Complete port with 7 pipeline modes powered by Whisper, Qwen3-ASR,
anime-whisper, Kotoba, and ChronosJAV. Runs entirely on CPU (free tier).
First request downloads the model (~1–4 GB) — please be patient.
Pipeline Mode
Sensitivity
Language
Output Format
ChronosJAV — anime-whisper (text gen + VAD alignment). Best for anime/JAV dialogue.
Scene Detection
Speech Segmenter (VAD)
Qwen Pipeline Options
Generator Backend
Input Mode
Transformers Pipeline Options
ASR Backend
HF Model
Content-Specific Recommendations
Content Type
Pipeline
Sensitivity
Anime / JAV Dialogue
anime
aggressive
Drama / Dialogue Heavy
balanced
aggressive
Group Scenes
faster
conservative
Amateur / Homemade
fast
conservative
ASMR / Whisper
fidelity
aggressive
Maximum Accuracy
qwen
balanced
Task Monitor (auto-refreshes every 8 s)
No tasks yet. Upload a file to start.
Pick a completed task, then download its subtitle file.