🚀 Big News: Socket Acquires Coana to Bring Reachability Analysis to Every Appsec Team.Learn more
Socket
Book a DemoInstallSign in
Socket

@restackio/integrations-deepgram

Package Overview
Dependencies
Maintainers
0
Versions
13
Alerts
File Explorer

Advanced tools

Socket logo

Install Socket

Detect and block malicious and high-risk dependencies

Install

@restackio/integrations-deepgram

This package provides an integration for Deepgram's speech-to-text and text-to-speech services within the Restack AI framework.

0.0.13
latest
npm
Version published
Maintainers
0
Created
Source

Restack Deepgram Integration

This package provides an integration for Deepgram's speech-to-text and text-to-speech services within the Restack AI framework.

Installation

To install the Deepgram integration, use npm or yarn:

npm install @restackio/integrations-deepgram

Configuration

Before using the Deepgram integration, make sure to set up your Deepgram API key. You can do this by setting the DEEPGRAM_API_KEY environment variable or by passing the API key directly to the client.

Usage

Initializing the Deepgram Service

To start the Deepgram service:

// services.ts

import Restack from "@restackio/ai";
import { deepgramService } from "@restackio/integrations-deepgram";

export async function services() {
  const client = new Restack();
  deepgramService({ client }).catch((err) => {
    console.error("Error starting Deepgram service:", err);
  });
}

services().catch((err) => {
  console.error("Error running services:", err);
});

Available Functions

This integration provides two main functions:

  • deepgramListen: Transcribe audio to text
  • deepgramSpeak: Convert text to speech

Transcribing Audio (Speech-to-Text)

// transcribeAudioWorkflow.ts

import { log, step } from "@restackio/ai/workflow";
import * as deepgramFunctions from "@restackio/integrations-deepgram/functions";
import { deepgramTaskQueue } from "@restackio/integerations-deepgram/taskQueue";

export async function transcribeAudioWorkflow() {
  const result = await step<typeof deepgramFunctions>({
    taskQueue: deepgramTaskQueue,
  }).deepgramListen({
    base64Payload: "your_base64_encoded_audio",
    options: {
      model: "nova-2",
      punctuate: true,
      interim_results: true,
      endpointing: 500,
      utterance_end_ms: 2000,
    },
  });
  log.info("result", { result: result.transcript });
}

Converting Text to Speech

import { log, step } from "@restackio/ai/workflow";
import * as deepgramFunctions from "@restackio/integrations-deepgram/functions";
import { deepgramTaskQueue } from "@restackio/integerations-deepgram/taskQueue";

export async function deepgramSpeakWorkflow() {
  const result = await step<typeof deepgramFunctions>({
    taskQueue: deepgramTaskQueue,
  }).deepgramSpeak({
    text: "Hello, world!",
    options: {
      model: "aura-arcas-en",
    },
  });
  log.info("result", { result: result.media.payload }); // Base64 encoded audio
}

FAQs

Package last updated on 09 Nov 2024

Did you know?

Socket

Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.

Install

Related posts