Papla

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

Setup

Set your Papla API key in the worker environment. Generate a key from the Papla Media site:

export PAPLA_API_KEY=<key>

Usage

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

from zrt.plugins import PaplaTTS

tts = PaplaTTS()

# Pipeline(tts=tts, ...)

Parameters

Parameter	Type	Default	Description
`api_key`	`str \| None`	`None`	Papla API key. Falls back to the `PAPLA_API_KEY` environment variable when unset.
`model_id`	`str`	`"papla_p1"`	TTS model identifier, also used as the voice ID for the synthesis request. Defaults to the P1 ultra-realistic English model.
`sample_rate`	`int`	`24000`	Output audio 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.

Sarvam AI LMNT

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