Skip to content

zenstory-ai/video-recap-skills / skills/video-recap

video-recap

Verified

把一段或多集视频做成带画框字幕的中文解说成片或纯原声高光短片。用户提供 .mp4 / .mov / .mkv / .webm,要求做影视解说、短剧二创、加旁白配音、跨集混剪或导出剪映草稿时使用;串联完成看片识台词、定主线与留原声、按台词停顿切镜头、写词检查、TTS 配音与混音加字幕。触发词:视频解说、影视解说、视频旁白、生成解说、视频 recap、video recap、voiceover、narration、recap。

FileKindSize
SKILL.mdskill md18.4 KB
assets/dashboard/app.jsscript16.2 KB
assets/dashboard/index.htmlother867 B
assets/dashboard/styles.cssother22.6 KB
assets/dashboard/tokens.cssother8.9 KB
assets/dashboard/views.jsscript31.4 KB
references/audio-modes.mdmarkdown3.6 KB
references/config-playbook.mdmarkdown8.1 KB
references/creative-editing-playbook.mdmarkdown12.3 KB
references/data-schema.mdmarkdown34.6 KB
references/index-tts.mdmarkdown2.1 KB
references/jianying/LICENSE.duo-videoother1.0 KB
references/jianying/SOURCE.mdmarkdown703 B
references/jianying/empty_draft_meta_info.jsonconfig1.7 KB
references/jianying/empty_jy_material_video.jsonconfig1.8 KB
references/jianying/empty_jy_meta_material_value.jsonconfig358 B
references/jianying/empty_jy_project_info.jsonconfig3.6 KB
references/jianying/empty_jy_segment.jsonconfig1.3 KB
references/jianying/empty_jy_text_styles.jsonconfig440 B
references/jianying/empty_yj_material_audio.jsonconfig865 B
references/jianying/empty_yj_material_text.jsonconfig2.4 KB
references/packaging.mdmarkdown6.8 KB
references/promotional-copy.mdmarkdown4.1 KB
references/prompt-templates.mdmarkdown2.0 KB
references/research-guide.mdmarkdown2.7 KB
references/resource-library.mdmarkdown12.1 KB
references/shot-review.mdmarkdown4.8 KB
scripts/agent_text.pyscript2.7 KB
scripts/artifacts.pyscript972 B
scripts/asr.pyscript12.5 KB
scripts/asr_timing_evidence.pyscript4.2 KB
scripts/assemble.pyscript31.0 KB
scripts/assemble_constants.pyscript894 B
scripts/assembly_contract.pyscript10.3 KB
scripts/assembly_settings.pyscript3.8 KB
scripts/audio_automation.pyscript6.6 KB
scripts/audio_mix.pyscript18.5 KB
scripts/briefing/__init__.pyscript101 B
scripts/briefing/builder.pyscript31.1 KB
scripts/briefing/context.pyscript6.1 KB
scripts/briefing/timeline.pyscript23.0 KB
scripts/codec_peak.pyscript5.1 KB
scripts/cut.pyscript148 B
scripts/cut_cli.pyscript12.4 KB
scripts/cut_contract.pyscript13.3 KB
scripts/cut_qc.pyscript1.9 KB
scripts/cut_render.pyscript13.2 KB
scripts/dashboard/__init__.pyscript159 B
scripts/dashboard/data.pyscript24.6 KB
scripts/dashboard/io.pyscript7.1 KB
scripts/dashboard/runs.pyscript21.8 KB
scripts/dashboard/templates.pyscript9.6 KB
scripts/dashboard_server.pyscript9.3 KB
scripts/detect.pyscript22.2 KB
scripts/doctor.pyexecutablescript12.9 KB
scripts/entry_suggestion.pyscript4.6 KB
scripts/export_jianying.pyscript5.6 KB
scripts/extract.pyscript2.5 KB
scripts/final_qc.pyscript19.0 KB
scripts/frame_grid.pyscript10.6 KB
scripts/jianying/__init__.pyscript49 B
scripts/jianying/builders.pyscript11.3 KB
scripts/jianying/model.pyscript2.7 KB
scripts/jianying/optional.pyscript1012 B
scripts/jianying/schema.pyscript2.5 KB
scripts/jianying/templates.pyscript1.0 KB
scripts/jianying/timeline_contract.pyscript5.8 KB
scripts/jianying/tracks.pyscript2.0 KB
scripts/jianying/writer.pyscript7.8 KB
scripts/lib.pyscript29.6 KB
scripts/library.pyscript31.1 KB
scripts/lint_summary.pyscript5.0 KB
scripts/loudness.pyscript14.7 KB
scripts/materials.pyscript22.1 KB
scripts/media.pyscript18.8 KB
scripts/narration_audio.pyscript13.5 KB
scripts/narration_lint.pyscript24.1 KB
scripts/narrative_selection.pyscript8.9 KB
scripts/packaging.pyscript6.1 KB
scripts/packaging_fonts.pyscript12.0 KB
scripts/packaging_plates.pyscript31.2 KB
scripts/packaging_studio.pyscript34.1 KB
scripts/providers/__init__.pyscript72 B
scripts/providers/fish_audio.pyscript3.1 KB
scripts/providers/index_tts.pyscript8.8 KB
scripts/recap.pyscript183 B
scripts/recap_cli.pyscript6.9 KB
scripts/recap_inspect.pyscript16.5 KB
scripts/recap_runner.pyscript22.0 KB
scripts/recap_runtime.pyscript11.8 KB
scripts/recap_source.pyscript1.8 KB
scripts/recap_stage_qc.pyscript2.7 KB
scripts/recap_timeline.pyscript7.7 KB
scripts/render_preflight.pyscript1.7 KB
scripts/resources/__init__.pyscript200 B
scripts/resources/lock.pyscript6.8 KB
scripts/resources/project_binding.pyscript16.1 KB
scripts/sentence_boundaries.pyscript28.8 KB
scripts/sentence_gate.pyscript8.6 KB
scripts/sfx_mix.pyscript14.6 KB
scripts/shot_review.pyscript18.9 KB
scripts/source_subtitles.pyscript7.2 KB
scripts/speech_ownership.pyscript9.3 KB
scripts/storyboard.pyscript21.8 KB
scripts/subtitles/__init__.pyscript56 B
scripts/subtitles/core.pyscript19.0 KB
scripts/subtitles/render.pyscript8.0 KB
scripts/timeline.pyscript8.2 KB
scripts/timeline_emit.pyscript5.4 KB
scripts/tts_audio.pyscript9.6 KB
scripts/tts_cache.pyscript4.5 KB
scripts/understand.pyscript171 B
scripts/understanding_brief.pyscript6.3 KB
scripts/understanding_cache.pyscript8.0 KB
scripts/understanding_runner.pyscript9.8 KB
scripts/understanding_storyboard.pyscript11.9 KB
scripts/validate.pyscript5.7 KB
scripts/visual_render.pyscript10.1 KB
scripts/vlm.pyscript16.4 KB
scripts/voiceover.pyscript28.0 KB

scripts/narration_audio.py

View on GitHub
"""Narration tempo fitting and sample-accurate timeline WAV placement."""

import os
import wave
from pathlib import Path

from lib import CONFIG, get_video_duration, log, narration_tempo_budget, run_cmd

def _apply_narration_speed(tts_segments, work_dir):
    """Globally speed up narration audio via atempo (CONFIG['narration_speed']).

    MiMo TTS reads a touch slowly for short-form recaps; a 1.1-1.2x bump makes it
    snappier without the chipmunk effect. Rewrites each segment's audio_path/duration
    to the sped copy so the rest of assembly is unchanged. No-op at speed 1.0.
    """
    speed = CONFIG["narration_speed"]
    if abs(speed - 1.0) <= 1e-3:
        return
    done = 0
    for seg in tts_segments:
        src = seg["audio_path"]
        if not os.path.exists(src):
            continue  # reported as a skipped segment during placement
        out = str(Path(work_dir) / f"_spd_{seg['index']}.wav")
        res = run_cmd(["ffmpeg", "-y", "-i", src, "-filter:a", f"atempo={speed:.3f}",
                              "-ar", "44100", "-ac", "1", "-acodec", "pcm_s16le", out])
        if res.returncode != 0:
            raise RuntimeError(f"解说提速失败 {src}: {res.stderr}")
        seg["_unsped_audio_path"] = src
        seg["_applied_global_speed"] = speed
        seg["audio_path"] = out
        seg["audio_duration"] = get_video_duration(out)
        done += 1
    log(f"解说整体提速: atempo={speed:.2f} ({done} 段)")


def _atempo_filter_chain(factor):
    """Build an FFmpeg atempo chain (each stage within [0.5, 2.0]) for a single-pass stretch."""
    parts = []
    rem = float(factor)
    while rem > 2.0:
        parts.append("atempo=2.0")
        rem /= 2.0
    while rem < 0.5:
        parts.append("atempo=0.5")
        rem /= 0.5
    parts.append(f"atempo={rem:.6f}")
    return ",".join(parts)


def _adjust_tts_speed(
    audio_path,
    target_duration,
    tts_rate_offset=0.0,
    *,
    segment_index=None,
    raw_source_path=None,
    base_speed=1.0,
):
    """Fit overlong TTS with bounded atempo; never time-trim speech in assemble.

    Assemble has no word/sentence timestamps, so if bounded atempo cannot make the
    audio fit, it returns `fit_status=no_safe_fit` and leaves the original audio
    untouched for QC to block instead of guessing a spoken_text truncation.
    """
    audio_path = Path(audio_path)
    current_dur = get_video_duration(audio_path)
    budget = narration_tempo_budget(tts_rate_offset)
    meta = {"fit_status": "fits", "segment_tempo_factor": 1.0}
    if current_dur <= target_duration:
        return (str(audio_path), current_dur, meta)

    ratio = current_dur / target_duration
    effective_max = budget["segment_tempo_max"]
    if ratio > effective_max:
        meta.update({
            "fit_status": "no_safe_fit",
            "truncate_reason": "no_safe_boundary",
            "needed_tempo_factor": ratio,
        })
        label = "" if segment_index is None else f"段 {segment_index + 1} "
        log(
            f"  TTS 无安全放置: {label}{current_dur:.1f}s 需 x{ratio:.2f},"
            f"超过段内预算 x{effective_max:.2f}(assemble 不按时间硬切)"
        )
        return (str(audio_path), current_dur, meta)

    # 温和加速。给 atempo/容器时长舍入留出 0.2% 安全余量;宁可极轻微
    # 多加速,也不能在写入时间线时裁掉最后一个音节。
    tempo = min(ratio * 1.002, effective_max)
    adjusted_path = audio_path.with_name(f"{audio_path.stem}_adj{audio_path.suffix}")
    use_single_pass = bool(raw_source_path and os.path.exists(raw_source_path) and base_speed > 0)
    encode_src = str(raw_source_path) if use_single_pass else str(audio_path)
    encode_tempo = (float(base_speed) * tempo) if use_single_pass else tempo
    cmd = ["ffmpeg", "-y", "-i", encode_src,
           "-filter:a", _atempo_filter_chain(encode_tempo),
           "-ar", "44100", "-ac", "1", str(adjusted_path)]
    result = run_cmd(cmd)
    if result.returncode != 0:
        raise RuntimeError(f"TTS 加速失败 {audio_path}: {result.stderr}")
    new_dur = get_video_duration(adjusted_path)
    if new_dur > target_duration + (1.0 / 44100.0):
        adjusted_path.unlink(missing_ok=True)
        meta.update({
            "fit_status": "no_safe_fit",
            "truncate_reason": "no_safe_boundary",
            "needed_tempo_factor": new_dur / target_duration,
        })
        log(
            f"  TTS 加速后仍超出安全窗口 {new_dur - target_duration:.3f}s;"
            "禁止裁尾,交由 Agent 缩短/移动文本"
        )
        return (str(audio_path), current_dur, meta)
    meta.update({"fit_status": "tempo_adjusted", "segment_tempo_factor": tempo})
    log(f"  TTS 温和加速: {current_dur:.1f}s → {new_dur:.1f}s (x{tempo:.2f})")
    return (str(adjusted_path), new_dur, meta)


def _edge_quiet_samples(pcm16_mono, sample_count, *, from_start, threshold=260):
    """Count near-silent PCM16 samples at one edge of a mono buffer."""
    indices = range(sample_count) if from_start else range(sample_count - 1, -1, -1)
    quiet = 0
    for index in indices:
        offset = index * 2
        value = int.from_bytes(pcm16_mono[offset:offset + 2], "little", signed=True)
        if abs(value) > threshold:
            break
        quiet += 1
    return quiet


def _speech_safe_fade_lengths(pcm16_mono, sample_count, sample_rate, configured_ms):
    """Limit fades to edge silence so first/last syllables are never attenuated.

    When TTS has no measurable edge silence, retain only a 5ms anti-click ramp.
    """
    configured = min(int(max(0.0, float(configured_ms)) * sample_rate / 1000), sample_count // 4)
    if configured <= 0:
        return 0, 0
    anti_click = min(int(0.005 * sample_rate), configured)
    leading = _edge_quiet_samples(pcm16_mono, sample_count, from_start=True)
    trailing = _edge_quiet_samples(pcm16_mono, sample_count, from_start=False)
    return min(configured, max(anti_click, leading)), min(configured, max(anti_click, trailing))


def _unplaced(seg, at, fit_status, reason, *, blocking=False):
    """Record a segment that contributes no audio: a zero-width window at `at` seconds."""
    seg["actual_place_start"] = at
    seg["actual_place_end"] = at
    seg["placed_audio_duration"] = 0.0
    seg["fit_status"] = fit_status
    seg["truncate_reason"] = reason
    seg["blocking"] = blocking


def _build_timed_narration(
    tts_segments,
    output_wav,
    video_duration,
    work_dir,
):
    """将 TTS 片段按时间轴放置到一条与视频等长的音轨上"""
    sample_rate = 44100
    total_samples = int(video_duration * sample_rate)
    buffer = bytearray(total_samples * 2)
    last_written_end = 0  # 追踪已写入位置,防止重叠
    pause_samples = 0  # 这一段的 pause_after_ms(负值按 0),下一段据此留间隔

    for seg in tts_segments:
        wav_path = seg["audio_path"]
        prev_pause_samples, pause_samples = (
            pause_samples,
            max(0, int(seg["pause_after_ms"] * sample_rate / 1000)),
        )

        # 放置状态的起始值;只有实际加速或未放置才覆盖。缺 WAV 的段也要有,QC 按键直读。
        tts_rate_offset = seg["tts_rate_offset"]
        budget = narration_tempo_budget(tts_rate_offset)
        seg.update({
            "fit_status": "fits",
            "segment_tempo_factor": 1.0,
            "global_narration_speed": budget["global_narration_speed"],
            "effective_tempo": budget["global_narration_speed"] * budget["tts_rate_factor"],
            "blocking": False,
        })

        if not os.path.exists(wav_path):
            _unplaced(seg, seg["start"], "skipped", "missing_wav")
            continue

        tts_dur = seg["audio_duration"]

        start_sample = int(seg["start"] * sample_rate)
        end_boundary = int(min(seg["end"], video_duration) * sample_rate)

        # 段间间隔:使用前一段的 pause_after_ms(来自 narration.json)
        min_start_with_pause = last_written_end + prev_pause_samples
        actual_start = min(max(start_sample, min_start_with_pause), end_boundary)

        # 根据实际可用空间决定是否加速
        available = end_boundary - actual_start
        available_duration = max(available / sample_rate, 0)
        if tts_dur > available_duration > 0:
            wav_path, _actual_dur, fit_meta = _adjust_tts_speed(
                wav_path, available_duration, tts_rate_offset,
                segment_index=seg["index"],
                raw_source_path=seg.get("_unsped_audio_path"),
                base_speed=seg.get("_applied_global_speed", 1.0),
            )
            if fit_meta["fit_status"] == "no_safe_fit":
                if "needed_tempo_factor" in fit_meta:
                    seg["needed_tempo_factor"] = round(fit_meta["needed_tempo_factor"], 4)
                _unplaced(seg, actual_start / sample_rate, "no_safe_fit",
                          fit_meta["truncate_reason"], blocking=True)
                continue
            seg["fit_status"] = fit_meta["fit_status"]
            seg["segment_tempo_factor"] = fit_meta["segment_tempo_factor"]
            seg["effective_tempo"] *= fit_meta["segment_tempo_factor"]

        # 放在拟合之后判断:_adjust_tts_speed 的输出读回来就是 44100Hz mono 16bit,无需再转
        try:
            with wave.open(wav_path, "rb") as wf_check:
                needs_resample = (
                    wf_check.getnchannels(), wf_check.getsampwidth(), wf_check.getframerate()
                ) != (1, 2, sample_rate)
        except (wave.Error, EOFError):
            # Valid post-processed WAV may use IEEE float, which Python's wave
            # reader does not support. FFmpeg performs the explicit PCM conversion.
            needs_resample = True
        if needs_resample:
            tmp_path = str(Path(work_dir) / f"_rs_{seg['index']}.wav")
            rs_result = run_cmd(["ffmpeg", "-y", "-i", wav_path,
                                        "-ar", str(sample_rate), "-ac", "1",
                                        "-acodec", "pcm_s16le", tmp_path])
            if rs_result.returncode != 0:
                log(f"  跳过: 重采样失败 {wav_path}: {rs_result.stderr}")
                _unplaced(seg, seg["start"], "skipped", "resample_failed")
                continue
            wav_path = tmp_path

        with wave.open(wav_path, "rb") as wf:
            wf_data = bytearray(wf.readframes(wf.getnframes()))

        # 按场景边界裁剪
        write_samples = len(wf_data) // 2

        if write_samples <= 0 or available <= 0:
            log(f"  跳过: {seg['start']:.1f}s-{seg['end']:.1f}s (无空间)")
            _unplaced(seg, seg["start"], "no_safe_fit", "no_room", blocking=True)
            continue

        if write_samples > available:
            # No tolerance-based trimming: even a few milliseconds may contain a
            # consonant/vowel release. _adjust_tts_speed must produce a complete file
            # that fits; otherwise block and ask the Agent to shorten/move the block.
            over = (write_samples - available) / sample_rate
            log(f"  TTS 无安全放置: 段 {seg['index'] + 1} 超出可用窗口 {over:.3f}s;禁止裁尾,交由 QC 阻断")
            _unplaced(seg, actual_start / sample_rate, "no_safe_fit", "no_safe_boundary", blocking=True)
            continue

        # fade-in / fade-out
        fade_in_len, fade_out_len = _speech_safe_fade_lengths(
            wf_data, write_samples, sample_rate, CONFIG["fade_ms"]
        )
        for i in range(fade_in_len):
            gain = i / fade_in_len
            s = i * 2
            sample = int.from_bytes(wf_data[s:s+2], 'little', signed=True)
            sample = int(sample * gain)
            wf_data[s:s+2] = sample.to_bytes(2, 'little', signed=True)
        for i in range(fade_out_len):
            gain = 1.0 - i / fade_out_len
            s = (write_samples - 1 - i) * 2
            sample = int.from_bytes(wf_data[s:s+2], 'little', signed=True)
            sample = int(sample * gain)
            wf_data[s:s+2] = sample.to_bytes(2, 'little', signed=True)

        # Persist the exact complete per-beat PCM used by the canonical mix. Editable
        # exports must reference this file, not the longer pre-fit TTS input; otherwise
        # their timeline_end silently chops the final word even when ffmpeg is correct.
        placed_path = Path(work_dir) / f"_placed_{seg['index']:04d}.wav"
        with wave.open(str(placed_path), "wb") as placed_wav:
            placed_wav.setnchannels(1)
            placed_wav.setsampwidth(2)
            placed_wav.setframerate(sample_rate)
            placed_wav.writeframes(bytes(wf_data))
        seg["placed_audio_path"] = str(placed_path)

        buffer[actual_start * 2: actual_start * 2 + write_samples * 2] = wf_data
        seg["actual_place_start"] = actual_start / sample_rate
        seg["actual_place_end"] = (actual_start + write_samples) / sample_rate
        seg["placed_audio_duration"] = write_samples / sample_rate
        last_written_end = actual_start + write_samples

    with wave.open(str(output_wav), "wb") as wf:
        wf.setnchannels(1)
        wf.setsampwidth(2)
        wf.setframerate(sample_rate)
        wf.writeframes(bytes(buffer))

    if tts_segments and all(seg["fit_status"] == "skipped" for seg in tts_segments):
        output_wav.unlink(missing_ok=True)
        raise RuntimeError(
            f"全部 {len(tts_segments)} 段解说均被跳过或未能写入"
            f"(WAV 缺失或无可用时间;跳过 {len(tts_segments)} 段),"
            "已中止以避免生成无解说视频"
        )

    log(f"解说音轨: {video_duration:.1f}s, {len(tts_segments)} 段")
slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."Stars: 198kUpdated Claude CodeCodexVerifiedInstall
ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read.Stars: 196kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 196kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt.Stars: 196kUpdated Claude CodeCodexVerifiedInstall