audiotrace is a Python package and CLI tool that performs structured analysis on voice-agent call recordings. It extracts transcripts, quality scores, sentiment, latency metrics, cost data, and detected events directly from raw audio files. Designed for developers building or monitoring voice AI applications, it is open source under the MIT license.
In the AI & ML space, audiotrace takes a focused approach. It focuses on analyzing raw audio recordings from voice agents to extract structured metrics like transcripts, quality, sentiment, latency, and cost. audiotrace is an open-source project aimed at developers. The project is open source (MIT License). It runs on the command line, and it can be self-hosted.
It is developed by audiotrace, and it first shipped in 2026. Key capabilities include Audio Transcription, Sentiment Analysis, and Latency Measurement. It exposes integrations via a public API.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match