Skip to main content
Inworld AI provides expressive TTS designed for game characters and conversational AI. Offers realistic voices with streaming support.
Vision Agents requires a Stream account for real-time transport. Most providers offer free tiers to get started.

​
Installation

uv add "vision-agents[inworld]"

​
Quick Start

from vision_agents.core import Agent, User
from vision_agents.plugins import inworld, gemini, deepgram, 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=inworld.TTS(),
)
Set INWORLD_API_KEY in your environment or pass api_key directly.

​
Parameters

NameTypeDefaultDescription
voice_idstr"Dennis"Voice ID (available in Inworld Portal)
model_idstr"inworld-tts-1.5-max"Model ("inworld-tts-1.5-max", "inworld-tts-1.5-min")
temperaturefloat1.1Randomness (0-2)
api_keystrNoneAPI key (defaults to INWORLD_API_KEY env var)
Inworld TTS supports up to 2,000 characters per request.

​
Next Steps

Build a Voice Agent

Get started with voice

Build a Video Agent

Add video processing