@acedatacloud/skills 2026.614.0 → 2026.614.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@acedatacloud/skills",
|
|
3
|
-
"version": "2026.614.
|
|
3
|
+
"version": "2026.614.1",
|
|
4
4
|
"description": "Agent Skills for AceDataCloud AI services — music, image, video generation, LLM chat, web search. Compatible with Claude Code, GitHub Copilot, Gemini CLI, OpenAI Codex, and 30+ AI coding agents.",
|
|
5
5
|
"keywords": [
|
|
6
6
|
"agent-skills",
|
|
@@ -66,14 +66,27 @@ curl -sS -X POST https://api.acedata.cloud/seedance/videos \
|
|
|
66
66
|
curl -sS -X POST https://api.acedata.cloud/suno/audios \
|
|
67
67
|
-H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" -H "Content-Type: application/json" \
|
|
68
68
|
-d '{"action":"generate","prompt":"uplifting minimal electronic, premium tech","instrumental":true,"model":"chirp-v5-5"}'
|
|
69
|
+
|
|
70
|
+
# Voiceover — OpenAI-compatible TTS, SYNCHRONOUS (returns audio bytes, no polling).
|
|
71
|
+
# Generate ONE file per scene so the audio aligns to scene boundaries.
|
|
72
|
+
curl -sS -X POST https://api.acedata.cloud/v1/audio/speech \
|
|
73
|
+
-H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" -H "Content-Type: application/json" \
|
|
74
|
+
-o scene1.mp3 \
|
|
75
|
+
-d '{"model":"tts-1-hd","input":"<scene narration>","voice":"nova"}'
|
|
69
76
|
```
|
|
70
77
|
|
|
71
78
|
All of the above return a `task_id` — **poll the matching `/<service>/tasks`** until
|
|
72
79
|
`state`/`status` is terminal, then read the media URL (see _shared/async-tasks.md).
|
|
73
80
|
The media is served from `*.cdn.acedata.cloud`. Per-model details: `flux-image`,
|
|
74
81
|
`seedream-image`, `nano-banana-image`, `seedance-video`, `veo-video`, `suno-music`,
|
|
75
|
-
`fish-audio` skills.
|
|
76
|
-
|
|
82
|
+
`fish-audio` skills.
|
|
83
|
+
|
|
84
|
+
**Voiceover (TTS):** `POST /v1/audio/speech` is the OpenAI-compatible route — it is
|
|
85
|
+
**synchronous** (returns the audio bytes directly, no `task_id`/polling), models
|
|
86
|
+
`tts-1-hd` (default) / `tts-1`, voices `alloy|echo|fable|onyx|nova|shimmer`, and it
|
|
87
|
+
speaks both English and Chinese. (`/fish/tts` is an alternate voice-cloning route.)
|
|
88
|
+
The endpoint does **not** return word timings — run WhisperX on the returned audio
|
|
89
|
+
for karaoke, or distribute words across the scene duration proportionally.
|
|
77
90
|
|
|
78
91
|
## Recipe — capture product UI (Playwright)
|
|
79
92
|
|
|
@@ -126,8 +139,9 @@ real bold sans (`C:/Windows/Fonts/arialbd.ttf`, `DejaVuSans-Bold.ttf`, etc.),
|
|
|
126
139
|
so the product stays visible.
|
|
127
140
|
|
|
128
141
|
> Reference implementation (Scene-JSON contract, caption-burn, render driver,
|
|
129
|
-
> material-library convention): **AceDataCloud/PlatformStudio**
|
|
130
|
-
> `scripts/
|
|
142
|
+
> material-library convention): **AceDataCloud/PlatformStudio** — `app/contract.py`,
|
|
143
|
+
> `app/pipeline/`, `scripts/render_veo_rough_cut.py`, `scripts/build_material_catalog.py`,
|
|
144
|
+
> and the curated material index `materials/catalog.json` + `materials/curated.json`.
|
|
131
145
|
|
|
132
146
|
## Recipe — upload to CDN + distribute
|
|
133
147
|
|