Skip to main content
Speech-to-Speech (STS), also known as Realtime in the SDK, is a single provider that handles listening, reasoning, and speaking over one connection. Realtime models include built-in STT, TTS, and turn detection — you configure llm=<provider>.Realtime() without separate speech plugins. You still need edge, agent_user, instructions, API keys, and call lifecycle setup. See Voice Agents for the full guide.

​
How It Works

When the LLM is a Realtime model, the Agent selects RealtimeInferenceFlow:
  • Call audio is sent to the Realtime API
  • Model audio and transcripts are published back to the call
  • STT, TTS, and turn detection plugins are automatically disabled

​
Quick Start

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

agent = Agent(
    edge=getstream.Edge(),
    agent_user=User(name="Assistant", id="agent"),
    instructions="You are a helpful voice assistant.",
    llm=gemini.Realtime(),  # no stt/tts/turn_detection needed
)

​
Realtime vs Custom Pipeline

ModeBest forYou choose
RealtimeFastest path, lowest latencyOne provider for speech in and out
Custom PipelineFull control over each stageSTT, LLM, and TTS independently
Use a custom pipeline when you want to mix providers — for example Deepgram STT, Gemini LLM, and Inworld TTS.

​
Providers

ProviderIntegration page
OpenAIOpenAI Realtime
GeminiGemini Live
QwenQwen OMNI
AWS BedrockAWS Bedrock
xAIxAI
InworldInworld

​
Next Steps

Voice Agents

Realtime setup and provider swapping

Interruption Handling

Barge-in and turn timing

Function Calling

Tools with realtime models

Custom Pipeline

Mix STT, LLM, and TTS providers