live-radio/README.md

# Live Ozan Radio

Personal AI radio — **no catalog music, ever**. DeepSeek is the DJ. Google **Lyria 3** composes every track. Taste comes from `settings.json` + `taste_seeds.json` — usually built from **Spotify screenshots in Cursor** (no Spotify API).

Inspired by [Magenta RealTime 2](https://magenta.withgoogle.com/magenta-realtime-2) (live, ~200ms) and [Lyria 3](https://deepmind.google/models/lyria/) (full songs via Gemini API). On Mac you can layer MRT2 for true live improvisation; this repo ships the cross-platform Lyria + DeepSeek stack first.

## Stack

| Layer | Product | Role |
|-------|---------|------|
| DJ brain | DeepSeek (Tinqs proxy or BYOK) | Mood, prompts, chat, variety |
| Music engine | Google Lyria 3 Pro / Clip | Generate MP3 tracks |
| Taste | `settings.json` + `taste_seeds.json` | Profile from screenshots or manual edit — see below |
| Player | FastAPI + `gateway/player.html` | Stream queue, library, chat, dashboard |
| Live (optional) | Magenta RealTime 2 | Apple Silicon only — see below |

## Player dashboard

Open **http://127.0.0.1:8787/player** after starting the server.

| Feature | What it does |
|---------|----------------|
| **Cost dashboard** | Today's estimated spend, per-track cost, songs generated vs daily cap |
| **Settings (gear icon)** | Shuffle mode, mix saved + new tracks, new-song chance, max songs/day |
| **Shuffle mode** | On track end or Skip, picks a random saved song or composes a new one |
| **Saved songs** | Click any track in the library to play |
| **DJ chat** | Talk to DeepSeek — requests can trigger new Lyria generations |

### Shuffle behaviour

When shuffle is on (default):

1. If you have saved songs **and** daily quota remains, each next track has a `new_song_chance` (default 35%) of being freshly composed.
2. Otherwise a random saved song plays (never the same track twice in a row if alternatives exist).
3. If the library is empty, it generates until the daily cap is hit.

Daily generation stats live in `songs/stats.json` (gitignored, local runtime only).

## Taste from Spotify screenshots (recommended)

**No Spotify API keys.** Screenshot your library (Home, Daily Mixes, playlists), open this repo in **Cursor**, attach images, and paste the prompt from **[docs/TASTE-FROM-SCREENSHOTS.md](docs/TASTE-FROM-SCREENSHOTS.md)**. The agent updates `settings.json` and `taste_seeds.json`.

Share that doc with friends — same flow for group taste (WhatsApp links + screenshots).

## Taste (`settings.json`)

Edit `settings.json` at the repo root, or let Cursor fill it from screenshots. The DJ reloads it on every generate and chat.

```json
{
  "taste": { "summary": "...", "genres": [], "mood": [], "instruments": [] },
  "playback": {
    "shuffle": true,
    "mix_existing_and_new": true,
    "new_song_chance": 0.35
  },
  "limits": { "max_new_songs_per_day": 10 },
  "costs": {
    "lyria_pro_usd": 0.08,
    "lyria_clip_usd": 0.04,
    "deepseek_per_track_usd": 0.002
  }
}
```

**Example profile (Ozan):** checked-in [`settings.json`](settings.json) + [`taste_seeds.json`](taste_seeds.json) — Anadolu psych + ethnic dubtronica from Spotify screenshots. Copy the structure for your own taste.

The player settings panel PATCHes `playback` and `limits` via `/api/settings` and writes back to this file.

## Saved songs

Every track is written to `./songs/` and **committed via Git LFS** (audio) + plain git (metadata):

| File | Storage | Contents |
|------|---------|----------|
| `{id}_{title}.mp3` | LFS | Audio |
| `{id}.meta.json` | git | Title, mood, DJ line, prompt, lyrics, timestamp |
| `manifest.json` | gitignored | Runtime queue index |

Browse in the player under **Saved songs**, or `GET /api/songs`. After clone: `git lfs install` then `git lfs pull`.

## Quick start (Forge / Windows)

```powershell
cd live-ozan-radio
python -m venv .venv
.venv\Scripts\activate
pip install -e .
copy .env.example .env
# Fill GEMINI_API_KEY + DEEPSEEK_API_KEY
# Taste: docs/TASTE-FROM-SCREENSHOTS.md (Cursor + Spotify screenshots)

$env:DEEPSEEK_BASE_URL = "https://api.deepseek.com/v1"
python -m ozan_radio serve
# Open http://127.0.0.1:8787/player
```

One-shot track (no server):

```powershell
python -m ozan_radio generate
```

## Environment

| Variable | Required | Notes |
|----------|----------|-------|
| `GEMINI_API_KEY` | Yes | [Google AI Studio](https://aistudio.google.com/apikey) — Lyria 3 |
| `DEEPSEEK_API_KEY` | Yes | Tinqs proxy token or DeepSeek direct |
| `DEEPSEEK_BASE_URL` | No | Default `https://api.deepseek.com/v1` |
| `LYRIA_MODEL` | No | `lyria-3-pro-preview` (default) or `lyria-3-clip-preview` |
| `RADIO_OUTPUT_DIR` | No | Default `./songs` |

### Cost estimates (defaults)

| Model | ~USD / track |
|-------|----------------|
| Lyria 3 Pro + DeepSeek | ~$0.082 |
| Lyria 3 Clip | ~$0.04 |

At the default cap of 10 new songs/day with Lyria Pro, projected max spend is **~$0.82/day**. Adjust `costs` and `limits` in `settings.json` or the player settings panel.

## API

| Method | Path | Description |
|--------|------|-------------|
| GET | `/api/now` | Current track metadata |
| GET | `/api/queue` | Full queue |
| GET | `/api/stats` | Dashboard: today's spend, quota, cost estimates |
| GET | `/api/settings` | Playback, limits, costs |
| PATCH | `/api/settings` | Update shuffle, daily cap, etc. |
| POST | `/api/generate` | DJ plans + Lyria renders next track |
| POST | `/api/shuffle/next` | Smart next: library shuffle or new generation |
| POST | `/api/skip` | Advance (uses shuffle when enabled) |
| GET/POST | `/api/chat` | DJ chat log and messages |
| GET | `/api/songs` | Saved library |
| POST | `/api/songs/{id}/play` | Play a saved track |
| GET | `/stream/{file}` | MP3 stream |
| GET | `/player` | Web UI |

## Magenta RealTime 2 (optional live layer)

On **Apple Silicon** (Kraken), install [magenta-rt](https://github.com/magenta/magenta-realtime) for sub-second live generation:

```bash
uv pip install "magenta-rt[mlx]"
mrt models init && mrt models download
mrt mlx generate --prompt "disco funk" --duration 4.0 --model=mrt2_small
```

Wire MRT2 as a bridge between tracks or as a live “bed” under the Lyria queue — PRs welcome.

## Repo

Public on Git Studio: **https://tinqs.com/tinqs/live-radio**

```bash
git clone git@ssh.tinqs.com:tinqs/live-radio.git
cd live-radio
git lfs install && git lfs pull
```

Static player preview: `https://tinqs.com/tinqs/live-radio/src/branch/main/gateway/player.html` (shell only — audio streams from your running server).

## Agent usage

DeepSeek (Pi, Cursor, Claude Code) can operate the station via HTTP or the skill in `.cursor/skills/ozan-radio/SKILL.md`.

## License

Apache 2.0 — same spirit as Magenta RealTime 2 open weights.