Agentic Radiostation
Academic Paper · 2025

Agentic Radiostation

An Autonomous AI-Powered Radio Broadcast System in Pure Rust

by Shyamal Chandra

4,102
Lines of Rust
Zero external runtimes
22
Source Files
Across 8 modules
6
DJ Personalities
Unique styles & voices
3
AI Agents
DJ · Producer · Music Director

Abstract

We present Agentic Radiostation, a fully autonomous radio broadcast system implemented in 100% pure Rust. The system combines multiple AI agents — a DJ, a Producer, and a Music Director — with real-time audio processing and HTTP streaming to create a self-sustaining, personality-driven radio station. Built without external runtimes, the project demonstrates how modern systems programming languages can host sophisticated agentic workflows, real-time audio pipelines, and interactive user interfaces in a single statically-linked binary.

Architecture

Three autonomous agents collaborate over shared state to produce a continuous, engaging radio feed.

The creative voice

DJ Agent

Six distinct personalities (DJ Turbo, Crystal Wave, Luna Nightshade, Nocturne, Sunny Daye, Chill Bot) each with unique style, catchphrases, energy level, and track-selection algorithms. Scores songs by energy compatibility, BPM proximity, artist rotation, and style fit.

The programmer

Producer Agent

Builds day-part-optimized schedules across six time segments — Early Morning through Late Night — assigning genre-appropriate DJs and mood-matched playlists to each slot.

The curator

Music Director

Manages listener requests, tracks rotation counts, recommends songs by mood, surfaces underplayed tracks, and ensures the station stays fresh across long-running sessions.

Audio Pipeline

Step 1
Decode
Symphonia pure-Rust decoder — any format to f32 PCM
Step 2
TTS
macOS say command with AIFF-to-PCM conversion
Step 3
Synthesize
Synthetic tone generation as fallback
Step 4
Encode
PCM to 16-bit LE with WAV headers
Step 5
Stream
Icecast/Shoutcast-compatible HTTP stream

Key Findings

The paper explores four transformative implications of autonomous AI-powered radio.

Democratization of Radio

Traditional radio requires studio infrastructure, licensed talent, and continuous operational cost. This system collapses that into a single binary that runs on any machine. A community center, school, or individual can operate a 24/7 radio station with zero marginal labor cost.

Zero marginal labor cost for 24/7 broadcast

Rust as an Agent Platform

Rust's ownership model and zero-cost abstractions make it a natural host for agentic systems. Agents become first-class types with trait bounds and pattern-matched state machines — all in the same binary, without a garbage collector, with thread safety guaranteed at compile time.

Thread-safe agents guaranteed at compile time

Agent Collaboration Patterns

The three-agent architecture establishes a reusable pattern: a creative agent (DJ) that produces content, a planning agent (Producer) that schedules and curates, and a service agent (Music Director) that handles external input and discovery. Separation of concerns, enforced at the type level.

Type-level separation of concerns

Future of Synthetic Media

The same architecture could produce personalized news casts, educational radio for classrooms, ambient soundscapes for workspaces, or branded radio for retail environments — each with a unique voice and schedule, each fully autonomous.

Personalized, autonomous media generation

The First Station on a Much Larger Dial

Agentic Radiostation is a proof point that autonomous, personality-driven media broadcast is achievable today with a single Rust binary. Its architecture — AI agents coordinating over shared state, real-time audio processing, and HTTP streaming — establishes patterns that will generalize to other domains: automated podcasting, personalized audio feeds, and agentic content generation of all kinds.

Full Paper

Download PDF

Your browser does not support inline PDF viewing.

Download the PDF to read the full paper.

Download PDF