# Stella Managed Media — Music

Capabilities for text-to-music generation.

Audience: AI agents. Plain text on purpose. Curl me.

## Capabilities

### `text_to_music` — generate a short music clip

- Single profile (`default`); Google Lyria 3 Pro preview.
- Convenience field: `prompt` becomes a single weighted prompt if `weightedPrompts` is not supplied.
- Useful `input` fields: `promptLabel`, `weightedPrompts`, `musicGenerationConfig`.
- `musicGenerationConfig` fields: `bpm` (55–145), `density` (0.05–0.9), `brightness` (0.1–0.8), `guidance` (2–5), `temperature` (0.6–1.4), optional `musicGenerationMode: "VOCALIZATION"`.

```bash
curl -X POST "$STELLA_API/api/media/v1/generate" \
  -H "Authorization: Bearer $STELLA_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "capability": "text_to_music",
    "prompt": "warm lo-fi keys, soft vinyl texture, gentle drums",
    "input": {
      "promptLabel": "Rainy tape",
      "musicGenerationConfig": {
        "bpm": 85,
        "density": 0.5,
        "brightness": 0.4,
        "guidance": 4,
        "temperature": 1.1
      }
    }
  }'
```

For more control, pass explicit weighted prompts:

```json
{
  "capability": "text_to_music",
  "input": {
    "promptLabel": "Neon focus",
    "weightedPrompts": [
      { "text": "steady ambient electronica with soft arpeggios", "weight": 1 },
      { "text": "harsh distorted guitars", "weight": -0.6 }
    ],
    "musicGenerationConfig": {
      "bpm": 104,
      "density": 0.45,
      "brightness": 0.5,
      "guidance": 4,
      "temperature": 1
    }
  }
}
```

## Notes for agents

- Music jobs return a normal media job and also materialize into `state/media/outputs/`.
- The generated clip is about 30 seconds. Use `musicGenerationMode: "VOCALIZATION"` only when the user asks for sung elements; otherwise keep it instrumental.
- Do not use real artist names, song titles, or copyrighted material in the prompt.

## Endpoint

POST <stella-api>/api/media/v1/generate
Content-Type: application/json
Authorization: Bearer <stella-session-token>

Where `<stella-api>` is the Stella backend base URL the desktop app is signed
in against (e.g. `https://api.stella.sh`). Reuse the user's existing session
token — do not invent your own credentials.

## Request body

```json
{
  "capability": "<id>",          // required; see per-kind sections below
  "profile": "<id>",             // optional; defaults to the capability's preferred profile
  "prompt": "...",               // optional convenience field; mapped to the capability's prompt key
  "aspectRatio": "16:9",         // optional convenience field for image/video; mapped to aspect_ratio
  "sourceUrl": "https://...",    // optional; for capabilities that take a public URL
  "source": "data:image/png;base64,...", // optional; for local files (preferred)
  "sources": { "video": "data:...", "audio": "data:..." }, // for multi-input capabilities
  "input": { /* provider-specific overrides, merged on top of the convenience fields */ }
}
```

`source` accepts a `data:` URI string or `{ "base64": "...", "mimeType": "image/png" }`.
The backend wraps the value into the right shape for the picked endpoint
(e.g. `image_urls: ["data:..."]` for image edit).

## Response (202 Accepted)

```json
{
  "jobId": "job_123",
  "capability": "text_to_image",
  "profile": "best",
  "status": "queued",
  "upstreamStatus": "IN_QUEUE",
  "subscription": {
    "query": "api.media_jobs.getByJobId",
    "args": { "jobId": "job_123" }
  }
}
```

## Watching for completion

You almost never need to. The Stella desktop renderer subscribes to every
succeeded media job for the signed-in user, downloads the output to
`state/media/outputs/<jobId>_<i>.<ext>`, and pops it open in the Display
sidebar automatically. Just submit the job and report back to the user; the
asset will appear on their screen.

If you do need the raw status, subscribe to Convex:
`useQuery(api.media_jobs.getByJobId, { jobId })`. Status values:
`queued`, `in_progress`, `processing`, `succeeded`, `failed`,
`cancelled`.

## Auth failure (401)

If the user is not signed in, the endpoint returns a structured 401:

```json
{
  "error": "Sign in to Stella to use media generation.",
  "code": "auth_required",
  "action": "Ask the user to open the Stella desktop app and finish signing in (Settings → Account, or the welcome screen on first launch). Once they're signed in, retry the same request — no payload changes needed.",
  "docsUrl": "https://stella.sh/docs/media"
}
```

When you see `code: "auth_required"`:
1. Stop the in-flight job — do not retry on a backoff.
2. Surface `action` to the user verbatim so they know what to do.
3. Once they confirm sign-in, re-run the original request with the same payload.

The response also sets `WWW-Authenticate: Bearer realm="stella-media"` for
non-agent HTTP clients.

## Errors

All other errors return `{ "error": "human-readable message" }` with an
appropriate status. Upstream provider errors (content policy, validation,
rate limits) are parsed and forwarded as-is — show the message to the user.