Deepgram JS Voice Agent

What it does

When your agent uses it

• Reviewing JavaScript/TypeScript in this repo that builds an interactive voice agent via agent.deepgram.com/v1/agent/converse
• Include voice agent
• Function calling

Example prompts

• “voice agent”
• “agent converse”
• “full duplex”
• “/deepgram-js-voice-agent”

Requirements

• Node.js
• A credential in DEEPGRAM_API_KEY

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1In-repo reference: reference.md → Agent V1 Settings Think Models; live websocket behavior is defined in src/CustomClient.ts and…
2. 2Canonical OpenAPI (REST): https://developers.deepgram.com/openapi.yaml
3. 3Canonical AsyncAPI (WSS): https://developers.deepgram.com/asyncapi.yaml
4. 4Context7: library ID /llmstxt/developers_deepgram_llms_txt
5. 5Product docs

What it can do on your machine

Read from SKILL.md and the folder at commit 108a127. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • npx

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • developers.deepgram.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • DEEPGRAM_API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Deepgram JS Voice Agent loads about 1.6k tokens when it runs. Until then it costs about 167 tokens; SKILL.md has 417 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~167

When it runs · the whole SKILL.md, loaded when a task matches

~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from deepgram/deepgram-js-sdk at commit 108a127, republished under its MIT licence (© deepgram). 417 words, ~1,581 tokens.

name

deepgram-js-voice-agent

description

Use when writing or reviewing JavaScript/TypeScript in this repo that builds an interactive voice agent via `agent.deepgram.com/v1/agent/converse`. Covers `client.agent.v1.createConnection()` / `connect()`, `sendSettings`, `sendMedia`, runtime updates, event handling, and function-call responses. Use `deepgram-js-text-to-speech` for one-way synthesis, `deepgram-js-speech-to-text` or `deepgram-js-conversational-stt` for transcription only, and `deepgram-js-management-api` for project/model admin rather than live agent runtime. Triggers include "voice agent", "agent converse", "full duplex", "barge-in", "function calling", and "agent.v1".

require("dotenv").config();

const { DeepgramClient, DeepgramEnvironment } = require("@deepgram/sdk");

const deepgramClient = new DeepgramClient({
  apiKey: process.env.DEEPGRAM_API_KEY,
  environment: DeepgramEnvironment.Agent,
});

const deepgramConnection = await deepgramClient.agent.v1.createConnection();

deepgramConnection.on("message", (data) => {
  if (data.type === "ConversationText") {
    console.log("Conversation text:", data);
  } else if (typeof data === "string") {
    console.log("Audio received (length):", data.length);
  }
});

deepgramConnection.connect();
await deepgramConnection.waitForOpen();

deepgramConnection.sendSettings({
  type: "Settings",
  audio: {
    input: { encoding: "linear16", sample_rate: 24000 },
    output: { encoding: "linear16", sample_rate: 16000, container: "wav" },
  },
  agent: {
    language: "en",
    listen: { provider: { type: "deepgram", version: "v1", model: "nova-3" } },
    think: {
      provider: { type: "open_ai", model: "gpt-4o-mini" },
      prompt: "You are a friendly AI assistant.",
    },
    speak: { provider: { type: "deepgram", model: "aura-2-thalia-en" } },
    greeting: "Hello! How can I help you today?",
  },
});

npx skills add deepgram/skills

© deepgram, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/deepgram-js-voice-agent of deepgram/deepgram-js-sdk.

Open the folder on GitHubat commit 108a127