides a library of pre-built voices (e.g. `"ava"`) as well as cloned voices identified by their UUID.
`model`	`str`	`"blizzard"`	TTS model identifier. `"blizzard"` is the production flagship (Blizzard 2.0); `"aurora"` is an alias that routes to Blizzard.
`sample_rate`	`int`	`24000`	Desired output sample rate in Hz.

Spoken replies support interruptions. When the caller talks over the agent, the runtime stops the audio and listens again. See the plugins overview for how TTS fits into the rest of the pipeline.

Papla Resemble AI

Plugins

Inference Gateway

Speech-to-text

LLM

Text-to-speech

Realtime models

Avatars

Turn detection

Voice activity detection

Noise cancellation

Setup

Usage

Parameters

​Setup

​Usage

​Parameters

Setup

Usage

Parameters