#8615 The voice actor has been cloned, but there is no corresponding reference audio. Please choose a different voice actor.se

105.110**8 Posted at: 1 hour ago

The voice actor has been cloned, but there is no corresponding reference audio. Please choose a different voice actor.
self=[AudiocppTTS]: uuid='5d3213fb51', proxy_str=None, tts_type=25, len=45, language='en', play=False, volume='+0%', pitch='+0Hz', rate='+0%', speed=1.0, has_done=0, wait_sec=1.0, dub_nums=1, error=None, api_url='', is_cuda=False, local_dir=None, is_redubb=False, model_name='', ainame=None, jsondata={'omnivoice': {'type': 'tts', 'file': 'OmniVoice-GGUF/omnivoice-q8_0.gguf', 'url': 'https://huggingface.co/audio-cpp/audio.cpp-gguf/resolve/main/OmniVoice-GGUF/omnivoice-q8_0.gguf?download=true', 'is_reference_text': True, 'is_language': False, 'is_seed': True}, 'qwen3_tts': {'type': 'tts', 'file': 'Qwen3-TTS-12Hz-1.7B-Base-GGUF/qwen3-tts-12hz-1.7b-base-q8_0_v2.gguf', 'url': 'https://huggingface.co/audio-cpp/audio.cpp-gguf/resolve/main/Qwen3-TTS-12Hz-1.7B-Base-GGUF/qwen3-tts-12hz-1.7b-base-q8_0_v2.gguf?download=true', 'support_languages': ['zh', 'en', 'ja', 'ko', 'de', 'fr
......
https://huggingface.co/audio-cpp/audio.cpp-gguf/resolve/main/Irodori-TTS-v4-Small-GGUF/irodori-tts-v4-small-q8_0.gguf?download=true', 'support_languages': ['ja'], 'is_reference_text': False, 'is_language': True, 'is_seed': True}, 'chatterbox': {'type': 'clon', 'file': 'Chatterbox-GGUF/chatterbox-q8_0.gguf', 'url': 'https://huggingface.co/audio-cpp/audio.cpp-gguf/resolve/main/Chatterbox-GGUF/chatterbox-q8_0.gguf?download=true', 'support_languages': ['ar', 'da', 'de', 'el', 'en', 'es', 'fi', 'fr', 'hi', 'it', 'ko', 'ms', 'nl', 'no', 'pl', 'pt', 'sv', 'sw', 'tr'], 'is_reference_text': False, 'is_language': True, 'is_send': True}}, gguf_obj={'type': 'tts', 'file': 'OmniVoice-GGUF/omnivoice-q8_0.gguf', 'url': 'https://huggingface.co/audio-cpp/audio.cpp-gguf/resolve/main/OmniVoice-GGUF/omnivoice-q8_0.gguf?download=true', 'is_reference_text': True, 'is_language': False, 'is_seed': True}

trk=[TransCreate]: uuid='5d3213fb51', proxy_str=None, cfg=[TaskCfgVTT]当前工作模式: 翻译视频 单视频模式
原始输入文件名: E:/ssstik.io_1793038609101.mp4,
输出结果保存到文件夹: E:/_video_out/ssstik.io_1793038609101-mp4,
临时文件夹: E:/pyvideotrans/tmp/7008/5d3213fb51
已选 清理已存在
未启用CUDA加速
STT Service:Whisper.NET, ggml-large-v3-turbo.bin, 发音语言: Simplified Chinese, ,
TranslateSrt:Google Translate (Free),原始语言:Simplified Chinese,目标语言:English, 已选 SendSRT, settings.get('trans_thread')=5, settings.get('aitrans_thread')=40
TTS Service:Audio.cpp(Local), 角色:clone, 配音语言:English, 未选 二次语音识别
音量:+0%, 语速:+0%, 已选 音频加速, 未选 视频慢速
已选 移除每条字幕配音开头和结尾静音缓冲
静音移除力度: default
字幕: Soft Subtitles , precent=15, hasend=False, should_recogn=True, should_trans=True, should_dubbing=True, should_hebing=True, is_copy_video=False, video_codec_num=264, ignore_align=False, is_audio_trans=False, clone_ref='', should_recogn2=False, do_diarize=True
video_duration_ms=117120


=
system:Windows-10-10.0.26200-SP0
version:v4.17
frozen:False
language:en_US
root_dir:E:/pyvideotrans
Python: 3.10.19 (main, Feb 12 2026, 00:37:08) [MSC v.1944 64 bit (AMD64)]

1 Replies

#1 DeepSeek reply at 1 hour ago

The root cause: you selected the clone voice for the Audio.cpp TTS channel. clone does not use a preset voice — for each subtitle line it must cut a reference audio clip from the vocal track of the original video, and then dub with that timbre. In this task the reference audio was not generated at all (clone_ref=''), so it aborted at the dubbing stage with "The voice actor has been cloned, but there is no corresponding reference audio".

Handling, in order:

  1. If you do not need to clone the original timbre (fastest fix): switch Voices to any normal voice in the TTS row of the main window (instead of clone) and re-run. Note: if you changed it to clone manually in the "voice assignment" window of single-video mode, change it back there as well.
  2. If you do need clone, the reference audio must be long enough to cut a valid clip:

    • Open Menu → Tools/Options → Advanced Options → Speech Recognition (ASR)
    • Set Min Speech Duration (ms) to 3000
    • Set Max Speech Duration (s) to 5 to 10
    • Check Clear Output on the main window and re-run (otherwise the existing subtitles and cache are reused, and the parameters do not take effect).
  3. If you want to control the timbre yourself: prepare a 3–10 second mono WAV clip with clear pronunciation and no background noise, open Menu → TTS Settings → Set Reference Audio, and enter it in the format file name#the text spoken in the file, then put the wav in the software directory/f5-tts folder and select that reference in Voices instead of clone.
  4. Also confirm that the original video really contains human speech, and that the first few recognized subtitle lines are not too short (one or two words); otherwise there is physically no material from which to cut a reference clip.

If the above still fails, this specific cause cannot be determined from the current information. Please provide the last 30 lines of the latest log file in the logs/ folder under the software installation directory, together with the Min/Max Speech Duration settings and whether vocal separation and denoise were checked.

Please refer to the related documentation:

Thinking...
Post Your Reply
If you have more than 50 messages, you will no longer receive an automatic reply. Please ask a new question!
Open source and free maintenance is not easy. If this project is helpful to you, please consider making a small donation to help the project continue to maintain and update.

Dondate via ko-fi.com

Related resource