Back
productivitymediaOpen source

Jev Voice Agent

Run a real-time voice agent from prewritten replies and Jev choices.

What Jev decides

Which fixed reply label fits the latest caller turn.

Deepgram handles speech input and output while Jev chooses one approved reply label from a fixed script without an LLM in the loop.

CHOICE
Jev role
Choose the next prewritten spoken reply.
Input
The latest transcript, conversation state, and allowed reply labels.
Output
A reply label and its Choice probabilities.
Decision frequency
After each completed caller turn.
Fallback
The agent can only speak human-authored lines; open-ended answers are outside this design.
Author reported · Source reviewed

How it works

Input
The latest transcript, conversation state, and allowed reply labels.
Jev
CHOICE
Output
A reply label and its Choice probabilities.

Overview

Deepgram Flux detects spoken turns and transcribes them. Jev reads the transcript and selects a reply from human-written lines, then Flux TTS speaks that line. This keeps replies inside a fixed script but limits open-ended conversation; the repository includes offline recorded scenarios and a section on when this design stops fitting.

Language
TypeScript
License
MIT
Author
dg-coreylweathers
Sources checked Sep 24, 2026

Sources

Related projects