# Music
> AI instrumental music generation from text prompts — pay per track in USDC or EURC. No API key, no account required.

Instrumental music generation behind x402 micropayments. A single POST /music/generate endpoint accepts a natural-language prompt (plus optional duration, bpm, key) and returns a track_id. The job is processed asynchronously by a music-generation backend (Pixazo/Minimax); poll GET /music/status/{track_id} (free) until complete, then download the audio via GET /music/download/{track_id} (free).

## Pricing
- `premium` tier — **$0.106125** on Base: `/music/generate`
- Chains: Base, Arbitrum, Polygon, Avalanche. Per-chain prices in `/.well-known/x402.json`.

## Operations
### inference
- **POST /music/generate** — Generate an AI instrumental music track from a text prompt. Returns a track_id for async completion; poll /music/status/{track_id} then download /music/download/{track_id}. — params: `prompt` (string)*, `duration` (integer), `bpm` (integer), `key` (string) (tier: `premium`)

## Workflows
- **music_generate** (Generate an instrumental track from a prompt): `generate`

## Data sources
- Pixazo (audio-generation) — Primary music generation backend.
- Minimax (audio-generation) — Alternative generation backend (platform.minimax.io).
- DeepSeek (prompt-structuring)

## Free endpoints
- GET `/`, `/health`, `/about`, `/.well-known/x402.json`, `/llms.txt`, `/openapi.json` (standard)
- GET `/music/status/{track_id}` — Check generation status (free)
- GET `/music/download/{track_id}` — Download completed audio (free)
- GET `/music/feedback` — Return the 50 most recent feedback entries
- POST `/music/feedback` — Submit feedback (response_id, rating 1-5, optional comment)

## Examples
- `generate` — Generate upbeat jazz: `{"prompt": "Upbeat jazz with saxophone, walking bass, brushed drums", "duration": 180, "bpm": 120}`