+ P Observe, evaluate, and improve your ElevenLabs agents
Capture every text-to-speech call from your ElevenLabs voice layer as structured trace data, alongside the rest of your agent's spans.
What Prefactor records from ElevenLabs
ElevenLabs + Prefactor
Observe for ElevenLabs
Prefactor observes your ElevenLabs agents in real time — every LLM call, tool invocation, and custom span captured as st
Open → EvaluateEvaluate for ElevenLabs
Prefactor evaluates your ElevenLabs agents — score outcome quality against the captured spans, track drift by comparing
Open → ObserveAct for ElevenLabs
Prefactor acts on your ElevenLabs agents at runtime — block, throttle, sandbox, or escalate a tool call or data access b
Open →How the ElevenLabs integration works
- Text-to-speech calls, voice/model selection, and streaming synthesis events each become spans in the conversation timeline.
- Beyond auto-captured spans, use withSpan to record any custom step you define — a quality check, a latency budget, a business action.
ElevenLabs integration FAQ
Do I need a dedicated package for ElevenLabs?
You can instrument ElevenLabs today with the framework-agnostic prefactor-core SDK; a dedicated package can be added on request.
What does Prefactor capture from ElevenLabs?
Prefactor records text-to-speech calls, voice/model selection, and streaming synthesis events as structured, timestamped spans — so every ElevenLabs call is captured as trace data you can reconstruct, search and export end to end.
Does Prefactor add latency or change how ElevenLabs runs?
No. Observability capture is designed to stay off your agent's critical path, so it doesn't alter your ElevenLabs synthesis or your callers' experience. The only part that acts inline is the optional runtime guardrails you enable per agent — by design, so a high-risk or low-confidence action can be held for human approval before it executes.
Can I evaluate agents that use ElevenLabs and catch regressions?
Yes. Once runs are captured, eval suites score quality and latency on real traffic, drift detection flags behaviour changes after deployment, and versioned eval history catches regressions before they ship — the observe → evaluate → improve loop applied to your ElevenLabs-powered agents.
Related guides
See it on your ElevenLabs agents
Book a 15-minute setup and our team gets you tracing in production.