tts-batchlisted

Render TTS audio for every segment listed in segments.index.json with budget guard, retries, and a manifest. Use after segmentation to produce the full narration track set.
huodebing-alt/Agentic-Headshot-Video-Studio · ★ 0 · AI & Automation · score 71

Install: claude install-skill huodebing-alt/Agentic-Headshot-Video-Studio

# TTS Batch / 批量配音 ## When to use / 何时使用 After segment-script-45s. Produces all segment MP3s in one pass. 切段完成后，一次性产出全部段落 MP3。 ## Inputs / 输入 - `workspace/script/segments.index.json`. - `config/voice.json`. - `config/yolo-spend.json` (budget guard). ## Output / 输出 - `workspace/voice/seg_*.mp3`. - `workspace/voice/manifest.json`: `[{id, mp3, seconds, chars, cost_est}]`. ## Steps / 步骤 1. YOLO guard: sum estimated cost across all segments; abort if > remaining budget. 2. For each segment, call `tts-segment` (or inline equivalent) with concurrency 3. 3. Aggregate manifest; compute total cost and duration. 4. Print summary table. ## Examples / 示例 ``` claude run tts-batch ``` ## Failure recovery / 失败回退 - If any segment fails twice, skip it but continue; final summary lists failures. - On total cost overrun mid-run, pause and surface confirmation prompt.