@oiioii/cli 0.1.11 → 0.1.12

package/README.md

@@ -29,6 +29,7 @@ human-readable output and a stable JSON envelope for AI agents and automation.
 | `video image` | Image-to-video generation | Implemented |
 | `video generate` | Model-validated mixed image/video/audio reference generation | Implemented |
 | `audio generate` | Seed Audio and Suno audio/music generation | Implemented |
+| `story create/list/status/cancel` | Submit and manage no-interaction Story workflow tasks | Implemented |
 | `upload resource` | Upload image/video/audio resources without a workspace | Implemented |
 | `upload file` | Upload image/video/audio and attach it to a workspace | Implemented |
 | `record get/open` | Query generation metadata and download resources | Implemented |
@@ -44,6 +45,7 @@ Important current limitations:
 - Generation submits `POST /v1/media/generations` by default and returns immediately with the authoritative backend `task_id` plus a `local_task_id`.
 - The backend task ID, workspace, media type, asset ID, progress, and terminal outputs are cached in the owner-only local task store.
 - `task status/wait` query the stored task transport for non-terminal cached tasks and accept either the backend or local task ID.
+- Story tasks can be listed, queried, and cancelled without a local task-cache entry.
 - If submission times out or disconnects before the backend task ID is received, the task remains `submitting`; `task retry <local_task_id>` resends the saved request with the original idempotency key.
 - REST metadata requests time out after 30 seconds; raw resource uploads/downloads use a 5-minute transfer timeout, and VOD transcode polling has a 10-minute overall deadline.
 - Image, video, and audio generation create local preview bundles after a queried task reaches a terminal state.
@@ -631,6 +633,17 @@ oiioii audio generate --prompt "cinematic orchestral background music" --model s
 oiioii audio generate --prompt "custom lyrics" --model suno --custom --tags "dream pop, female vocal" --json
 ```
 
+ElevenLabs v4 supports direct speech synthesis plus optional official voice,
+stability, language, accent, and emotion controls:
+
+```bash
+oiioii audio elevenlabs \
+  --prompt "你好，这是 ElevenLabs V4。" \
+  --speaker-id <voice-id> \
+  --stability 0.5 \
+  --json
+```
+
 Current behavior:
 
 - Accepts `--model-id <id>` from `inspect models`, or an exact
@@ -645,6 +658,63 @@ Current behavior:
 Generation consumes real credits. Do not run image/video/audio generation in
 unbounded automated loops, and do not retry failures blindly.
 
+## Story Generation
+
+`story create` submits the no-interaction Story OpenAPI workflow. It creates a
+new workspace named by `--task-name`; provide exactly one script source and a
+style URI:
+
+```bash
+oiioii story create \
+  --task-name "CLI Story" \
+  --script-file ./story.txt \
+  --style hogi://style/1844 \
+  --wait \
+  --json
+```
+
+Without `--wait`, the response returns the authoritative backend `taskId` and
+workspace ID. Query it directly without relying on local task history:
+
+```bash
+oiioii story status <task_id> --json
+oiioii story list --status processing --limit 20 --json
+oiioii story cancel <task_id> --json
+```
+
+`story list` returns cursor pagination for Story OpenAPI root tasks only. Cancel
+is idempotent for an already-cancelled task; completed and failed tasks return
+`TASK_NOT_CANCELLABLE`. Existing workspace assets are retained, and media work
+already submitted to a provider may finish in the background.
+
+Use `--script-uri hogi://document/...` instead of `--script-file` for an
+already uploaded document. `--idempotency-key` supports safe replay after an
+ambiguous submission; reuse the same key and identical request options.
+
+## Quick Media Workflows
+
+`media` is a production command for invoking the headless Quick Media Agent
+actions. It creates one root asynchronous task and can optionally wait for the
+terminal result and download the generated resources:
+
+```bash
+oiioii media create \
+  --workspace-id <workspace-id> \
+  --type video \
+  --prompt "Animate the clouds" \
+  --model-id 90 \
+  --hogi-uri hogi://image/<id> \
+  --wait \
+  --download-dir ./outputs \
+  --json
+
+oiioii media status <task-id> --json
+```
+
+Use `--model-id` or `--model [--variant]` for catalog-backed selection. The
+advanced `--tool` and `--model-version` options bypass or override catalog
+selection and should use values returned by `inspect models`.
+
 ## Async Generation and Workspace Assets
 
 Image, video, and audio commands submit through OpenAPI by default: