fixa docs home page
Search...
⌘K
Ask AI
support
dashboard
dashboard
Search...
Navigation
get started
introduction
fixa
fixa-observe
get started
introduction
quickstart
classes
Agent
Scenario
Evaluators
Test
TestRunner
TestResult
On this page
overview
get started
introduction
welcome to fixa - a python package for testing and evaluating AI voice agents
overview
fixa uses a voice agent to call your voice agent and an LLM to evaluate how the conversation went.
under the hood, this package uses:
Pipecat
for the agent
Cartesia for TTS
Deepgram for transcription
OpenAI for the evaluator
Twilio to initiate calls
(other integrations coming soon)
quickstart
Assistant
Responses are generated using AI and may contain mistakes.