{"id":51596625,"url":"https://github.com/TheDeathDragon/LiveTranslate","last_synced_at":"2026-07-11T19:01:20.986Z","repository":{"id":344590918,"uuid":"1182323028","full_name":"TheDeathDragon/LiveTranslate","owner":"TheDeathDragon","description":"Real-time audio translation, captures system audio + mic, runs ASR (Whisper/SenseVoice),   translates via LLM API with streaming display. Perfect for VTubers, livestreamers, and watching foreign content. Windows 实时音频翻译，ASR 语音识别后 LLM 流式翻译显示，适合 VTuber、主播和外语视频观看。","archived":false,"fork":false,"pushed_at":"2026-07-09T16:18:58.000Z","size":6431,"stargazers_count":420,"open_issues_count":3,"forks_count":37,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-07-09T18:12:02.412Z","etag":null,"topics":["asr","funasr","live-translation","real-time-translation","speech-recognition","subtitle-overlay","voice-recognition","vtuber","vtuber-software","vuter-subtitle"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/TheDeathDragon.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-03-15T11:10:24.000Z","updated_at":"2026-07-09T16:20:52.000Z","dependencies_parsed_at":null,"dependency_job_id":"0f7157d1-0df1-4ea3-8616-7e9c04fc4a6b","html_url":"https://github.com/TheDeathDragon/LiveTranslate","commit_stats":null,"previous_names":["thedeathdragon/livetranslate"],"tags_count":3,"template":false,"template_full_name":null,"purl":"pkg:github/TheDeathDragon/LiveTranslate","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TheDeathDragon%2FLiveTranslate","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TheDeathDragon%2FLiveTranslate/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TheDeathDragon%2FLiveTranslate/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TheDeathDragon%2FLiveTranslate/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/TheDeathDragon","download_url":"https://codeload.github.com/TheDeathDragon/LiveTranslate/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TheDeathDragon%2FLiveTranslate/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35372639,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-07-11T02:00:05.354Z","response_time":104,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["asr","funasr","live-translation","real-time-translation","speech-recognition","subtitle-overlay","voice-recognition","vtuber","vtuber-software","vuter-subtitle"],"created_at":"2026-07-11T19:01:17.044Z","updated_at":"2026-07-11T19:01:20.977Z","avatar_url":"https://github.com/TheDeathDragon.png","language":"Python","funding_links":[],"categories":["Subtitle and Localization"],"sub_categories":[],"readme":"# LiveTranslate\n\n**English** | [中文](README_zh.md)\n\nReal-time audio translation for Windows. Captures system audio (WASAPI loopback) and optional microphone input, runs ASR, translates via LLM API, and displays results in a transparent overlay.\n\nWorks with any system audio — videos, livestreams, voice chat. No player modifications needed.\n\n![Python 3.10+](https://img.shields.io/badge/Python-3.10%2B-blue)\n![Windows](https://img.shields.io/badge/Platform-Windows-0078d4)\n![License](https://img.shields.io/badge/License-MIT-green)\n\n## Screenshot\n\n![LiveTranslate](screenshot/en.png)\n\n## Video\n\n[![Install \u0026 Demo](https://img.shields.io/badge/Bilibili-Install%20%26%20Demo-00A1D6?logo=bilibili)](https://www.bilibili.com/video/BV1K2Awz6Euw)\n\n## Features\n\n- **Real-time pipeline**: System audio → VAD → ASR → LLM translation → overlay\n- **Multiple ASR engines**: faster-whisper, SenseVoice, FunASR Nano, Anime-Whisper\n- **Remote ASR**: offload speech recognition to a GPU machine over HTTP — see [REMOTE_ASR.md](REMOTE_ASR.md)\n- **Any OpenAI-compatible API**: DeepSeek, Grok, Qwen, GPT, Ollama, vLLM, etc.\n- **Streaming translation display**: Real-time character-by-character translation output\n- **Per-model settings**: Streaming, structured output (JSON), context history, disable thinking\n- **Microphone mix-in**: Optionally mix microphone input with system audio for ASR\n- **Low-latency VAD**: 32ms chunks + Silero VAD with adaptive silence detection\n- **Transparent overlay**: Always-on-top, click-through, draggable, 14 color themes\n- **CUDA acceleration**: GPU-accelerated ASR inference\n- **Auto model management**: Setup wizard, ModelScope / HuggingFace dual sources\n- **Built-in benchmark**: Compare translation model speed and quality\n\n## Changelog\n\nSee [English Changelog](i18n/CHANGELOG_en.md) | [中文更新日志](i18n/CHANGELOG_zh.md)\n\n## Requirements\n\n- **OS**: Windows 10/11\n- **Python**: 3.10–3.12 (or use the portable build)\n- **GPU** (recommended): NVIDIA + CUDA 12.6 (Blackwell GPUs like RTX 50xx require CUDA 12.8)\n- **Network**: Access to a translation API\n\n## Quick Start\n\n### Portable build (no Python required, recommended for non-developers)\n\nDownload `LiveTranslate-portable-*.zip` from [Releases](https://github.com/TheDeathDragon/LiveTranslate/releases), unzip, and double-click **`start.bat`**. The first run auto-downloads a portable Python 3.12 and installs GPU-aware dependencies — no Python installation needed.\n\n### From source\n\n```bash\ngit clone https://github.com/TheDeathDragon/LiveTranslate.git\ncd LiveTranslate\n```\n\nDouble-click **`install.bat`** — the installer will:\n1. Detect Python 3.10–3.12 (auto-install via winget if missing)\n2. Create a virtual environment\n3. Auto-detect NVIDIA GPU and let you choose CUDA / CPU PyTorch\n4. Install all dependencies\n\nThen double-click **`start.bat`** to launch.\n\nTo update, double-click **`update.bat`** — it will pull the latest code and update dependencies (auto-installs Git via winget if missing).\n\n\u003cdetails\u003e\n\u003csummary\u003eManual install\u003c/summary\u003e\n\n```bash\npython -m venv .venv\n.venv\\Scripts\\activate\n\n# PyTorch (choose one)\npip install torch torchaudio --index-url https://download.pytorch.org/whl/cu126  # CUDA\npip install torch torchaudio --index-url https://download.pytorch.org/whl/cu128  # CUDA (RTX 50xx)\npip install torch torchaudio --index-url https://download.pytorch.org/whl/cpu    # CPU only\n\n# Dependencies\npip install -r requirements.txt\npip install funasr --no-deps\n\n# Launch\n.venv\\Scripts\\python.exe main.py\n```\n\n\u003e FunASR uses `--no-deps` because `editdistance` requires a C++ compiler. `editdistance-s` in `requirements.txt` is a pure-Python drop-in replacement.\n\n\u003c/details\u003e\n\n## First Launch\n\n1. Setup wizard appears — choose download source (ModelScope / HuggingFace) and cache path\n2. Silero VAD + SenseVoice models download automatically (~1GB)\n3. Main UI appears when ready\n\n## Translation API\n\nSettings → Translation tab:\n\n| Parameter | Example |\n|-----------|---------|\n| API Base | `https://api.deepseek.com/v1` |\n| API Key | Your key |\n| Model | `deepseek-chat` |\n| Proxy | `none` / `system` / custom URL |\n\n## Architecture\n\n```\nAudio (WASAPI 32ms) → VAD (Silero) → ASR → LLM Translation → Overlay\n         ↑ optional mic mix-in\n```\n\n```\nmain.py                 Entry point \u0026 pipeline\n├── audio_capture.py    WASAPI loopback + mic mix-in\n├── vad_processor.py    Silero VAD\n├── asr_engine.py       faster-whisper backend\n├── asr_funasr.py       Unified FunASR model selector backend\n├── asr_sensevoice.py   SenseVoice backend\n├── asr_funasr_nano.py  FunASR Nano backend\n├── asr_anime_whisper.py Anime-Whisper backend (ja anime/galgame)\n├── asr_remote.py        Remote Whisper client (→ asr_server.py, see REMOTE_ASR.md)\n├── translator.py       OpenAI-compatible client (streaming, JSON schema, context)\n├── model_manager.py    Model download \u0026 cache\n├── subtitle_overlay.py PyQt6 overlay\n├── control_panel.py    Settings UI (7 tabs)\n├── dialogs.py          Wizard, download \u0026 model config dialogs\n└── benchmark.py        Translation benchmark\n```\n\n## Acknowledgements\n\n- [faster-whisper](https://github.com/SYSTRAN/faster-whisper) — Whisper inference via CTranslate2\n- [FunASR](https://github.com/modelscope/FunASR) — SenseVoice / Fun-ASR-Nano\n- [Anime-Whisper](https://huggingface.co/litagin/anime-whisper) — Japanese anime/galgame ASR\n- [Silero VAD](https://github.com/snakers4/silero-vad) — Voice activity detection\n\n## Star History\n\n\u003ca href=\"https://www.star-history.com/?repos=TheDeathDragon%2FLiveTranslate\u0026type=date\u0026legend=top-left\"\u003e\n \u003cpicture\u003e\n   \u003csource media=\"(prefers-color-scheme: dark)\" srcset=\"https://api.star-history.com/image?repos=TheDeathDragon/LiveTranslate\u0026type=date\u0026theme=dark\u0026legend=top-left\" /\u003e\n   \u003csource media=\"(prefers-color-scheme: light)\" srcset=\"https://api.star-history.com/image?repos=TheDeathDragon/LiveTranslate\u0026type=date\u0026legend=top-left\" /\u003e\n   \u003cimg alt=\"Star History Chart\" src=\"https://api.star-history.com/image?repos=TheDeathDragon/LiveTranslate\u0026type=date\u0026legend=top-left\" /\u003e\n \u003c/picture\u003e\n\u003c/a\u003e\n\n## License\n\n[MIT License](LICENSE)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FTheDeathDragon%2FLiveTranslate","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FTheDeathDragon%2FLiveTranslate","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FTheDeathDragon%2FLiveTranslate/lists"}