ArchishmanSengupta/autovoiceevals
A self-improving loop for voice AI agents. Uses karpathy's autoresearch as foundation.
This tool helps you automatically improve your voice AI agent's performance. You provide details about your agent's purpose, services, and limitations. It then generates challenging scenarios, tests your agent against them, and suggests prompt improvements, keeping what works best. This is ideal for product managers, customer service managers, or anyone responsible for a voice AI's effectiveness.
Use this if you manage a voice AI agent and want to continuously improve its ability to handle diverse and complex customer interactions without manual testing.
Not ideal if you need a static testing suite or are not using a Vapi, Smallest AI, or ElevenLabs conversational AI platform.
Stars
83
Forks
13
Language
Python
License
MIT
Category
Last pushed
Mar 18, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/ArchishmanSengupta/autovoiceevals"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
rapidaai/voice-ai
Rapida is an open-source, end-to-end voice AI orchestration platform for building real-time...
lixiangyu890601/EasyAICC-Easy-AI-Call-Center
外呼系统，智能外呼，自动外呼系统，人工外呼，呼叫中心
modal-labs/quillman
A voice chat app
voicetestdev/voicetest
Test harness for voice agents. Import from Retell, VAPI, Bland, LiveKit. Run autonomous...
DrDroidLab/voicesummary
Open Source AI Database for Voice Agent Transcripts | Call Analysis & Insights | Extraction |...