ElevenLabs provides real-time speech-to-text via Scribe v2 with ~150ms latency, 99 languages, and built-in VAD-based turn detection. No separate turn detection plugin is needed.
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.
ElevenLabs also provides highly realistic text-to-speech. You can use both in the same agent.
Installation
uv add "vision-agents[elevenlabs]"
Quick Start
from vision_agents.core import Agent, Userfrom vision_agents.plugins import elevenlabs, gemini, getstreamagent = 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=elevenlabs.STT(), tts=elevenlabs.TTS(),)
Set ELEVENLABS_API_KEY in your environment or pass api_key directly.
ElevenLabs STT includes built-in turn detection via VAD. When you use elevenlabs.STT, the Agent automatically ignores any external TurnDetector plugin to prevent conflicts. You do not need to add a separate turn detection plugin.
Next Steps
ElevenLabs TTS
Expressive text-to-speech
Build a Voice Agent
Get started with voice
Was this page helpful?
Assistant
Responses are generated using AI and may contain mistakes.