@remixmate/cli 0.9.25 → 0.9.26

package/README.md

@@ -268,6 +268,10 @@ npm run regress:update
 # Run only the render-plan snapshot layer:
 npm run test:render-plan
 
+# Narration speed wiring (gen_script → render plan → gen-voice --speed).
+# Fully offline: no registry, no TTS call.
+npm run test:narration-speed
+
 # L3 — selective, real Remotion render of chosen template(s). NOT full-library
 # by design (rendering is slow + needs asset generation). Catches crashes /
 # black frames the static layers can't. Needs PRIV_TOKEN for narration TTS;

package/dist/manifest.json

@@ -1,7 +1,7 @@
 {
   "schemaVersion": 1,
-  "version": "0.9.25",
-  "generatedAt": "2026-09-08T15:32:17.519Z",
+  "version": "0.9.26",
+  "generatedAt": "2026-09-13T00:51:13.551Z",
   "skills": [
     {
       "id": "export-jianying",
@@ -382,6 +382,10 @@
             "type": "string",
             "description": "Narration voice id. Default depends on the bound template's outputLanguage; query gen_voice with list_voices=true to see available ids."
           },
+          "speed": {
+            "type": "number",
+            "description": "Narration speech rate, 0.5-2.0 (default 1.0). Stored at global.narration.speed and applied when prepare_video_assets synthesizes the voice-over. **Must** pass when the user picked a speech rate — a template's 语速 / speed parameter arrives as a multiplier like 1.1, and without this flag it is silently dropped and the narration comes back at 1.0. Above ~1.3 subtitle alignment drifts and the delivery sounds mechanical; suggest shortening the script instead of raising it further."
+          },
           "template_id": {
             "type": "string",
             "description": "Template id (e.g. html-slide). The template owns outputLanguage and may also declare a defaultVoiceId; both flow into the produced DSL."
@@ -444,6 +448,7 @@
           "ratio",
           "scenes",
           "voice_id",
+          "speed",
           "template_id",
           "headline",
           "subheadline",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@remixmate/cli",
-  "version": "0.9.25",
+  "version": "0.9.26",
   "description": "AI media generation skills for Claude Code / Codex — 12 skills covering image, video, voice, digital human, web screenshot, web recording, script, template registry, rendering, Jianying export, and video deconstruction.",
   "type": "module",
   "main": "dist/index.js",
@@ -23,6 +23,7 @@
     "test:validators": "PYTHONDONTWRITEBYTECODE=1 python3 scripts/test-validators.py",
     "test:template-pipeline": "PYTHONDONTWRITEBYTECODE=1 node dist/cli.js exec -- python3 scripts/test-template-pipeline.py",
     "test:props-contract": "PYTHONDONTWRITEBYTECODE=1 python3 scripts/test-props-contract.py",
+    "test:narration-speed": "PYTHONDONTWRITEBYTECODE=1 python3 scripts/test-narration-speed.py",
     "test:render-plan": "PYTHONDONTWRITEBYTECODE=1 python3 scripts/test-render-plan-snapshot.py",
     "test:render-plan:update": "PYTHONDONTWRITEBYTECODE=1 python3 scripts/test-render-plan-snapshot.py --update",
     "test:contracts": "PYTHONDONTWRITEBYTECODE=1 python3 skills/template-registry/scripts/check_contracts.py",

package/skills/gen-script/SKILL.md

@@ -401,6 +401,7 @@ python3 <SkillDir>/scripts/gen_script.py \
 | `--ratio` | Aspect ratio. | `16:9` |
 | `--scenes` | Scene count. | auto-planned |
 | `--voice-id` | Narration voice id. | resolved from template + language fallback |
+| `--speed` | Narration speech rate (0.5–2.0), written to `global.narration.speed` and applied when `prepare_video_assets` calls gen-voice. Pass it whenever the user picked a speed (the replicate form's 语速 field sends one). Above ~1.3 subtitle alignment drifts and the delivery turns mechanical — shorten the script instead. | `1.0` |
 | `--allow-digital-human` | Whether to allow digital-human assets. | off |
 | `--allow-ai-video` | Whether to allow AI-generated video assets. | off |
 | `--validate` | Validate-only mode: only validate the input DSL. | — |

package/skills/gen-script/scripts/gen_script.py

@@ -80,6 +80,24 @@ FALLBACK_VOICE = {
     "en": "english-male-friendly-01",
 }
 
+# ── Narration speed ───────────────────────────────────────────────────────────
+# Written to global.narration.speed; render_video copies it down into the
+# gen-voice asset payload (same route as narration text) and passes it to
+# `gen-voice --speed`. The envelope mirrors gen-voice's own 0.5–2.0 contract;
+# the real per-voice limits (capabilities speedMin/speedMax) are only known at
+# synthesis time, which is several confirmation steps and a few paid image
+# generations later — so an obviously-out-of-range value fails here instead.
+DEFAULT_NARRATION_SPEED = 1.0
+SPEED_MIN = 0.5
+SPEED_MAX = 2.0
+
+
+def _resolve_narration_speed(speed):
+    """CLI speed → the value written to global.narration.speed. Total function."""
+    if speed is None:
+        return DEFAULT_NARRATION_SPEED
+    return float(speed)
+
 
 def _resolve_template_language_meta(template_config):
     """Tolerant reader for outputLanguage / defaultVoiceId on a template dict.
@@ -750,6 +768,7 @@ def _build_carousel_caption_dsl(
     resolution: str,
     output_language: str,
     resolved_voice_id: str,
+    narration_speed: float,
     font_id: str | None,
     font_name: str | None,
     narration_enabled: bool,
@@ -907,7 +926,7 @@ def _build_carousel_caption_dsl(
             # 无配音模板：关闭 CC 字幕（字幕段是 narration→TTS 的派生物），
             # 并省略 global.narration，避免下游误判存在旁白。
             "subtitle": {"enabled": narration_enabled, "style": "bottom"},
-            **({"narration": {"voiceId": resolved_voice_id, "speed": 1.0}} if narration_enabled else {}),
+            **({"narration": {"voiceId": resolved_voice_id, "speed": narration_speed}} if narration_enabled else {}),
             **({"font": {"fontId": font_id, **({"fontName": font_name} if font_name else {})}} if font_id else {}),
             "bgm": {"enabled": True, "volume": 0.12},
         },
@@ -961,6 +980,7 @@ def build_dsl(
         scene_count: int | None,
         allow_digital_human: bool,
         allow_ai_video: bool,
+        speed: float | None = None,
         template_id: str | None = None,
         stub_image_url: str = "",
         stub_video_url: str = "",
@@ -992,6 +1012,10 @@ def build_dsl(
     图给第 i 个场景，没被占到的场景照常走 gen-image 补图。这条规则不是随便定的——
     见 docs/asset-annotation-design.md §6：另外两种立场（模型自由挑选 / 严格一一对应）
     都会让"只传两张图"要么失去可预期性，要么直接跑不通。
+
+    speed 是旁白语速倍率，落在 global.narration.speed（不给 = 1.0）。它**不写进
+    gen-voice 资产的 payload**——与旁白文本同一条规矩：唯一来源在 DSL 上，
+    render_video 在调 TTS 前按 assetRef 回查注入，免得两处存一个值各自漂移。
     """
     # Load template config（registry 单一数据源）→ 归一化 contract
     template_config = _load_template_config(template_id) if template_id else None
@@ -1010,6 +1034,7 @@ def build_dsl(
     # values fall back to "zh" so old templates keep their current behavior.
     output_language, template_default_voice_id = _resolve_template_language_meta(template_config)
     resolved_voice_id = _resolve_voice_id(voice_id, template_default_voice_id, output_language)
+    narration_speed = _resolve_narration_speed(speed)
     if resolved_voice_id != voice_id:
         print(
             f"ℹ️  voice resolution: cli={voice_id!r} → resolved={resolved_voice_id!r} "
@@ -1087,6 +1112,7 @@ def build_dsl(
             resolution=resolution,
             output_language=output_language,
             resolved_voice_id=resolved_voice_id,
+            narration_speed=narration_speed,
             font_id=font_id,
             font_name=font_name,
             narration_enabled=needs_narration,
@@ -1377,7 +1403,7 @@ def build_dsl(
             # 无配音模板：关闭 CC 字幕（字幕段是 narration→TTS 的派生物），并省略
             # global.narration，避免下游误判存在旁白。
             "subtitle": {"enabled": needs_narration, "style": "bottom"},
-            **({"narration": {"voiceId": resolved_voice_id, "speed": 1.0}} if needs_narration else {}),
+            **({"narration": {"voiceId": resolved_voice_id, "speed": narration_speed}} if needs_narration else {}),
             **({"font": {"fontId": font_id, **({"fontName": font_name} if font_name else {})}} if font_id else {}),
             "bgm": {"enabled": True, "volume": 0.12},
         },
@@ -1417,6 +1443,17 @@ Examples:
     parser.add_argument("--resolution", default="1080p", help="Resolution (default: 1080p)")
     parser.add_argument("--scenes", type=int, default=None, help="Scene count (default: auto-planned)")
     parser.add_argument("--voice-id", default=None, help="Narration voice id. When omitted, the resolver picks template.defaultVoiceId, then the language-keyed fallback (zh→Chinese (Mandarin)_Male_Announcer, en→TBD English voice). gen_voice --list-voices --local prints the language-tagged catalog.")
+    parser.add_argument(
+        "--speed",
+        type=float,
+        default=None,
+        help=(
+            f"Narration speech rate ({SPEED_MIN}-{SPEED_MAX}, default {DEFAULT_NARRATION_SPEED}). "
+            "Stored at global.narration.speed and applied by render_video when it calls gen-voice. "
+            "Above ~1.3 subtitle alignment starts to drift and the delivery turns mechanical — "
+            "shorten the script instead."
+        ),
+    )
     parser.add_argument(
         "--font-id",
         default=None,
@@ -1521,6 +1558,15 @@ Examples:
         parser.print_help()
         sys.exit(1)
 
+    if args.speed is not None and not (SPEED_MIN <= args.speed <= SPEED_MAX):
+        print(
+            f"❌ --speed must be in the range {SPEED_MIN}~{SPEED_MAX} (got {args.speed}).\n"
+            "   Speech rate is a multiplier, not a percentage: 1.0 is the voice's own pace, "
+            "1.1 is slightly brisker.",
+            file=sys.stderr,
+        )
+        sys.exit(1)
+
     # ── 模板感知的 ratio 自动推导 ────────────────────────────────────────────
     # 用户没显式传 --ratio 时：
     #   1. 若指定了 --template-id，取模板 supportedAspectRatios[0]（避免横竖屏不匹配）
@@ -1552,6 +1598,8 @@ Examples:
     print(f"   platform: {args.platform}", file=sys.stderr)
     print(f"   duration: {args.duration}s", file=sys.stderr)
     print(f"   ratio: {args.ratio}", file=sys.stderr)
+    if args.speed is not None:
+        print(f"   narration speed: {args.speed}x", file=sys.stderr)
 
     # CLI flag takes precedence; env vars act as fallback with a visible warning
     # so silent cross-session leakage is always observable.
@@ -1592,6 +1640,7 @@ Examples:
         ratio=args.ratio,
         resolution=args.resolution,
         voice_id=args.voice_id,
+        speed=args.speed,
         font_id=args.font_id,
         font_name=args.font_name,
         scene_count=args.scenes,

package/skills/gen-script/skill.json

@@ -52,6 +52,10 @@
         "type": "string",
         "description": "Narration voice id. Default depends on the bound template's outputLanguage; query gen_voice with list_voices=true to see available ids."
       },
+      "speed": {
+        "type": "number",
+        "description": "Narration speech rate, 0.5-2.0 (default 1.0). Stored at global.narration.speed and applied when prepare_video_assets synthesizes the voice-over. **Must** pass when the user picked a speech rate — a template's 语速 / speed parameter arrives as a multiplier like 1.1, and without this flag it is silently dropped and the narration comes back at 1.0. Above ~1.3 subtitle alignment drifts and the delivery sounds mechanical; suggest shortening the script instead of raising it further."
+      },
       "template_id": {
         "type": "string",
         "description": "Template id (e.g. html-slide). The template owns outputLanguage and may also declare a defaultVoiceId; both flow into the produced DSL."
@@ -114,6 +118,7 @@
       "ratio",
       "scenes",
       "voice_id",
+      "speed",
       "template_id",
       "headline",
       "subheadline",

package/skills/gen-script/version.json

@@ -2,6 +2,6 @@
   "skillName": "gen-script",
   "repoName": "agent-skill-media-maker",
   "skillId": "474",
-  "version": "V11",
+  "version": "V12",
   "skillDescription": "Video-script generation skill. Turns a user-supplied topic into a structured Video DSL (JSON) that describes the full video — scene structure, asset requirements, and narrative flow.\n\nUse this skill as soon as the user mentions any of these intents:\n- Write a video script, generate a video script, plan a video, write storyboards\n- Create a short video, plan video content, generate a Video DSL\n- Turn a topic into a video structure / video content plan\n\nEven when the user does not say \"generate the DSL\", use this skill whenever they want to turn a topic into a structured video plan.\n\n⚠️ Stop-and-confirm gate: after this skill returns a DSL, show the full script and wait for the user's explicit confirmation. Never call `prepare_video_assets` in the same turn."
 }

package/skills/render-video/scripts/render_video.py

@@ -159,6 +159,22 @@ RESOLUTION_MAP = {
 }
 
 
+def _narration_speed(narration: dict) -> Optional[float]:
+    """Read a narration block's speech-rate multiplier, or None when unset.
+
+    Tolerant on purpose: the DSL is hand-editable, and a malformed speed must
+    not take down a render that would otherwise be fine — it falls back to the
+    voice's own pace. 0 and negatives are treated as unset for the same reason
+    ab-api does (`speed: 0` there means "follow the global setting").
+    """
+    if not isinstance(narration, dict):
+        return None
+    raw = narration.get("speed")
+    if isinstance(raw, bool) or not isinstance(raw, (int, float)):
+        return None
+    return float(raw) if raw > 0 else None
+
+
 def extract_narration_lines(narration: dict) -> Optional[tuple[list[str], int, list[Optional[float]]]]:
     """If narration uses the structured {intro, items, outro} form, return
     (lines, intro_line_count, at_sec_list). `at_sec_list` is parallel to
@@ -621,6 +637,8 @@ def build_render_plan(dsl: dict, binding: dict) -> dict:
     # so adjust_timeline_to_audio can later auto-derive highlightMap from
     # per-line TTS timestamps.
     dsl_assets_by_id = {a["assetId"]: a for a in dsl.get("assets", [])}
+    global_narration = (dsl.get("global") or {}).get("narration") or {}
+    global_speed = _narration_speed(global_narration)
     for scene in dsl.get("scenes", []):
         narration = (scene.get("audio") or {}).get("narration") or {}
         ref = narration.get("assetRef")
@@ -628,6 +646,15 @@ def build_render_plan(dsl: dict, binding: dict) -> dict:
         if not asset:
             continue
         payload = asset.setdefault("payload", {})
+        # Speech rate follows the same route as the narration text: single source
+        # of truth on the DSL, copied down here because resolve_asset_audio only
+        # ever sees the asset. Scene-level overrides global (mirrors the narration
+        # editor's "行级覆盖 > 全局"); neither set = gen-voice's own 1.0 default.
+        speed = _narration_speed(narration)
+        if speed is None:
+            speed = global_speed
+        if speed is not None:
+            payload["speed"] = speed
         extracted = extract_narration_lines(narration)
         if extracted:
             lines, intro_lines, _ = extracted
@@ -862,6 +889,11 @@ def resolve_asset_audio(asset: dict, private_token: str, timeout: int) -> dict:
     cmd.extend(["--text", tts_text, "--json-output"])
     if payload.get("voiceId"):
         cmd.extend(["--voice-id", payload["voiceId"]])
+    # Injected by build_render_plan from the DSL (scene narration > global).
+    # Absent = let gen-voice apply its own default rather than pinning 1.0 here.
+    speed = _narration_speed(payload)
+    if speed is not None:
+        cmd.extend(["--speed", str(speed)])
     if private_token:
         cmd.extend(["--priv-token", private_token])
 

package/skills/render-video/version.json

@@ -2,6 +2,6 @@
   "skillName": "render-video",
   "repoName": "agent-skill-media-maker",
   "skillId": "473",
-  "version": "V19",
+  "version": "V20",
   "skillDescription": "Final-render skill: loads a persisted RenderPlan by `job_id` and drives the Remotion engine to produce the final video.\n\nUse this skill as soon as the user mentions any of these intents (after assets are already prepared):\n- Render the video, composite the video, export the video\n- Turn the prepared assets into the final clip\n- Render with Remotion\n\nPrerequisite: assets must already be generated via `prepare_video_assets`. This skill never resolves or regenerates assets — pass it a `job_id` from a previous `prepare_video_assets` call.\n\n⚠️ Stop-and-confirm gate: never call this skill until the user has explicitly confirmed the assets prepared by `prepare_video_assets`. If those assets were prepared in the current turn and the user has not replied since, stop and ask instead of rendering."
 }