BBS.pyVideoTrans.com 配音全部失败 :Edge-TTS HTTP 500 (configured proxy): Invalid response statusall_voices={'en-US-BrianNeural'}:

#8468 配音全部失败 :Edge-TTS HTTP 500 (configured proxy): Invalid response statusall_voices={'en-US-BrianNeural'}:...

[Last reply:57 minutes ago] 这是 Edge-TTS 走网络代理失败导致的：报错中的 (configured proxy) 明确表示 Edge-TTS 通过你配置的代理请求微软接口，代理返回了无效状态（HTTP 500）。解决方案（按顺序尝试）1. 让 Edge-TTS 绕过代理（最直接）在软件根目录 I:\dy\dy\pyvideotrans\ 下新建一个空文本文件，命名为：edgetts-noproxy.txt（注意是空文...

206.14**3 Posted at: 57 minutes ago

#8467 [WinError 32] The process cannot access the file because it is being used by another process: 'D:/EXTRAS/py videotrans/tmp/19308/2d1ad91e61/final_audio_temp.wav'：D:/EXTRAS/py video...

💬 1

[Last reply:1 hour ago] This is a Windows file-lock problem (WinError 32): the alignment stage generated final_audio_temp.wav, and when it tried to rename/move it to target.wav, that file was still held by another process (m...

103.83**8 Posted at: 1 hour ago

#8466 源码部署本项目，运行uv sync --all-extras，如果已安装，请单独执行uv sync --extra dotnet 安装 pythonnet 模块在那里运行运行uv sync --all-extras...

💬 1

[Last reply:2 hours ago] uv sync 系列命令必须在源码项目的根目录运行，也就是 git clone 之后进入的 pyvideotrans 文件夹；该目录中应能看到 pyproject.toml 和 uv.lock。操作顺序：git clone https://github.com/jianchang512/pyvideotrans.gitcd pyvideotrans（即项目根目录）uv sync --all-ext...

104.28**4 Posted at: 2 hours ago

#8465 Missing dubbing for subtitle 1: I:/dy/dy/pyvideotrans/tmp/24828/ab142ca8eb/0-bbe9c3c86408e686999d4ec304b17b78.wavTraceback (most recent call last):...

💬 1

[Last reply:2 hours ago] 这是由于 Edge-TTS 配音阶段未能成功生成音频文件（单条配音失败不会立即中断，直到对齐阶段检查文件时才发现缺失，从而抛出 Missing dubbing for subtitle 1）。常见触发原因是 Edge-TTS 403 限流，或所填代理 http://127.0.0.1:10808 对 Edge-TTS 连接异常。解决方案（按顺序尝试）：升级版本修复 Edge-TTS 403：Edg...

206.14**3 Posted at: 2 hours ago

#8464 语音识别阶段出错[parakeet日语(内置)] videotrans.configure.excepts.SpeechToTextErrorTraceback (most recent call last):...

💬 1

[Last reply:3 hours ago] 最可能的原因是 parakeet日语(内置) 模型未下载完整或已损坏（该渠道首次使用需在线下载模型，网络不稳定极易失败）。此外，v4.12 已用 Nemotron-3.5-asr-0.6b(内置) 替换了原 parakeet 日语渠道，旧渠道在新版本下可能不兼容。请按以下步骤处理：手动下载模型并放置：下载 parakeet-ja.zip，解压后将其内的 parakeet 文件夹复制到软件目录/m...

120.238**4 Posted at: 3 hours ago

#8463 连接被重置，网络可能不稳定Traceback (most recent call last):...

💬 1

[Last reply:4 hours ago] 核心原因是网络层连接被远程服务端强制中断（WinError 10054），失败发生在「微软(免费)」翻译渠道请求阶段，属于网络/代理或微软免费接口限流问题，并非软件逻辑错误。处理步骤：先检查代理设置：主界面「网络代理」文本框若填写了内容，请先完全清空。微软翻译国内可直连，填写无效代理会导致所有请求被重置。若本机开着 Clash/VPN 等工具（全局模式），请切换为「直连/规则模式」或暂时关闭后重试...

113.111**3 Posted at: 4 hours ago

#8462 Error no file named pytorch_model.bin, model.safetensors, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory D:/FFFFFFFFFFFFFFFFFFFFFF/win-pyvideotrans-v4.16/mo...

💬 1

[Last reply:5 hours ago] 核心原因：Qwen3-TTS 内置模型的下载不完整，models--Qwen--Qwen3-TTS-12Hz-0.6B-Base/speech_tokenizer/ 目录下缺少模型权重文件（如 model.safetensors），通常是模型下载中断或镜像站返回了不完整文件所致。解决步骤：关闭软件，进入以下目录并删除整个 Base 模型文件夹（清空后重新下载，避免残缺文件被复用）：D:/FFFFF...

104.28**5 Posted at: 5 hours ago

#8461 Unrecognized feature extractor in D:/翻译软件/win-pyvideotrans-v4.16/models/models--Qwen--Qwen3-TTS-12Hz-0.6B-Base\speech_tokenizer. Should have a `feature_extractor_type` key in its p...

💬 1

[Last reply:5 hours ago] 核心原因：Qwen3-TTS 模型文件不完整。speech_tokenizer 子目录缺少 preprocessor_config.json 或 config.json 里的 feature_extractor_type 字段，这是模型自动下载中途失败或文件被浏览器重命名造成的，属模型损坏，非软件 bug。解决方案（按顺序操作）：关闭 pyVideoTrans。删除整个残缺模型文件夹：D:/翻译软...

104.28**7 Posted at: 5 hours ago

#8460 Error no file named pytorch_model.bin, model.safetensors, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory D:/翻译软件/win-pyvideotrans-v4.16/models/models--Qwen-...

💬 1

[Last reply:6 hours ago] 核心原因这是 Qwen3-TTS 模型下载不完整导致的。报错明确指出 models--Qwen--Qwen3-TTS-12Hz-0.6B-Base\speech_tokenizer 目录内缺少模型权重文件（model.safetensors / pytorch_model.bin 等）。Qwen3-TTS 仓库中 speech_tokenizer 是一个独立的子模型目录，需完整下载其权重，国内网络...

104.28**7 Posted at: 6 hours ago

#8459 Error no file named pytorch_model.bin, model.safetensors, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory D:/翻译软件/win-pyvideotrans-v4.16/models/models--Qwen-...

💬 1

[Last reply:6 hours ago] 这是由于 Qwen3-TTS 模型文件未完整下载导致的。目录 models/models--Qwen--Qwen3-TTS-12Hz-0.6B-Base 存在，但其中缺少核心权重文件（model.safetensors），说明上次自动下载失败或中断（该模型位于 huggingface.co，国内网络不稳定极易下载失败）。解决方案1. 删除残缺目录先彻底删除这个不完整的目录，避免残留文件干扰：D:...

104.28**2 Posted at: 6 hours ago

#8458 配音全部失败 :403, message='Invalid response status', url='wss://speech.platform.bing.com/consumer/speech/synthesize/readaloud/edge/v1?TrustedClientToken=6A5AA1D4EAFF4E9FB37E23D68491D6F4...

💬 1

[Last reply:7 hours ago] 这是 Edge-TTS 免费接口的验证逻辑（Sec-MS-GEC）已变更，导致微软服务器返回 403 拒绝连接。你当前使用的是 v4.12 冻结预打包版，该问题已在 v4.16 中修复。解决方案（Windows 预打包版）：前往 https://pyvideotrans.com/downpackage 下载最新完整包，或下载 v4.16 及以上的补丁包。用补丁包内的全部文件和文件夹（尤其是 sp....

106.46**6 Posted at: 7 hours ago

#8457 Whisper.NET setup invalid: Whisper.net.dll not found: D:\pyVideoTrans\deps\Whisper.net.dll; Native directory not found: D:\pyVideoTrans\deps\nativeTraceback (most recent call last)...

💬 1

[Last reply:7 hours ago] The core cause: the Whisper.NET channel is not an out-of-the-box built-in speech recognition channel. It requires you to manually deploy the .NET runtime files. Your D:\pyVideoTrans\deps\ directory co...

91.59**7 Posted at: 7 hours ago

#8456 配音阶段出错 [Edge-TTS(免费)] edge-tts error:target_audio='E:/BaiduNetdiskDownload/tmp/27056/4384184248/家园防线-edgetts-txt-1792914333.9888594.mp3'Traceback (most recent call last):...

💬 1

[Last reply:11 hours ago] 这是网络代理导致的连接失败。日志中显示 proxy_str='http://127.0.0.1:10090'，Edge-TTS 请求走了你填写的代理，而该代理无法连接微软的语音服务（speech.platform.bing.com:443），因此报 ClientConnectorError。Edge-TTS 在国内通常可直接访问，无需代理。解决方案（按优先级尝试）方法一：让 ...

240e**9bb9 Posted at: 11 hours ago

#8455 配音中出错了:C:/PyVideoTrans/win-pyvideotrans-v4.17/tmp/12216/c23116072b/target.wavTraceback (most recent call last):...

💬 1

[Last reply:12 hours ago] 这是最终合成阶段找不到有效的配音文件 target.wav（空文件或未生成）。结合你使用的是 GPT-SoVITS(本地API) 配音渠道，最可能是配音环节实际全部失败但未中断，导致 target.wav 为空/损坏，最终在合成时抛出 "配音中出错了"。排查与解决步骤：确认 GPT-SoVITS 服务是否已启动：必须是启动 api.py（默认 9880 端口），而不是 WebUI（7860 端口）...

106.35**1 Posted at: 12 hours ago

#8454 配音全部失败 :403, message='Invalid response status', url='wss://speech.platform.bing.com/consumer/speech/synthesize/readaloud/edge/v1?TrustedClientToken=6A5AA1D4EAFF4E9FB37E23D68491D6F4...

💬 1

[Last reply:12 hours ago] 这是因为微软 Edge-TTS 免费接口的验证逻辑已变更（并伴随高频请求触发的 IP 限流），导致 WebSocket 握手被拒绝返回 403。你当前使用的是 v4.12，该版本内置的 edge-tts 逻辑已失效。解决方案（按顺序操作）：升级到 v4.16 或更高版本：前往官网下载最新完整包/补丁包覆盖安装。v4.16 已专门修复 Edge-TTS 403 问题。若为源码部署版本，在软件目录执行...

106.46**6 Posted at: 12 hours ago

#8453 配音中出错了:C:/PyVideoTrans/win-pyvideotrans-v4.17/tmp/11268/c23116072b/target.wavTraceback (most recent call last):...

💬 1

[Last reply:13 hours ago] 此报错发生在最后合成阶段，含义是「配音音频文件 target.wav 不存在、为空（0 字节）或无法读取」。最常见原因是 Edge-TTS 免费接口被限流/403，导致大量字幕配音失败，最终合并配音时生成的 target.wav 为空文件；其次是 C 盘剩余空间不足导致写入失败。排查与解决步骤：确认文件状态：打开 C:/PyVideoTrans/win-pyvideotrans-v4.17/tmp...

106.35**1 Posted at: 13 hours ago

#8452 404 Client Error: Not Found for url: https://edge.microsoft.com/translate/auth...

💬 1

[Last reply:17 hours ago] 这是微软免费翻译 API 接口已变更导致的：你使用的 v3.84 版本中，内置的旧接口地址 https://edge.microsoft.com/translate/auth 已失效，因此服务端返回 404；这并非网络或密钥问题。解决方案（任选一种）升级软件（推荐）：微软接口的适配已在 v4.09 修复。请下载最新完整包（2.6GB+，请勿下载 260MB 补丁包），解压覆盖使用；配置文件 vid...

2408**179e Posted at: 17 hours ago

#8451 Traceback (most recent call last): File...

💬 1

[Last reply:21 hours ago] This is caused by an incomplete upgrade overwrite: the safetensors library in the _internal folder is still the old version (0.4.5), while the transformers in the new version requires safetensors>=...

146.212**6 Posted at: 21 hours ago

#8450 model 'qwen3.6' not foundhttp://localhost:11434/v1...

💬 1

[Last reply:21 hours ago] The 404 returned by Ollama indicates that the model name qwen3.6 you filled in does not exist in the local Ollama instance. This is a model-name mismatch, not a pyVideoTrans problem.Solution:Run ollam...

146.212**6 Posted at: 21 hours ago

#8449 You selected LLM error correction and used the DeepSeek channel, but did not fill in the key or api url. Please fill in the key or deselect....

💬 1

[Last reply:21 hours ago] The root cause: the LLM Correction checkbox is enabled, and the LLM correction channel defaults to DeepSeek, but no valid DeepSeek Secret Key (or API URL) has been filled in, so the request cannot be ...

146.212**6 Posted at: 21 hours ago

#8468 配音全部失败 :Edge-TTS HTTP 500 (configured proxy): Invalid response statusall_voices={'en-US-BrianNeural'}:...

#8467 [WinError 32] The process cannot access the file because it is being used by another process: 'D:/EXTRAS/py videotrans/tmp/19308/2d1ad91e61/final_audio_temp.wav'：D:/EXTRAS/py video...

#8466 源码部署本项目，运行uv sync --all-extras，如果已安装，请单独执行uv sync --extra dotnet 安装 pythonnet 模块在那里运行运行uv sync --all-extras...

#8465 Missing dubbing for subtitle 1: I:/dy/dy/pyvideotrans/tmp/24828/ab142ca8eb/0-bbe9c3c86408e686999d4ec304b17b78.wavTraceback (most recent call last):...

#8464 语音识别阶段出错[parakeet日语(内置)] videotrans.configure.excepts.SpeechToTextErrorTraceback (most recent call last):...

#8463 连接被重置，网络可能不稳定Traceback (most recent call last):...

#8462 Error no file named pytorch_model.bin, model.safetensors, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory D:/FFFFFFFFFFFFFFFFFFFFFF/win-pyvideotrans-v4.16/mo...

#8461 Unrecognized feature extractor in D:/翻译软件/win-pyvideotrans-v4.16/models/models--Qwen--Qwen3-TTS-12Hz-0.6B-Base\speech_tokenizer. Should have a `feature_extractor_type` key in its p...

#8460 Error no file named pytorch_model.bin, model.safetensors, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory D:/翻译软件/win-pyvideotrans-v4.16/models/models--Qwen-...

#8459 Error no file named pytorch_model.bin, model.safetensors, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory D:/翻译软件/win-pyvideotrans-v4.16/models/models--Qwen-...

#8458 配音全部失败 :403, message='Invalid response status', url='wss://speech.platform.bing.com/consumer/speech/synthesize/readaloud/edge/v1?TrustedClientToken=6A5AA1D4EAFF4E9FB37E23D68491D6F4...

#8457 Whisper.NET setup invalid: Whisper.net.dll not found: D:\pyVideoTrans\deps\Whisper.net.dll; Native directory not found: D:\pyVideoTrans\deps\nativeTraceback (most recent call last)...

#8456 配音阶段出错 [Edge-TTS(免费)] edge-tts error:target_audio='E:/BaiduNetdiskDownload/tmp/27056/4384184248/家园防线-edgetts-txt-1792914333.9888594.mp3'Traceback (most recent call last):...

#8455 配音中出错了:C:/PyVideoTrans/win-pyvideotrans-v4.17/tmp/12216/c23116072b/target.wavTraceback (most recent call last):...

#8454 配音全部失败 :403, message='Invalid response status', url='wss://speech.platform.bing.com/consumer/speech/synthesize/readaloud/edge/v1?TrustedClientToken=6A5AA1D4EAFF4E9FB37E23D68491D6F4...

#8453 配音中出错了:C:/PyVideoTrans/win-pyvideotrans-v4.17/tmp/11268/c23116072b/target.wavTraceback (most recent call last):...

#8452 404 Client Error: Not Found for url: https://edge.microsoft.com/translate/auth...

#8451 Traceback (most recent call last): File...

#8450 model 'qwen3.6' not foundhttp://localhost:11434/v1...

#8449 You selected LLM error correction and used the DeepSeek channel, but did not fill in the key or api url. Please fill in the key or deselect....

Related resource