skillfed

livekit-plugins-deepgram

Agent Framework plugin for services using Deepgram's API.

livekit-plugins-deepgram v1.6.10 2.7M downloads/30d#2,949 on PyPI13,002
Permissive license Apache-2.0 Active released

What it is and what it does

This package is a plugin that bridges Deepgram's voice AI platform with LiveKit Agents, enabling speech-to-text and text-to-speech capabilities in agent-based applications. It wraps Deepgram's API behind the livekit-agents framework, allowing developers to add voice transcription and synthesis to real-time communication workflows.

The plugin is designed for applications that need to process voice in real-time—such as live transcription, voice-driven agents, or automated voice responses. It depends on livekit-agents for framework integration and numpy for numerical operations, and requires a Deepgram API key to function.

Use it for:

  • Add live transcription to video conferencing applications powered by LiveKit Agents.
  • Build voice-controlled agents that understand and respond to spoken input.
  • Implement automated voice responses in real-time communication systems.
  • Create accessibility features that transcribe or synthesize speech in agent workflows.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Integrates Deepgram's voice AI services (speech-to-text and text-to-speech) into LiveKit Agents for real-time audio processing in agent applications.

Yes. The package is actively maintained, has no known vulnerabilities, and integrates cleanly into the LiveKit ecosystem with low install friction. Install it if you are building LiveKit Agents that need Deepgram's speech-to-text or text-to-speech services. You will need a Deepgram API key to use it.

Install

livekit-plugins-deepgram on PyPI

pip

pip install livekit-plugins-deepgram

uv

uv add livekit-plugins-deepgram

poetry

poetry add livekit-plugins-deepgram

Installing livekit-plugins-deepgram

Before you install

Low install friction with a pure-Python wheel distribution. Actively maintained with a release on 2026-08-13 and no known vulnerabilities. Depends only on livekit-agents and numpy.

License in practice

Apache-2.0 permissive license allows commercial and private use with minimal restrictions; suitable for most projects.

Quickstart

pip install livekit-plugins-deepgram

# Set DEEPGRAM_API_KEY environment variable before use
import livekit_plugins_deepgram

Requires a valid Deepgram API key set as the DEEPGRAM_API_KEY environment variable; Python 3.10 or later (requires_python >=3.10.0).

Verify before relying

  • Whether Deepgram API key setup is required before any functionality works
  • Specific audio format or codec support details beyond the integration scope
  • How the plugin exposes STT and TTS functionality through livekit-agents

Package facts

License Apache-2.0 (permissive)
Python support supports the current Python release (>=3.10.0)
Install friction low — pure-Python wheel
Runtime dependencies 2 — livekit-agents, numpy
Maintenance actively maintained — 1 days since the last release
Last repo commit
First released
Downloads 2,672,833/month — #2,949 on PyPI (30-day window, as of 2026-08-14)
Known vulnerabilities none known (OSV.dev, checked 2026-08-14)

Evidence: livekit_plugins_deepgram-1.6.10-py3-none-any.whl

Keywords: ai, audio, deepgram, livekit, realtime, video, voice

Intended Audience :: DevelopersLicense :: OSI Approved :: Apache Software LicenseProgramming Language :: Python :: 3Programming Language :: Python :: 3 :: OnlyProgramming Language :: Python :: 3.10Topic :: Multimedia :: Sound/AudioTopic :: Multimedia :: VideoTopic :: Scientific/Engineering :: Artificial Intelligence

Tags

deepgram speech to textlivekit agent integrationreal-time voice aideepgram tts stt pluginlive audio transcriptionvoice ai agents
voice-aireal-time-audiolivekit-plugin

More Artificial Intelligence packages

litellm

LiteLLM provides a unified Python interface to…

permissive · top 100 on PyPI

huggingface-hub

Client library and CLI tool for downloading,…

permissive · top 100 on PyPI

langchain

LangChain provides a framework for building…

permissive · top 1,000 on PyPI

hf-xet

hf-xet provides chunk-based deduplication and…

permissive · top 1,000 on PyPI

tokenizers

Tokenizers converts raw text into token…

permissive · top 1,000 on PyPI

transformers

Transformers provides a unified framework for…

permissive · top 1,000 on PyPI

deepgram-sdk

Official Python SDK for Deepgram's speech…

permissive · top 5,000 on PyPI

livekit-plugins-aws

Integrates Amazon AWS AI services (Bedrock,…

permissive · top 15,000 on PyPI

livekit-plugins-cartesia

Integrates Cartesia's voice AI services…

permissive · top 5,000 on PyPI

livekit-plugins-sarvam

Integrates Sarvam.ai's Indian-language voice AI…

permissive · top 15,000 on PyPI

livekit-plugins-soniox

Integrates Soniox speech-to-text and…

permissive · top 15,000 on PyPI

livekit-plugins-google

Integrates Google Cloud AI services (Gemini,…

permissive · top 5,000 on PyPI

livekit-plugins-inworld

Integrates Inworld's text-to-speech and…

permissive · top 15,000 on PyPI

livekit-plugins-gladia

Integrates Gladia's speech-to-text API with…

permissive · top 15,000 on PyPI

livekit-plugins-azure

Integrates Azure AI services, particularly…

permissive · top 15,000 on PyPI

livekit-plugins-speechmatics

Integrates Speechmatics speech-to-text into…

permissive · top 15,000 on PyPI

Further reading