ElevenLabs

ElevenLabs provides highly realistic and expressive voices for text-to-speech, plus real-time speech-to-text via Scribe. Supports multiple languages and voice styles.

Vision Agents requires a Stream account for real-time transport. Most providers offer free tiers to get started.

Installation

uv add vision-agents[elevenlabs]

Quick Start

from vision_agents.core import Agent, User
from vision_agents.plugins import elevenlabs, 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-2.5-flash"),
    stt=deepgram.STT(),
    tts=elevenlabs.TTS(),
)

Set ELEVENLABS_API_KEY in your environment or pass api_key directly.

TTS

Expressive text-to-speech synthesis.

tts = elevenlabs.TTS(
    voice_id="VR6AewLTigWG4xSOukaG",
    model_id="eleven_multilingual_v2",
)

Name	Type	Default	Description
voice_id	str	"VR6AewLTigWG4xSOukaG"	ElevenLabs voice ID
model_id	str	"eleven_multilingual_v2"	TTS model
api_key	str	None	API key (defaults to ELEVENLABS_API_KEY env var)

STT

Real-time transcription via Scribe v2 (~150ms latency, 99 languages).

stt = elevenlabs.STT(
    model_id="scribe_v2_realtime",
    language_code="en",
)

Name	Type	Default	Description
model_id	str	"scribe_v2_realtime"	Scribe model
language_code	str	"en"	Language code
api_key	str	None	API key (defaults to ELEVENLABS_API_KEY env var)

Scribe v2 does not support turn detection. Use a separate turn detection plugin like Smart Turn if needed.

Next Steps

Build a Voice Agent

Get started with voice

Build a Video Agent

Add video processing