BBS.pyVideoTrans.com No audio file was generated during the listening test.self=[QwenttsLocal]: uuid=None, proxy_str=None, tts_type=1, len=1, language='en', play=True, volume='+0%', pitch='+0Hz', rate='+0%', speed=1.0, has_done=0, wait_sec=1.0, dub_nums=1, error='No audio file was generated during the listening test.', api_url='', is_cuda=False, local_dir='D:/AI_dub_pyvideotrans-v4.15/models/models--Qwen--Qwen3-TTS-12Hz-0.6B-CustomVoice', is_redubb=False, model_name='0.6B', ainame=None:

#7901 No audio file was generated during the listening test.self=[QwenttsLocal]: uuid=None, proxy_str=None, tts_type=1, len=1, language='en', play=True, volume='+0%', pitch='+0Hz', rate=...

[Last reply:5 hours ago] The Qwen3-TTS (Built-in) listening test failed to produce any audio. This almost always happens when the model files are incomplete/corrupted (the download from huggingface.co was interrupted), or whe...

37.142**1 Posted at: 5 hours ago

#7900 Proxy configuration issue, check settings or disable proxy:{'text': 'Hello, my dear friend, I hope every day of yours is wonderful and joyful!', 'rate': '+0%', 'role': 'Sonia(Femal...

💬 1

[Last reply:9 hours ago] 核心原因：软件启用了网络代理 http://127.0.0.1:2802，但该代理端口没有服务在运行（连接被拒绝 ConnectionRefused），导致 Edge-TTS 请求全部失败。解决方案（按顺序排查）：检查代理是否真的在运行：127.0.0.1:2802 是本机代理端口，请确认你的代理软件已启动、端口号是否正确（很多软件默认端口是 10808、10809、7890 等，而非 2802）...

58.218**0 Posted at: 9 hours ago

#7899 list index out of range...

💬 1

[Last reply:9 hours ago] list index out of range 是一个通用 Python 索引错误，可能出现在语音识别、字幕翻译、配音或音画对齐等多个阶段，仅凭这一条信息无法定位具体的出错环节。此外，你的安装路径 D:/Program Files (exe)/_AV/pyVideoTrans 存在问题：包含空格和括号 ( ) 等特殊字符，官方明确建议解压路径仅包含英文和数字，不要有任何特殊符号，也不要放在 Pro...

99.239**2 Posted at: 9 hours ago

#7898 list index out of range...

💬 3

[Last reply:10 hours ago] The M2M100 model is a local model that is not bundled with the software — it is downloaded on first use from a domestic mirror. This "list index out of range" error almost certainly means the M2M100 m...

91.94**2 Posted at: 10 hours ago

#7897 429 Client Error: Too Many Requests for url: https://www.google.com/sorry/index?continue=https://translate.google.com/m%3Fsl%3Dzh-cn%26tl%3Den%26hl%3Den%26q%3D%25E6%259C%25AC%25E8%...

💬 1

[Last reply:11 hours ago] 这是 Google 翻译渠道返回 429 限流错误（Too Many Requests），底层原因是请求过于频繁或所用代理 IP 被 Google 判定为异常流量。解决方案（按推荐顺序）：降低请求频率：进入菜单 → 工具/选项 → 高级选项 → 字幕翻译，将传统翻译渠道每批字幕行数调小（如 1），并增大翻译后暂停秒（如 3-5 秒）。更换代理节点：你当前使用 http://127.0.0....

94.183**5 Posted at: 11 hours ago

#7896 Traceback (most recent call last): File...

💬 1

[Last reply:11 hours ago] 这是超长视频（时长约 20 小时，video_duration_ms=72372500 ≈ 20.1 小时）下，音画对齐阶段尝试将整个音频写入单个 WAV 文件，超出标准 WAV 格式 4GB 尺寸上限，导致 struct.error: argument out of range。标准 WAV 文件头部用 32 位无符号整数记录数据长度，最大约 4GB。你的视频总时长 20 小时，即使单声道 16...

113.95**5 Posted at: 11 hours ago

#7895 ASR Error [Qwen-ASR(Local)] CUDA error: CUBLAS_STATUS_EXECUTION_FAILED when calling `cublasGemmEx( handle, opa, opb, m, n, k, alpha_ptr, a, CUDA_R_16F, lda, b, CUDA_R_16F, ldb, bet...

💬 1

[Last reply:12 hours ago] This is a CUDA/cuBLAS runtime failure inside the Qwen-ASR local model when running in fp16 (CUDA_R_16F). It is NOT a problem with the input audio file. Common causes: GPU driver / CUDA / cuDNN version...

202.150**5 Posted at: 12 hours ago

#7894 list index out of range...

💬 1

[Last reply:13 hours ago] "list index out of range" is a generic Python indexing error and cannot be pinpointed to one specific cause from this message alone. The exact stage that failed (STT / translation / TTS / alignment / ...

37.142**1 Posted at: 13 hours ago

#7893 Video file selection required...

💬 1

[Last reply:18 hours ago] This message means the software cannot start the task because no video/audio file has been selected.Cause: The required first field Select Video/Audio on the main interface is empty. pyVideoTrans will...

88.164**1 Posted at: 18 hours ago

#7892 in which version the kokoro is available build in...

💬 1

[Last reply:18 hours ago] Kokoro-TTS has been available as a built-in local API channel since at least v4.11, as referenced in the custom TTS API documentation. However, the knowledge base does not explicitly state the exact v...

152.59**3 Posted at: 18 hours ago

#7891 最后一步字幕配音嵌入时出错frame= 1305 fps= 53 q=28.0 size= 29440KiB time=00:01:04.66 bitrate=3729.8kbits/s speed=2.61x elapsed=0:00:24.74 frame= 1333 fps= 53 q=26.0 size= 29952KiB time=...

💬 1

[Last reply:19 hours ago] 最后一步合成硬字幕时，FFmpeg 执行 subtitles=filename='end.ass' 滤镜失败。日志显示 ffmpeg 已输出大量进度信息（frame=...）后突然以 exit status 1 退出，且两次（硬件 h264_nvenc 和软件 libx264）均失败。核心原因分析：该错误不是编码器问题（因为软编码 libx264 也失败了），而是 ASS 硬字...

206.14**3 Posted at: 19 hours ago

#7890 Traceback (most recent call last): File...

💬 1

[Last reply:20 hours ago] 核心原因是 ffmpeg 调用失败，报错发生在“按字幕剪辑视频/文稿匹配打轴”功能重建输入视频阶段：runffmpeg 执行 ffmpeg 时返回非 0，最终抛出 FFmpegError。从命令和路径看，最可疑点是文件路径/文件名包含大量特殊字符、空格、中文、方括号、点号、&、www. 等复杂内容，导致 ffmpeg 命令执行异常。请按以下步骤处理：将原始视频移动到浅层、纯英文数字路径例...

206.14**3 Posted at: 20 hours ago

#7889 Traceback (most recent call last): File...

💬 1

[Last reply:21 hours ago] 核心原因是文件路径中包含中文、空格和特殊字符（&、.等），导致 ffmpeg 命令解析失败。从报错看，ffmpeg 正在执行 shot_matcher（文稿匹配与打轴功能的抽帧）时崩溃。解决方案：将该 mkv 视频移动到浅层全英文目录下，例如 D:/videos/law_s25e09.mkv。文件名只保留英文字母、数字和下划线，去掉所有中文、空格、&、.、[]、() 等特殊符号。重...

206.14**3 Posted at: 21 hours ago

#7887 我用阿里的这个模型翻译字幕，为什么会出现空白时间戳...

💬 3

[Last reply:23 hours ago] 了解。若你已确认是阿里百炼 Qwen-MT 渠道本身的问题（内容审核导致中途停止返回、返回不完整），这属于该渠道的服务端行为，软件端无法绕过其审核机制。建议：更换翻译渠道。首选 DeepSeek 或 OpenAI（ChatGPT），这两个渠道翻译质量高、价格低、无此类中途审核中断问题，且对字幕格式的返回更稳定。DeepSeek 配置方式：访问 https://platform.deepseek.c...

85.211**6 Posted at: 1 day ago

#7888 <400> InternalError.Algo.DataInspectionFailed: Output data may contain inappropriate content.Traceback (most recent call last):...

💬 1

[Last reply:1 day ago] `这是翻译结果被阿里百炼平台的内容安全审核拦截导致的，不是软件本身故障。报错信息 <400> InternalError.Algo.DataInspectionFailed: Output data may contain inappropriate content 是阿里云服务端返回的，表示 AI 模型本次生成的译文（或输入字幕内容）触发了阿里云的内容合规检查。核心解决办法：更换翻译...

2a03**6b Posted at: 1 day ago

#7886 语音识别阶段出错[faster-whisper(本地内置)] No transcription results returned. Please check the original audio/video or model and try again.Traceback (most recent call last):...

💬 1

[Last reply:1 day ago] 核心原因有三类：视频本身无有效人声/音轨、模型文件下载不完整或损坏、软件版本过旧（v4.03）。需逐项排查。按顺序排查：确认视频有声音：用播放器手动播放 jade.wears1 (3).mp4，确认能正常听到人声。若从网上下载的视频，画面与音轨可能分离导致无音轨；若仅有背景音乐无人声，ASR 无法识别，必然返回空结果。规范文件路径名：你的路径 D:/Desktop/jade.wears1/jade...

240e**e1f5 Posted at: 1 day ago

#7885 语音识别阶段出错[faster-whisper(内置)] No human voice detected. Please confirm that human speech is present in the original file. [info.duration_after_vad=0.0s]._kw={'beam_size': 5, 'best_of...

💬 1

[Last reply:1 day ago] 核心原因：VAD（语音活动检测）过滤后有效语音时长为 0（duration_after_vad=0.0s），即系统判定整段音频中没有人类说话声。虽然识别出语言为 en，但这只是模型对音频特征的猜测，并非真实语音。常见原因及排查步骤：确认视频是否真有人声：日志中 is_audio_trans=False、should_dubbing=False，说明这是视频文件。请先用播放器确认该视频确实包含人声说...

104.28**2 Posted at: 1 day ago

#7884 expected str, bytes or os.PathLike object, not NoneTypeTraceback (most recent call last):...

💬 1

[Last reply:1 day ago] The error occurs because your input file is an audio-only file (.MP3) but the alignment engine (_rate.py) is trying to run its video-extension/slow-down routine, which requires a video stream. With no...

109.226**0 Posted at: 1 day ago

#7883 语音识别阶段出错[faster-whisper(内置)] Unable to open file 'model.bin' in model 'D:/software/2ai/win-pyvideotrans-v4.15/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo',Tracebac...

💬 1

[Last reply:1 day ago] 核心原因：faster-whisper 的 large-v3-turbo 模型文件缺失或不完整。报错显示软件在 models--mobiuslabsgmbh--faster-whisper-large-v3-turbo 目录中找不到 model.bin 文件，这通常是模型自动下载失败（网络不稳定/被中断/仅下载了部分文件）导致的，属于下载失败间接引发的错误。解决方案（按顺序尝试）：检查模型目录打开...

104.28**5 Posted at: 1 day ago

#7882 ...

💬 1

[Last reply:1 day ago] 这是配音和画面需要重新对齐导致的报错，属于 ffmpeg 执行阶段失败。需提供日志才能定位具体原因。请按以下步骤操作：打开软件安装目录下的 logs/ 文件夹，找到最新的日志文件（如 20250622.log）。复制该日志文件底部约 30 行的报错信息发出来。同时，可以先尝试以下排查：勾选主界面的清理已生成，然后重试。进入菜单 -> 工具 -> 高级选项 -> 视频输出控制，...

2408**3f2e Posted at: 1 day ago