GitHub - keltokhy/writ-fm: 24/7 AI-powered internet radio station. Claude writes the DJ scripts, Chatterbox speaks them.

A 24/7 AI-powered music-forward radio station. AI generates the music, writes short hosted breaks, TTS speaks them, and the stream runs forever.

What is this?

WRIT-FM is a music-forward internet radio station where:

5 AI hosts rotate across 8 shows, each with a distinct voice and topic focus
AI-generated music is the primary content
Short hosted talk breaks play occasionally between larger music blocks
Scripts are written by Claude CLI, rendered by Kokoro TTS
Music is generated by ACE-Step via music-gen.server
A Claude Code operator loop keeps everything stocked and running 24/7

Architecture

┌──────────────────────────────────────────────────────────────┐
│  writ CLI                     (tmux-based process manager)   │
├──────────────────────────────────────────────────────────────┤
│  ezstream + feeder.py                                        │
│    ├── ezstream: Icecast source client (Ogg Vorbis)          │
│    ├── feeder.py: builds playlists per show schedule          │
│    ├── Builds music-forward playlists with hosted breaks       │
│    ├── Detects new content and reloads playlist (SIGHUP)      │
│    └── Runs API server as daemon thread (:8001)              │
├──────────────────────────────────────────────────────────────┤
│  Icecast :8000 ──► cloudflared tunnel ──► public URL         │
│  API :8001 ───► /now-playing /schedule /health /messages     │
├──────────────────────────────────────────────────────────────┤
│  content_generator/                                          │
│    ├── talk_generator.py        (Claude CLI + Kokoro TTS)    │
│    ├── music_bumper_generator.py (ACE-Step via music-gen)    │
│    ├── listener_response_generator.py                        │
│    └── persona.py               (5 hosts, station identity)  │
├──────────────────────────────────────────────────────────────┤
│  operator_daemon.sh             (Claude Code maintenance)    │
│  listener_daemon.sh             (message → on-air response)  │
└──────────────────────────────────────────────────────────────┘

Quick Start

1. Install dependencies

# Install uv (Python package manager)
curl -LsSf https://astral.sh/uv/install.sh | sh

# Install system dependencies (macOS)
brew install icecast ffmpeg ezstream vorbis-tools

# Set up Python environment
uv sync

2. Set up TTS

cd mac/kokoro
uv venv
uv pip install kokoro soundfile
# Downloads ~200MB model on first run

3. Configure

cp config/icecast.xml.example config/icecast.xml
cp mac/config.yaml.example mac/config.yaml

# Edit mac/config.yaml — set Icecast password (must match icecast.xml)

4. Start the station

The writ CLI manages all components via tmux:

./writ start          # Start core streaming stack (icecast, stream, tunnel)
./writ start all      # Start core + content daemons
./writ status         # Health check all components
./writ stop           # Stop everything

Start individual components:

./writ start icecast  # Icecast server
./writ start stream   # Streamer + API
./writ start tunnel   # Cloudflared tunnel
./writ start content  # music-gen, operator, listener
./writ start operator # Claude Code maintenance loop

Other commands:

./writ logs stream -f     # Tail streamer logs
./writ attach operator    # Attach to operator tmux window
./writ restart stream     # Restart a component

5. Generate content

./writ generate talk                          # 2 talk breaks per upcoming slot
./writ generate talk --show midnight_signal   # Specific show
./writ generate music                         # AI music tracks
./writ generate status                        # Show segment counts

Or run generators directly:

uv run python mac/content_generator/talk_generator.py --all --count 2 --min 3
uv run python mac/content_generator/music_bumper_generator.py --all --min 20

Hosts

Host	Voice	Focus
The Liminal Operator	`am_michael`	Philosophy, radio lore, morning reflections
Dr. Resonance	`bm_daniel`	Music history, genre archaeology
Nyx	`af_heart`	Dreams, night philosophy
Signal	`am_onyx`	News analysis, current events
Ember	`af_bella`	Soul, funk, music as feeling

Weekly Schedule

8 talk shows rotate across the day. See config/schedule.yaml for the full definition.

Daily base schedule:

00:00-04:00 — Midnight Signal (Liminal Operator — philosophy)
04:00-06:00 — The Night Garden (Nyx — dreams, night)
06:00-09:00 — Dawn Chorus (Liminal Operator — morning reflections)
09:00-12:00 — Sonic Archaeology (Dr. Resonance — music history)
12:00-14:00 — Signal Report (Signal — news analysis)
14:00-16:00 — The Groove Lab (Ember — soul, funk)
16:00-18:00 — Crosswire (Dr. Resonance + Ember — panel debate)
18:00-20:00 — Sonic Archaeology
20:00-22:00 — The Groove Lab
22:00-00:00 — The Night Garden

Weekly override:

Sunday 18:00-20:00 — Listener Hours (mailbag)

Segment Types

Hosted talk breaks (450-1000 words):

deep_dive — Compact single-topic exploration
news_analysis — Current events through a late-night lens (uses RSS headlines)
interview — Short simulated interview with a historical or fictional figure
panel — Two hosts discuss a topic from different angles
story — Narrative storytelling from music and culture
listener_mailbag — Listener letters and responses
music_essay — Focused essay on an artist, album, or genre

Short-form (transitions):

station_id — Station identification
show_intro — Show opening
show_outro — Show closing

Automated Operation

The operator daemon runs Claude Code on a 15-minute loop to:

Health-check the stream, Icecast, and encoder
Stock AI music tracks when music-gen.server is available (minimum 20 per show)
Stock short talk breaks for current and upcoming shows (minimum 3 per slot)
Process listener messages into on-air responses
Carry editorial continuity across runs via the station ledger and intent cards

./writ start operator   # Start via writ CLI (tmux-managed)
./run_operator.sh       # Run once manually
bash mac/operator_daemon.sh  # Run as a persistent loop

Each run reads an operator brief (mac/content_generator/context.py --operator-brief) summarizing recent topics, active threads, unread listener messages, and the operator's own recent diary entries. The operator picks a run mode — maintenance, responsive, continuity, special, or quiet — and may write intent cards in output/operator_intents/ to guide specific segments. Editorial decisions and free-form diary notes are appended to the station ledger (~/.writ/station_ledger.jsonl) so future runs can carry threads forward and pick up the operator's voice across passes instead of starting cold each time.

The listener daemon polls for new messages every 30 seconds and generates spoken responses:

Customizing

Change hosts and personalities — Edit mac/content_generator/persona.py. Each host has an identity, voice style, philosophy, and anti-patterns.

Modify the schedule — Edit config/schedule.yaml to add/remove shows, change time slots, or assign different hosts and voices.

Use different TTS voices — Kokoro includes 28 voices (see mac/kokoro/tts.py). Assign voices per-show in config/schedule.yaml.

Add music styles — Edit mac/content_generator/music_pools_expanded.py to change the AI music generation prompts per show.

Files

├── writ                        # Station CLI (start/stop/status/logs/generate)
├── run_operator.sh             # Single operator run (Claude Code, with lock + timeout)
├── mac/
│   ├── feeder.py               # Playlist feeder (manages ezstream + API)
│   ├── radio.xml               # ezstream config (Icecast, Ogg encoding)
│   ├── api_server.py           # Now-playing API (daemon thread in feeder)
│   ├── schedule.py             # Schedule parser and resolver
│   ├── play_history.py         # Track history and dedup
│   ├── music_gen_client.py     # REST client for music-gen.server
│   ├── operator_prompt.md      # Music-forward operator maintenance prompt
│   ├── operator_daemon.sh      # Operator loop (runs run_operator.sh)
│   ├── listener_daemon.sh      # Listener message polling daemon
│   ├── start_music_gen.sh      # Start music-gen + daemons in tmux
│   ├── kokoro/                 # Kokoro TTS wrapper
│   ├── content_generator/
│   │   ├── talk_generator.py              # Talk segment generator (with --intent support)
│   │   ├── music_bumper_generator.py      # AI music bumper generator
│   │   ├── listener_response_generator.py # Listener message → audio
│   │   ├── context.py                     # Operator brief and intent card templates
│   │   ├── ledger.py                      # Append-only editorial memory
│   │   ├── music_pools_expanded.py        # Music generation prompts
│   │   ├── persona.py                     # Host definitions and station identity
│   │   └── helpers.py                     # Shared utilities
│   └── config.yaml             # Local config
├── config/
│   ├── schedule.yaml           # Weekly show schedule
│   └── icecast.xml.example     # Icecast template
├── output/
│   ├── talk_segments/{show}/   # Generated hosted breaks
│   ├── music_bumpers/{show}/   # AI-generated music tracks
│   └── scripts/                # Script metadata
└── docs/                       # Web-facing pages

Requirements

Python 3.11+
ffmpeg, ezstream, vorbis-tools
Icecast2
Claude CLI (for script generation and operator loop)
Kokoro TTS (~200MB model)
music-gen.server + ACE-Step (optional, for AI music tracks)
cloudflared (optional, for public tunnel)
Apple Silicon recommended

License

MIT