Advanced Options Reference

In Menu → Tools / Options → Advanced Options, you can customize various parameters for finer control.

【Common】

• Software interface language: Set the software's interface language. Requires a restart to take effect.

• Countdown for single video translation pause: Countdown in seconds for a single video translation.

• Set output directory: Directory to save results (STT, TTS, TransSubtitles). Defaults to the 'output' folder.

• Number of retries after failure: Number of retries after failure

• LLM Correction errors How many subtitles are sent each time: When LLM Correction errors in the LLM large model, the number of subtitles se nt each time is important. A larger value results in better sentence segmentation. Sending all subtitles at once is optimal, but this is limited by the maximum output token and context (max_token). An excessively long input may exceed the AI limit and fail. The default is 20 subtitles.

• AI provider for LLM Correction errors: AI provider for LLM Correction errors

• Disable desktop notifications: Disable desktop notifications for task completion or failure.

• Threads nums for separation: The more threads used for separation of human and background voices, the faster the process, but the more res ources it consumes.

• BGM separation model: Select the model used when separating background noise.

• Translating batches, quantity per batch: When translating in batches, set the number of lines to translate simultaneously in each batch he re.

• Show all parameters?: To avoid confusion caused by too many parameters, most parameters are hidden by default on the main interface. Selec ting this option will switch to displaying all parameters by default.

• Number of CPU tasks[restart]: Process Maximum for CPU

• Number of GPU tasks[restart]: The number of GPU tasks that can be executed simultaneously should be set to 1 unless video memory very larg e

• Force the operation of heavy-duty equipment: Force the operation of heavy-duty equipment; do not tamper with it unless you know what you a re doing.

【Video Output】

• Video output quality control (CRF): Constant Rate Factor (CRF) for video quality. 0=lossless (huge file), 51=low quality (small file).

• Output video compression preset: Controls the encoding speed vs. quality balance (e.g., ultrafast, medium, slow). Faster means larger file s.

• H.264/H.265 encoding: Video codec: libx264 (better compatibility) or libx265 (higher compression).

• Output video format (mp4/mkv): Output video format (mp4/mkv)

• Variable frame rate (vfr)/fixed frame rate (cfr): When there is slow-motion video processing, variable frame rate (VRF) works better, whil e fixed frame rate (CFR) has better compatibility.

• Force software video encoding?: Force software encoding (slower but more compatible). Hardware encoding is preferred by default.

• ffmpeg decode video use cuda: When compositing videos, prioritize hard decoding; it's fast but prone to errors.

• Custom FFmpeg command arguments: Custom FFmpeg command arguments, added before the output file argument.

【ASR Settings】

• Select VAD: Select VAD

• VAD: Speech probability threshold: VAD: Minimum probability for an audio chunk to be considered speech.

• no speech threshold: no speech threshold

• VAD:max speech duration(s): VAD: Maximum duration (s) of a single speech segment before splitting.

• VAD:min speech duration(ms): If a subtitle's duration is less than this value in milliseconds, attempt to merge it into an adjacent subtit le.

• VAD:Min silence duration for split(ms): VAD: Minimum silence duration (ms) to mark the end of a segment.

• The model used for secondary recognition: The model used for secondary recognition (always using the Faster-Whisper channel)

• Recognition(2): max duration(s): Maximum speech duration (seconds) during secondary recognition. Limits the maximum length of a single spe ech segment. Forced segmentation occurs if this length is exceeded. Enter a number in seconds.

• Recognition(2): min duration(ms): Shortest speech duration (milliseconds) during secondary recognition. If a subtitle's duration is less t han this value in milliseconds, attempt to merge it into an adjacent subtitle. Unit: milliseconds.

• Model for speaker separation: The model used for speaker separation. The default is the built-in model, supporting both Chinese and Englis h. Pyannote is optional. If selected, you must have a token from https://huggingface.co and agree to the Pyannote licensing agreement. For details, please visit the URL for a tutorial: https://pvt9.com/shuohuaren

• Your token from huggingface.co: Enter your token from huggingface.co. Otherwise, you cannot use Pyannote speaker separation. For details, please see the tutorial: https://pvt9.com/shuohuaren

• Compute data type: Compute type for faster-whisper (e.g., int8, float16, float32).

• Recognition accuracy (beam_size): Beam size for transcription (1-5). Higher is more accurate but uses more VRAM.

• Recognition accuracy (best_of): Best-of for transcription (1-5). Higher is more accurate but uses more VRAM.

• Enable context awareness: Condition on previous text for better context (uses more GPU, may cause repetition).

• temperature: temperature

• repetition penalty: Increasing this value helps reduce repetitions

• compression ratio threshold: Decrease this value helps reduce repetitions

• hotwords: hotwords

• faster-whisper models: Comma-separated list of model names for faster-whisper modes.

• whisper.cpp models: Comma-separated list of model names for whisper.cpp mode.

• Gemini speech recognition batch slice count: Number of audio slices per request for Gemini recognition. Larger values improve accuracy but increase failure rate.

• Convert Traditional to Simplified Chinese subtitles: Force conversion of recognized Traditional Chinese to Simplified Chinese.

• Remove punctuation at end subtitles?: Remove punctuation at the end of subtitles?

• Cloud API pauses after each recognition/Seconds: The number of seconds the cloud API pauses after each recognition to prevent exceeding th e frequency limit.

【Translation】

• Batch size (lines) for traditional translation: Number of subtitle lines per request for traditional translation.

• Batch size (lines) for AI translation: Number of subtitle lines per request for AI translation.

• Pause (s) after each translation request: Delay (in seconds) between translation requests to prevent rate-limiting.

• Send full SRT format for AI translation: Send full SRT format content when using AI translation.

• AI temperature for translation subtitles: AI models temperature,default is 1.0

• AI ​​translation includes all original subtitles for reference?: The AI ​​translation channel includes all original subtitles for referenc e.

【Dubbing】

• Concurrent dubbing threads: Number of concurrent threads for dubbing.

• Pause (s) after each dubbing request: Delay (in seconds) between dubbing requests to prevent rate-limiting.

• Remove the mute buffer each subtitle audio: Remove the mute buffer before and after each subtitle audio. Selecting this option will improv e audio-visual synchronization, but may make the ending feel rushed.

• Save dubbed audio for each subtitle line: Save the dubbed audio for each individual subtitle line.

• Text Text normalization: Text normalization before dubbing

• The higher concurrent of EdgeTTS: The higher the concurrent voice-over capacity of the EdgeTTS channel, the faster the speed, but rate thr ottling may fail.

• Retries after EdgeTTS failure: Number of retries after EdgeTTS channel failure

• ChatTTS voice timbre value: ChatTTS voice timbre value.

【Alignment】

• Maximum audio speed-up rate: Maximum audio speed-up rate. Default: 100.

• Maximum video slow-down rate: Maximum video slow-down rate. Default: 10 (cannot exceed 10).

• Number of characters per line for CJK: Number of characters per line for Chinese, Japanese, and Korean subtitles; more than this will resu lt in a line break

• Number of words per line for Other: Number of words per line for subtitles in other languages; more than this will result in a line break

【Whisper Prompt】

...