asterisk-ai-voice-agent is a self-hosted developer package that connects Asterisk telephony to streaming speech-to-text, LLM processing, and text-to-speech over AudioSocket. It supports barge-in and 20 ms audio frame pacing for conversational voice applications.
asterisk-ai-voice-agent sits in PulseGate's Other voice & speech category. It focuses on building a self-hosted conversational voice agent for Asterisk telephony with streaming speech recognition and speech synthesis. It is built as an open-source project for telephony and VoIP developers. asterisk-ai-voice-agent is open source under the MIT license. asterisk-ai-voice-agent is available on the command line and API, and it can be self-hosted.
It is developed by ICT Innovations, and it first shipped in 2026. The project is developed in the open on GitHub with 8 commits in the last 90 days. Among its 8 catalogued features are speech-to-text, LLM processing, and text-to-speech. 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
Closest matches by what these projects do