| 1 | --- |
| 2 | description: Shared post-processing stage for narration audio, PPTX embedding, and optional native video export. |
| 3 | --- |
| 4 | |
| 5 | # Generate Audio Stage |
| 6 | |
| 7 | > Shared narration stage. Run from the Generate PPTX route after notes/export readiness, or from the Enhance Native PPTX narration module after its notes step. By default, `edge-tts` produces one audio/SRT pair per slide from the same streaming request. Cloud TTS providers (`elevenlabs` / `minimax` / `qwen` / `cosyvoice`) currently produce audio only. The caller owns final PPTX integration. |
| 8 | |
| 9 | This stage is **context-independent**: it reads `notes/*.md` and queries the selected TTS voice catalog, so either owning route may invoke it in a fresh session. It does not choose the top-level route and does not patch slide design. |
| 10 | |
| 11 | **Trigger**: In Generate PPTX, run when the effective `Narration Audio` outcome |
| 12 | in `design_spec.md` §I is `enabled`; a later explicit request first updates that |
| 13 | outcome and its provenance. Quick Generate instead runs when the request or |
| 14 | current agent's active-context decision selects narration. In Enhance Native |
| 15 | PPTX, run when its confirmed enhancement plan has `audio.enabled: true`. |
| 16 | |
| 17 | **Hard dependency — speaker notes**: Audio requires complete per-slide speaker |
| 18 | notes. Generate PPTX additionally requires its effective `Speaker Notes` |
| 19 | outcome to be enabled; Enhance Native PPTX follows its confirmed notes/audio |
| 20 | plan, where enabling audio also enables notes. Quick records the same dependency |
| 21 | in active context. Do not enter audio generation while the owning route's notes |
| 22 | are missing or incomplete; generate and validate those notes first, then resume |
| 23 | this stage. |
| 24 | |
| 25 | ## When to Run |
| 26 | |
| 27 | - Per-page narration files exist at `notes/*.md`. In Generate PPTX, split `notes/total.md` during Step 7.1. In Enhance Native PPTX, the notes module writes numeric files such as `001.md`. |
| 28 | - Default mode: `edge-tts` is installed (`python3 -m pip install edge-tts`). |
| 29 | - The stage is page-level only: with edge, one notes file becomes `audio/<stem>.mp3` plus `notes/subtitles/<stem>.srt`; with a cloud provider, it becomes one audio file. Do not use a single long audio track or attempt automatic long-audio splitting. |
| 30 | - PPT narration assets must be PowerPoint-reliable audio: `m4a` (AAC), `mp3`, or `wav`. The built-in TTS path defaults to `mp3`; provider formats such as `pcm`, `opus`, or `flac` must be transcoded before embedding. |
| 31 | - PowerPoint recorded narration export requires `ffprobe` so slide timings can be written from actual audio duration. |
| 32 | - Optional automatic video export requires Windows PowerPoint 2016+ and runs |
| 33 | through `powerpoint_video.py`; the command waits for PowerPoint's native |
| 34 | encoder to finish before returning. |
| 35 | - macOS PowerPoint may export MP4/MOV manually, but it has no equivalent |
| 36 | `CreateVideo` automation contract and its movie export does not preserve |
| 37 | animation effects. Do not replace the missing API with UI scripting. |
| 38 | - Optional post-export video calibration requires `ffmpeg` plus `numpy`; it runs only after a finished PowerPoint video is supplied or created. |
| 39 | - High-quality cloud mode: provider API key is set before use: |
| 40 | - ElevenLabs: `ELEVENLABS_API_KEY` |
| 41 | - MiniMax: `MINIMAX_API_KEY` |
| 42 | - Qwen: `QWEN_API_KEY` or `DASHSCOPE_API_KEY` |
| 43 | - CosyVoice: `COSYVOICE_API_KEY` or `DASHSCOPE_API_KEY` |
| 44 | - Keys may live in the current process environment or the first `.env` found in this order: current working directory, skill directory (e.g. `~/.agents/skills/ppt-master/.env`), clone repo root, `~/.ppt-master/.env` |
| 45 | - The deck is in a single dominant language (mixed-language decks: pick the dominant one — the AI uses judgment, not a heuristic). |
| 46 | |
| 47 | If per-slide notes are missing, recover through the owning route. Generate |
| 48 | PPTX returns to its enabled notes branch and then runs |
| 49 | `total_md_split.py <project_path>`; Enhance Native PPTX returns to |
| 50 | `native-enhance-pptx` Step 6 and writes numeric notes directly. Never run the |
| 51 | Generate splitter against a Native Enhance project. |
| 52 | |
| 53 | --- |
| 54 | |
| 55 | ## Step 1: Determine the deck's language |
| 56 | |
| 57 | The AI already knows the deck's language from writing the notes. No detection script needed. |
| 58 | |
| 59 | - Identify the primary language from the notes content: `zh` / `en` / `ja` / `ko` / etc. |
| 60 | - For mixed-language decks (e.g. Chinese with English technical terms), pick the language the audience will hear most of. |
| 61 | - For Chinese specifically: pick the locale based on context — `zh-CN` (mainland mandarin, default), `zh-TW` (Taiwanese mandarin), or `zh-HK` (Cantonese). Default Generate may ask when context is unclear; Quick chooses the best supported default and continues. |
| 62 | |
| 63 | --- |
| 64 | |
| 65 | ## Step 2: Choose audio backend and pull the voice catalog |
| 66 | |
| 67 | Default to **edge** unless the user explicitly asks for a cloud provider / higher-quality cloud narration / a cloned voice. |
| 68 | |
| 69 | **edge backend**: |
| 70 | |
| 71 | ```bash |
| 72 | python3 skills/ppt-master/scripts/notes_to_audio.py --list-voices --locale <locale> |
| 73 | ``` |
| 74 | |
| 75 | **ElevenLabs backend**: |
| 76 | |
| 77 | ```bash |
| 78 | python3 skills/ppt-master/scripts/notes_to_audio.py --provider elevenlabs --list-voices |
| 79 | ``` |
| 80 | |
| 81 | **Cloud providers using explicit voice IDs/names**: |
| 82 | |
| 83 | ```bash |
| 84 | python3 skills/ppt-master/scripts/notes_to_audio.py --provider minimax --list-voices |
| 85 | python3 skills/ppt-master/scripts/notes_to_audio.py --provider qwen --list-voices |
| 86 | python3 skills/ppt-master/scripts/notes_to_audio.py --provider cosyvoice --list-voices |
| 87 | ``` |
| 88 | |
| 89 | The output is a flat list of all available voices for the selected provider. From this list, the AI picks **3–6 candidates** to recommend, applying these rules: |
| 90 | |
| 91 | - **Cover both genders** when both exist for the locale. |
| 92 | - **For edge**: prefer `COMMON_VOICES`-listed voices (curated set inside `notes_to_audio.py`) when the locale has them — they are battle-tested. |
| 93 | - **For ElevenLabs**: prefer voices already present in the user's account; if the user provides a specific `voice_id`, do not override it. |
| 94 | - **For MiniMax / Qwen / CosyVoice**: if the user provides a cloned `voice_id`, use it directly. Do not attempt voice cloning inside this narration stage. |
| 95 | - **Match the deck's tone** — pick the strongest recommendation based on style: |
| 96 | - Consultant / data-driven / 财报 → 稳重男声（如 `zh-CN-YunjianNeural`）or 清晰女声（如 `zh-CN-XiaoxiaoNeural`） |
| 97 | - General / 教学 / 产品介绍 → 明亮女声 / 年轻男声（如 `zh-CN-XiaoyiNeural` / `zh-CN-YunxiNeural`） |
| 98 | - 发布会 / 播报 → 播报感男声（如 `zh-CN-YunyangNeural`） |
| 99 | - English consultant deck → `en-US-GuyNeural` (steady) or `en-US-JennyNeural` (clear) |
| 100 | - Japanese / Korean → pick from `ja-JP-*` / `ko-KR-*` neural voices, mark gender + tone |
| 101 | |
| 102 | For each candidate, write a **one-line Chinese description** covering: 性别 · 调性 · 适用场景。For cloud providers, include the voice name/ID exactly as it must be passed to `--voice-id`. |
| 103 | |
| 104 | --- |
| 105 | |
| 106 | ## Step 3: One-shot user interaction (mandatory) |
| 107 | |
| 108 | Send a single message to the user that resolves all five configuration decisions at once and provides a recommended value for each. Before offering automatic video export, run `python3 skills/ppt-master/scripts/powerpoint_video.py --check`; do not present an unavailable local capability as executable. Do NOT split into multiple rounds. |
| 109 | |
| 110 | **Cloned-voice fast path**: if the user mentioned a cloned voice / 克隆音色 / 复刻音色 / "my own voice" along with a `voice_id`, skip the voice-recommendation list — set the provider to whichever the user named (`elevenlabs` / `minimax` / `qwen` / `cosyvoice`), pin the `voice_id` they gave you, and only confirm rate + embed + video. |
| 111 | |
| 112 | **Message template** (Chinese; translate to user's chat language if different). “Embed” means caller-specific integration: SVG re-export for Generate PPTX, or native OOXML application for Enhance Native PPTX. |
| 113 | |
| 114 | > 检测到 notes 主语言为 **<语言>**（locale: `<locale>`）。基于 deck 调性（<风格>），我推荐以下配置： |
| 115 | > |
| 116 | > **生成模式**：⭐ 推荐 `<edge|elevenlabs|minimax|qwen|cosyvoice>`（理由：<一句话，如"无需配置，稳定生成"或"用户要求高质量云端音色">）。 |
| 117 | > |
| 118 | > **音色**： |
| 119 | > - **[1] <ShortName>** — <性别·调性·适用场景> ⭐ **推荐** |
| 120 | > - [2] <ShortName> — <性别·调性·适用场景> |
| 121 | > - [3] <ShortName> — <性别·调性·适用场景> |
| 122 | > - [4] <ShortName> — <性别·调性·适用场景> |
| 123 | > - [5] <ShortName> — <性别·调性·适用场景> |
| 124 | > - 也可直接输入清单中的其他 ShortName。 |
| 125 | > |
| 126 | > **语速/风格参数**：⭐ 推荐 `<rate or provider defaults>`（理由：<一句话，如"页均 2–3 句，正常语速听感最稳"或"ElevenLabs 默认 voice settings 保留音色原始表现最稳">）。 |
| 127 | > |
| 128 | > **生成完是否重新导出嵌入音频的 PPTX**：⭐ 推荐 **是**（一次到位，自动按音频时长设页面停留）。 |
| 129 | > |
| 130 | > **带音频 PPTX 完成后是否继续导出视频**：⭐ 推荐 **是**（仅在本机 Windows PowerPoint 2016+ 可用时；将等待原生视频导出完成）。 |
| 131 | > |
| 132 | > 直接回"好"用全部推荐值，或告诉我想改的部分（如"音色 2，语速 -5%"或"用 MiniMax 的 voice_id xxx"）。 |
| 133 | |
| 134 | **Recommended-value rules**: |
| 135 | - 生成模式：默认 `edge`；当用户明确追求高质量云端音色或提供 cloud voice ID 时，按用户指定选 `elevenlabs` / `minimax` / `qwen` / `cosyvoice`。 |
| 136 | - 音色：从 Step 2 候选里挑最贴合 deck 调性的那一个。 |
| 137 | - 语速：edge 默认 `+0%`；notes 字数密集（页均 >4 句长句）建议 `-5%`；notes 简短紧凑建议 `+5%`；超出此范围需说明理由。Cloud providers 默认用 provider defaults，除非用户明确要调速或改风格。 |
| 138 | - 嵌入：默认推荐"是"；除非用户已有定制 PPTX 不希望覆盖。 |
| 139 | - 视频：`powerpoint_video.py --check` 成功时默认推荐"是"；不可用时说明只能交付带音频 PPTX，不自动改用第三方渲染器。 |
| 140 | |
| 141 | --- |
| 142 | |
| 143 | ## Step 4: Execute (no further interaction) |
| 144 | |
| 145 | **Blocking notes preflight**: `notes_to_audio.py` resolves the complete notes |
| 146 | roster from `svg_output/*.svg` on Generate projects or |
| 147 | `analysis/slide_index.json` on Native Enhance projects. Before any TTS request, |
| 148 | every expected note must exist, be readable, and contain spoken text. Exit code |
| 149 | `2` returns the caller to its notes-generation step; never continue with partial |
| 150 | audio generation. |
| 151 | |
| 152 | Run sequentially — do NOT bundle: |
| 153 | |
| 154 | ```bash |
| 155 | # 1A. Generate audio with edge (default) |
| 156 | python3 skills/ppt-master/scripts/notes_to_audio.py <project_path> \ |
| 157 | --voice <chosen-ShortName> --rate <chosen-rate> |
| 158 | |
| 159 | # 1B. Or generate audio with ElevenLabs |
| 160 | python3 skills/ppt-master/scripts/notes_to_audio.py <project_path> \ |
| 161 | --provider elevenlabs --voice-id <chosen-voice-id> \ |
| 162 | --elevenlabs-model eleven_multilingual_v2 |
| 163 | |
| 164 | # 1C. Or generate audio with MiniMax |
| 165 | # Defaults to the China endpoint; set MINIMAX_TTS_BASE_URL=https://api.minimax.io/v1/t2a_v2 for overseas access. |
| 166 | python3 skills/ppt-master/scripts/notes_to_audio.py <project_path> \ |
| 167 | --provider minimax --voice-id <chosen-voice-id> \ |
| 168 | --minimax-model speech-2.8-hd |
| 169 | |
| 170 | # 1D. Or generate audio with Qwen TTS |
| 171 | python3 skills/ppt-master/scripts/notes_to_audio.py <project_path> \ |
| 172 | --provider qwen --voice-id <chosen-voice> \ |
| 173 | --qwen-model qwen3-tts-flash --qwen-language-type Chinese |
| 174 | |
| 175 | # 1E. Or generate audio with CosyVoice |
| 176 | python3 skills/ppt-master/scripts/notes_to_audio.py <project_path> \ |
| 177 | --provider cosyvoice --voice-id <chosen-voice> \ |
| 178 | --cosyvoice-model cosyvoice-v3-flash |
| 179 | |
| 180 | # 2A. When animations.json is active, author or refresh narration_timing.json |
| 181 | # by matching SVG group semantics to SRT topics, then derive the narrated |
| 182 | # sidecar. Reuse current SVG semantics when complete; otherwise read only |
| 183 | # the missing or stale svg_output pages. |
| 184 | python3 skills/ppt-master/scripts/narration_sync.py animations <project_path> \ |
| 185 | --narration-padding 0.5 --force |
| 186 | |
| 187 | # 2B. Re-export with audio embedded |
| 188 | # Use the base export's [REPORT] path to preserve source-bound deck motion. |
| 189 | python3 skills/ppt-master/scripts/svg_to_pptx.py <project_path> \ |
| 190 | --recorded-narration audio --narration-padding 0.5 \ |
| 191 | --inherit-motion-from "<base_postflight_report>" |
| 192 | |
| 193 | # Optional: use the canonical presentation animation instead |
| 194 | python3 skills/ppt-master/scripts/svg_to_pptx.py <project_path> \ |
| 195 | --recorded-narration audio --narration-padding 0.5 \ |
| 196 | --animation-config animations.json \ |
| 197 | --inherit-motion-from "<base_postflight_report>" |
| 198 | |
| 199 | # Optional: export narration with no object or page-transition animation |
| 200 | python3 skills/ppt-master/scripts/svg_to_pptx.py <project_path> \ |
| 201 | --recorded-narration audio --narration-padding 0.5 \ |
| 202 | --no-animations |
| 203 | |
| 204 | # 2C. Merge page-local SRT against timing values read from the final PPTX |
| 205 | python3 skills/ppt-master/scripts/narration_sync.py subtitles <project_path> \ |
| 206 | --pptx <final_narrated_pptx> --force |
| 207 | |
| 208 | # 2D. Optional: export through installed Windows PowerPoint and wait for completion |
| 209 | python3 skills/ppt-master/scripts/powerpoint_video.py \ |
| 210 | <final_narrated_pptx> -o <final_video.mp4> |
| 211 | |
| 212 | # 2E. Align the frozen narration text against the finished video's audio track |
| 213 | python3 skills/ppt-master/scripts/video_subtitles.py <project_path> \ |
| 214 | --video <final_video.mp4> --language <language> --force |
| 215 | ``` |
| 216 | |
| 217 | **Default — bounded Edge concurrency (may override)**: Generate up to three |
| 218 | slide-level audio/SRT pairs concurrently. Use `--concurrency <N>` to tune the |
| 219 | Edge path or `--concurrency 1` for serial troubleshooting. Cloud providers |
| 220 | remain serial. |
| 221 | |
| 222 | If `notes_to_audio.py` errors with a missing dependency or missing provider API key, fix the prerequisite and re-run — do NOT swallow the error. |
| 223 | |
| 224 | The edge command writes each MP3 and its internal page SRT from the same `edge-tts` stream. SRT cues use the service's `WordBoundary` timing: sentence-ending punctuation always closes a cue; text over the default 20-visible-character limit first splits at commas, semicolons, or colons, then at the nearest word boundary. Override the limit with `--subtitle-max-chars`. Adjacent timing overlap up to 100 ms is tolerated by moving the later cue start to the previous cue end; larger overlap fails instead of silently distorting timing. Each SRT uses a page-local timeline whose origin is `00:00:00,000`, including any leading silence before the first cue. Cloud-provider commands currently write audio only. |
| 225 | |
| 226 | **Mandatory when `animations.json` is consumed — semantic animation context**: Before writing or refreshing `<project_path>/narration_timing.json`, determine whether the active context already contains the current top-level SVG group IDs and visible group-content semantics for every affected page. Reuse that context without rereading SVG when it is complete and still matches the current `svg_output/`. If any page is missing, stale, or represented only by group IDs/order without content meaning, read only that page's SVG as a read-only source and extract the missing group semantics. Always combine those semantics with the page SRT topics/timestamps and `animations.json`; group order alone is not a semantic narration mapping. |
| 227 | |
| 228 | > Active `animations.json` requires `narration_timing.json`; explicit `--no-animations` bypasses both. Without a sidecar, `narration_sync.py animations` maps groups **positionally** (group N → cue N) and warns when later objects may reveal during an earlier topic. Treat that warning as required repair: author the semantic plan and re-derive. |
| 229 | |
| 230 | **Narration animation ownership**: When `animations.json` is consumed, it remains read-only. The audio stage deep-copies it to `narration_animations.json`, preserves transitions, effects, durations, order, and explicit `effect: none`, then changes only the derived trigger/delay values needed for click-free narration playback. The authored `narration_timing.json` maps each animated content group—not each effect row—to the SRT cue that speaks about that content. For `effects[]`, the cue anchors the group's first active row; later rows keep global order and their relative delay. The command may still read an affected SVG page to resolve structural group order when a sparse sidecar cannot identify every effective group; this structural fallback does not replace the semantic-context step and never edits SVG, notes, or `animations.json`. Unmatched groups keep their canonical relative delay. |
| 231 | |
| 232 | **Title timing handoff when canonical animation exists**: preserve the title reveal decision already made by the custom-animation pass. Assign a title group to an SRT cue only when the user's request or the active motion plan explicitly chose `narration-cued`; otherwise leave its `cue` omitted in `narration_timing.json` so it keeps the canonical relative delay from `animations.json`. Do not infer `narration-cued` merely because speaker notes mention the title. |
| 233 | |
| 234 | **Narrated export animation selection**: |
| 235 | |
| 236 | | Sidecar state | Behavior | |
| 237 | |---|---| |
| 238 | | `narration_animations.json` exists | Use it by default | |
| 239 | | Only canonical `animations.json` exists | Block until narration synchronization creates the derived sidecar | |
| 240 | | Both are absent | Create no sidecar; inherit the base report's deck motion | |
| 241 | |
| 242 | Generate passes the base report through `--inherit-motion-from`: inherited |
| 243 | `-a none` preserves explicit objects-off, while final Stage-2 `false` does not. |
| 244 | Only explicit all-motion-off uses `--no-animations`. Invalid reports block; |
| 245 | audio duration plus padding owns final advance. |
| 246 | |
| 247 | When canonical custom animation is synchronized, |
| 248 | `<project_path>/narration_timing.json` is the explicit semantic mapping for |
| 249 | narrated object animation. It is fingerprinted to the ordered SRT set; `cue` |
| 250 | is the 1-based subtitle cue, and omitted `cue` keeps that group's canonical |
| 251 | relative delay. Reuse a complete current mapping when its fingerprint and SVG |
| 252 | group semantics remain valid; rebuild only affected pages when either input |
| 253 | changed. |
| 254 | |
| 255 | Get the exact fingerprint value with: |
| 256 | |
| 257 | ```bash |
| 258 | python3 skills/ppt-master/scripts/narration_sync.py fingerprint <project_path> |
| 259 | ``` |
| 260 | |
| 261 | ```json |
| 262 | { |
| 263 | "version": 1, |
| 264 | "srt_sha256": "<sha256 of the ordered page-local SRT set>", |
| 265 | "narration_padding": 0.5, |
| 266 | "slides": { |
| 267 | "01_title": { |
| 268 | "groups": [ |
| 269 | { "id": "page-title", "cue": 1 }, |
| 270 | { "id": "supporting-visual" } |
| 271 | ] |
| 272 | } |
| 273 | } |
| 274 | } |
| 275 | ``` |
| 276 | |
| 277 | `narration_sync.py subtitles` may still write `<project_path>/notes/subtitles/total.srt` as a PPTX-timeline diagnostic. It is not the delivery subtitle for a finished video. |
| 278 | |
| 279 | When video export was selected, `powerpoint_video.py` opens the final narrated PPTX through local Windows PowerPoint, requests its native video encoder with recorded timings and narrations enabled, and polls `CreateVideoStatus` until the MP4 succeeds, fails, or times out. The interface is synchronous to its caller even though PowerPoint performs encoding asynchronously. It preserves PowerPoint's own animation and media behavior rather than re-rendering the deck. |
| 280 | |
| 281 | If native video export fails, keep the narrated PPTX as a successful upstream |
| 282 | artifact and report the video failure separately. Do not regenerate audio or |
| 283 | the PPTX unless their own validation failed. |
| 284 | |
| 285 | After the MP4 exists, `video_subtitles.py` takes the exact narration text frozen in the page SRT set and force-aligns it against the finished video's actual audio track with `stable-ts`. Long delivery cues may be split for display at this final stage. This writes a same-stem external SRT without changing the MP4, notes, page SRT, or animation files. |
| 286 | |
| 287 | This stage keeps subtitles as external SRT files. It does not burn subtitles into the video. Automatic MP4 export is an optional Windows PowerPoint integration, not an independent renderer; when PowerPoint automation is unavailable, stop after the narrated PPTX instead of claiming a downgraded video. |
| 288 | |
| 289 | **Caller integration**: |
| 290 | |
| 291 | | Caller | After audio generation | |
| 292 | |---|---| |
| 293 | | Generate PPTX | With Edge SRT and an existing `animations.json`, derive `narration_animations.json`; with no sidecar, inherit the base report's resolved motion, while explicit all-motion-off uses `--no-animations`. Export with `--recorded-narration audio`, optionally continue through `powerpoint_video.py`, then generate the delivery SRT from the finished video. | |
| 294 | | Enhance Native PPTX | Return to [`native-enhance-pptx`](../native-enhance-pptx.md) Step 9; its `apply` command owns audio relationships, timings, transitions, and the enhanced export. If video was selected, pass that final PPTX to `powerpoint_video.py`. | |
| 295 | |
| 296 | For Generate PPTX, `--recorded-narration audio` prepares PowerPoint's recorded timings and narrations: every slide must have a matching supported audio file, every duration must be readable by `ffprobe`, and object animations must not use `--animation-trigger on-click`. Use `after-previous` or `with-previous` for narrated/video export. Narration changes the slide-advance layer only: the resolved page-transition effect remains unchanged, `-t none` remains visually transition-free, and narration advance disables click while using audio duration plus padding. The re-export is saved as `exports/<project_name>_<timestamp>_narrated.pptx`, telling it apart from silent exports. |
| 297 | |
| 298 | **Narrated SVG export**: use the default text-flow mode. It keeps authored line breaks in one editable, no-wrap text frame; narration does not require per-line text frames. |
| 299 | |
| 300 | --- |
| 301 | |
| 302 | ## Step 5: Completion report |
| 303 | |
| 304 | Output one summary block listing: |
| 305 | |
| 306 | - Number of audio files generated and their location (`<project_path>/audio/*`). |
| 307 | - For edge, number of matching page-local SRT files and their location (`<project_path>/notes/subtitles/*`). |
| 308 | - For narrated object animation, whether current SVG semantics were reused or which missing/stale pages were reread, plus semantic mapping coverage and fallback count. |
| 309 | - For Generate PPTX with Edge SRT and canonical custom animation, derived narration animation group count and `narration_animations.json` path; otherwise report inherited base motion or explicit all-motion-off. |
| 310 | - When video export was selected, the final MP4 path and native PowerPoint export status. |
| 311 | - When a finished video exists, the final aligned sidecar SRT path. |
| 312 | - The provider, voice, and rate/settings actually used. |
| 313 | - The caller-owned integration result: narrated SVG export path, enhanced native PPTX path, or “audio only”. |
| 314 | - For Generate PPTX when embedding was skipped, one-line hint: `python3 skills/ppt-master/scripts/svg_to_pptx.py <project_path> --recorded-narration audio`. |
| 315 |