Skip to main content

Documentation Index

Fetch the complete documentation index at: https://visionagents.ai/llms.txt

Use this file to discover all available pages before exploring further.

Vogent uses neural models to predict when a speaker has completed their conversational turn. Provides intelligent turn-taking for natural conversation flow.
Vision Agents requires a Stream account for real-time transport. Most providers offer free tiers to get started.

​
Installation

uv add "vision-agents[vogent]"

​
Quick Start

from vision_agents.core import Agent, User
from vision_agents.plugins import vogent, gemini, deepgram, elevenlabs, 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=elevenlabs.TTS(),
    turn_detection=vogent.TurnDetection(),
)
Models download automatically on first use.

​
Parameters

NameTypeDefaultDescription
buffer_in_secondsfloat2.0Audio buffer duration
confidence_thresholdfloat0.5Turn completion threshold (0-1)
sample_rateint16000Audio sample rate

​
Events

from vision_agents.core.turn_detection.events import TurnStartedEvent, TurnEndedEvent

@turn_detection.events.subscribe
async def on_turn_ended(event: TurnEndedEvent):
    print(f"User finished: confidence={event.confidence}")

​
Next Steps

Build a Voice Agent

Get started with voice

Build a Video Agent

Add video processing