Deepgram STT

Deepgram provides fast, accurate real-time speech-to-text with built-in turn detection. Ideal for conversational agents.

Vision Agents uses Stream Video for real-time WebRTC transport by default. External WebRTC transports are supported as well. Most AI providers offer free tiers to get started.

Deepgram also provides low-latency text-to-speech. You can use both in the same agent.

Installation

uv add "vision-agents[deepgram]"

Quick Start

from vision_agents.core import Agent, User
from vision_agents.plugins import deepgram, gemini, getstream

agent = Agent(
    edge=getstream.Edge(),
    agent_user=User(name="Assistant", id="agent"),
    instructions="You are a helpful assistant.",
    llm=gemini.LLM("gemini-3-flash-preview"),
    stt=deepgram.STT(),
    tts=deepgram.TTS(),
)

Set DEEPGRAM_API_KEY in your environment or pass api_key directly.

Parameters

stt = deepgram.STT(
    model="nova-3",
    language="en",
    eager_turn_detection=True,
)

Name	Type	Default	Description
model	str	"nova-3"	Deepgram model
language	str	"en"	Language code
eager_turn_detection	bool	False	Enable faster turn detection
api_key	str	None	API key (defaults to DEEPGRAM_API_KEY env var)

Next Steps

Deepgram TTS

Low-latency text-to-speech

Build a Voice Agent

Get started with voice