Deepgram

Deepgram is a text-to-speech plugin. It synthesizes the LLM’s reply into the agent’s voice over a streaming WebSocket using Deepgram’s Aura voices. It occupies the pipeline’s tts slot.

Deepgram is also available as a speech-to-text plugin.

Setup

Set your Deepgram API key in the worker environment. Generate a key from the Deepgram console:

export DEEPGRAM_API_KEY=<key>

Usage

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

from zeroruntime.plugins import DeepgramTTS

tts = DeepgramTTS(
    model="aura-2-andromeda-en",
)

# Pipeline(tts=tts, ...)

import { DeepgramTTS } from '@zeroruntime/js-sdk/plugins';

const tts = DeepgramTTS({
  model: 'aura-2-andromeda-en',
});

// Pipeline({ tts, ... })

Parameters

Constructor parameters for DeepgramTTS. The Python and Node JS SDKs share these field names.

Parameter	Type	Default	Description
`api_key`	`str`	`None`	Deepgram API key. Falls back to the `DEEPGRAM_API_KEY` environment variable when unset.
`model`	`str`	`"aura-2-andromeda-en"`	Deepgram Aura voice/model ID.
`encoding`	`str`	`"linear16"`	Output audio encoding.
`sample_rate`	`int`	`24000`	Output sample rate (Hz).
`base_url`	`str`	`"wss://api.deepgram.com/v1/speak"`	Deepgram streaming endpoint.

Import paths

SDK	Import	Constructor
Python	`from zeroruntime.plugins import DeepgramTTS`	`DeepgramTTS(...)`
Node JS	`import { DeepgramTTS } from '@zeroruntime/js-sdk/plugins'`	`DeepgramTTS({ ... })`

The synthesized audio is streamed back to the caller as the final stage of the pipeline.

Plugins

Inference Gateway

Speech-to-text

LLM

Text-to-speech

Realtime models

Avatars

Turn detection

Voice activity detection

Noise cancellation

Setup

Usage

Parameters

Import paths

​Setup

​Usage

​Parameters

​Import paths

Setup

Usage

Parameters

Import paths