End-to-end testing for voice agents. YAML scenarios, real audio through LiveKit/Daily/VAPI/Retell, and 13 evaluators for latency, tone, and roleplay consistency.
This repository also configures its own agents. See what voicecheck tells them →
Skill Claude Code
Set up VoiceCheck end to end — install the package with the right extras, run a zero-key smoke test to prove the pipeline works, configure a transport (LiveKit, Daily, VAPI, or Retell) and audio providers, then scaffold, validate, and run a first scenario. Use when someone wants to install, onboard onto, or get…
Skill Claude Code
Author a VoiceCheck test for a voice agent — turn a description of what the agent should do into a scenario YAML with the right evaluators, validate and dry-run it, then optionally wire it into pytest. Use when someone wants to write a VoiceCheck scenario, add a voice-agent test, assert latency / tone / tool calls /…