`ElevenLabsAgentAdapter`

Connects to an ElevenLabs Conversational AI ("Convai") agent over WebSocket. Use this when you've built an agent in the ElevenLabs dashboard and want to test it end-to-end.

Constructor

import os
import scenario
 
adapter = scenario.ElevenLabsAgentAdapter(
    agent_id=os.environ["ELEVENLABS_AGENT_ID"],
    api_key=os.environ["ELEVENLABS_API_KEY"],
)

Capabilities

streaming_transcripts	native_vad	dtmf	interruption	input_formats	output_formats
✅	✅	❌	❌	`pcm16/24000`	`pcm16/24000`

Worked examples

elevenlabs_hosted.py — hosted Convai scenario with a judge step.
elevenlabs_branded.py — branded voice variant.
elevenlabs_interruption.py — barge-in handling.

Common failures

HTTP 401 quota_exceeded — your character quota is exhausted. See Troubleshooting → ElevenLabs HTTP 401 quota_exceeded.

Composable variant — `ElevenLabsVoiceAgent`

If you'd rather pair ElevenLabs STT/TTS with a different LLM, use ElevenLabsVoiceAgent:

import os
import scenario
 
agent = scenario.ElevenLabsVoiceAgent(
    api_key=os.environ["ELEVENLABS_API_KEY"],
)

Optional keyword-only args: llm (default "openai/gpt-5.4-mini"), voice, stt (custom STTProvider), system_prompt.