deepgram-python-voice-agent

Official

Build a live, interactive voice agent (Python)

Authordeepgram
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Interacting with a voice agent can be complex; this skill provides a blueprint to build and test a real-time, full-duplex voice agent using the Deepgram Python SDK, covering connection, streaming, event handling, and dynamic updates.

Core Features & Use Cases

  • Full-duplex voice agent runtime: STT + LLM + TTS with live conversation and barge-in.
  • Dynamic mid-session updates: swap prompts, speak, or think settings without disconnecting; inject messages; keep-alive; manage conversation history for reconnects.
  • Tool calling and function execution: trigger function/tool calls from the model and handle responses within a single WebSocket session.
  • Durable connections and orchestration: host configuration and context persistence to resume conversations after disconnects.

Quick Start

Run the example to start a live, interactive voice agent connected to agent.deepgram.com and begin exchanging audio.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: deepgram-python-voice-agent
Download link: https://github.com/deepgram/deepgram-python-sdk/archive/main.zip#deepgram-python-voice-agent

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.