DuplexJev-32B and DuplexJev-4B: speech decision models for full-duplex voice agents. Typed single-token readout from a frozen speech LLM, served with vLLM. Try it: api.adventists.cn/duplexjev
-
Updated
Nov 8, 2026 - Python
DuplexJev-32B and DuplexJev-4B: speech decision models for full-duplex voice agents. Typed single-token readout from a frozen speech LLM, served with vLLM. Try it: api.adventists.cn/duplexjev
Set of 📝 with 🔗 to help those building realtime (S2S) voice ai 🎙️🤖
This repository showcases the integration between Agent Voice Response and Ultravox's Real-time Speech-to-Speech API. The application leverages Ultravox's powerful language model to process audio input from users, providing intelligent, context-aware responses in real-time audio format.
Twilio-to-Ultravox voice-agent backend with transcript ingestion, monitoring dashboard, and automated risk analysis (keyword + Gemini) for conversation review.
Voice-first mental health support backend using Twilio + Ultravox with Gemini-based risk analysis, dashboards, and conversation monitoring.
Voice AI agent for ISP tech support on Asterisk + Ultravox: FAQ, client lookup, NetBox data, SSH switch diagnostics, Telegram call reports (RO/RU)
A reference integration between Teler and Ultravox, based on Media Streaming over WebSockets.
MCP server for Ultravox — API coverage for voice AI agents.
A reference Node integration between Teler and Ultravox, based on Media Streaming over WebSockets.
To associate your repository with the ultravox topic, visit your repo's landing page and select "manage topics."