Neuphonic

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

Setup

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

export NEUPHONIC_API_KEY=<key>

Usage

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

from zrt.plugins import NeuphonicTTS

tts = NeuphonicTTS()

# Pipeline(tts=tts, ...)

Parameters

Parameter	Type	Default	Description
`api_key`	`str \| None`	`None`	Neuphonic API key. Falls back to the `NEUPHONIC_API_KEY` environment variable when unset.
`voice_id`	`str \| None`	`None`	Voice identifier (a UUID string from your Neuphonic voice library). The chosen voice also determines which underlying model is used. Defaults to letting Neuphonic select a default voice.
`lang_code`	`str`	`"en"`	Language code for synthesis. Other supported codes include `"es"`, `"pt"`, `"fr"`, `"de"`, `"zh"`, `"ja"`, `"ko"`, and `"ur"`.
`sampling_rate`	`int`	`22050`	Output audio sampling rate in Hz. Valid values: `8000`, `16000`, `22050`, `24000`.

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 the tts slot fits into the rest of the pipeline.

Speechify NVIDIA

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