Add WebUi (Adopted from https://github.com/kigner/audio.cpp-webui, add support for Linux)

.gitignore

@@ -28,3 +28,18 @@ __pycache__/
 /*.wav
 /flutter/
 /.cache/
+
+# --- portable bundle: distributed manually, never committed ---
+/audiocpp-portable/
+
+# --- WebUI runtime artifacts: keep the source + empty dirs, drop generated files ---
+/webui/output/*
+!/webui/output/.gitkeep
+/webui/logs/*
+!/webui/logs/.gitkeep
+/webui/third_party/
+/webui/llm_api_key.txt
+# written by the in-UI language picker; per-machine, not a project setting
+/webui/configs/ui_language.json
+# personal voice recording — stays local, repo is public
+/webui/voice/my-record.wav

CMakeLists.txt

@@ -568,6 +568,13 @@ target_link_libraries(engine_runtime PUBLIC ggml)
 target_link_libraries(engine_runtime PRIVATE sentencepiece cjson_vendor yaml_vendor)
 if (ENGINE_ENABLE_OPENMP)
     target_link_libraries(engine_runtime PRIVATE OpenMP::OpenMP_CXX)
+    if (MSVC)
+        # MSVC's default /openmp implements only OpenMP 2.0 and rejects the
+        # '#pragma omp simd' directives in longformer_attention.cpp (error C7660).
+        # /openmp:experimental enables the OpenMP 4.0 SIMD support; it overrides the
+        # /openmp added by OpenMP::OpenMP_CXX above (harmless D9025 override notice).
+        target_compile_options(engine_runtime PRIVATE /openmp:experimental)
+    endif()
 endif()
 
 if (ENGINE_ENABLE_CUDA)

_env.bat

@@ -0,0 +1,47 @@
+@echo off
+REM _env.bat -- shared environment detection for the audio.cpp .bat launchers.
+REM Called (not run) by run_webui.bat / run_server.bat / run_cli_tts.bat. It sets
+REM common variables and deliberately does NOT use setlocal, so they propagate back
+REM to the caller. Change detection logic here only.
+REM
+REM Exports: ROOT BUNDLE WEBUI_DIR PY HAS_CUDA BACKEND SERVER_EXE CLI_EXE GGUF_EXE
+
+REM --- ROOT = this script's directory, without the trailing backslash ---
+set "ROOT=%~dp0"
+if "%ROOT:~-1%"=="\" set "ROOT=%ROOT:~0,-1%"
+
+REM Dev tree: the repo root doubles as the bundle (models\ live under it; the
+REM binaries live under build\). webui.py's own _find_bundle_root handles this.
+set "BUNDLE=%ROOT%"
+set "WEBUI_DIR=%ROOT%\webui"
+
+REM --- Python with the deps (gradio/requests/torch/safetensors/opencc/...) ---
+REM Order: explicit override, project venv (Scripts\ on Windows), then a bundle venv.
+set "PY="
+if defined AUDIOCPP_PYTHON if exist "%AUDIOCPP_PYTHON%" set "PY=%AUDIOCPP_PYTHON%"
+if not defined PY if exist "%ROOT%\venv\Scripts\python.exe" set "PY=%ROOT%\venv\Scripts\python.exe"
+if not defined PY if exist "%ROOT%\venv\python.exe"         set "PY=%ROOT%\venv\python.exe"
+if not defined PY if exist "%BUNDLE%\venv\Scripts\python.exe" set "PY=%BUNDLE%\venv\Scripts\python.exe"
+if not defined PY if exist "%BUNDLE%\venv\python.exe"         set "PY=%BUNDLE%\venv\python.exe"
+
+REM --- CUDA present? (NVIDIA driver installs nvcuda.dll in System32) ---
+set "HAS_CUDA="
+if exist "%SystemRoot%\System32\nvcuda.dll" set "HAS_CUDA=1"
+
+REM --- Locate the from-source binaries. The default Visual Studio generator nests
+REM them in build\bin\Release (multi-config); Ninja/Makefiles use build\bin. ---
+set "BIN="
+if exist "%ROOT%\build\bin\Release\audiocpp_server.exe" set "BIN=%ROOT%\build\bin\Release"
+if not defined BIN if exist "%ROOT%\build\bin\audiocpp_server.exe" set "BIN=%ROOT%\build\bin"
+if defined BIN set "SERVER_EXE=%BIN%\audiocpp_server.exe"
+if defined BIN set "CLI_EXE=%BIN%\audiocpp_cli.exe"
+if defined BIN set "GGUF_EXE=%BIN%\audiocpp_gguf.exe"
+
+REM --- BACKEND: read the actual build's GGML_CUDA flag from its CMakeCache, so we
+REM never advertise a GPU backend a CPU-only build can't serve. cuda when ON, else cpu. ---
+set "BACKEND=cpu"
+if exist "%ROOT%\build\CMakeCache.txt" (
+    for /f "tokens=2 delims==" %%A in ('findstr /b /c:"GGML_CUDA:BOOL" "%ROOT%\build\CMakeCache.txt" 2^>nul') do (
+        if /I "%%A"=="ON" set "BACKEND=cuda"
+    )
+)

requirements.txt

@@ -0,0 +1,87 @@
+# audio.cpp -- unified Python requirements (webui + SpeakType + tools)
+# Frozen from the project venv on 2026-07-15.
+# One env covers every Python layer of the project:
+#   webui/     gradio UI + realtime pipeline (gradio, numpy, requests; torch for silero VAD)
+#   SpeakType/ voice dictation demo (sounddevice, pywebview, pywin32, pyperclip; torch for silero VAD)
+#   tools/     model_manager etc. (requests, huggingface-hub, safetensors, tqdm)
+# The portable bundle ships this same env pre-installed as audiocpp-portable\venv.
+# Windows-only wheels (pywin32 and the pythonnet/pywebview desktop stack, used by
+# SpeakType) carry a sys_platform marker so this file also installs cleanly on Linux.
+# Regenerate:  venv\Scripts\python.exe -m pip freeze > requirements.txt
+#annotated-doc==0.0.4
+annotated-types==0.7.0
+anyio==4.14.1
+bottle==0.13.4
+brotli==1.2.0
+certifi==2026.6.17
+cffi==2.1.0
+charset-normalizer==3.4.7
+click==8.4.2
+clr_loader==0.3.1; sys_platform == "win32"
+colorama==0.4.6
+fastapi==0.138.2
+filelock==3.29.4
+fsspec==2026.6.0
+gradio==6.19.0
+gradio_client==2.5.0
+groovy==0.1.2
+h11==0.16.0
+hf-gradio==0.4.1
+hf-xet==1.5.1
+httpcore==1.0.9
+httptools==0.8.0
+httpx==0.28.1
+huggingface_hub==1.21.0
+idna==3.18
+iniconfig==2.3.0
+Jinja2==3.1.6
+markdown-it-py==4.2.0
+MarkupSafe==3.0.3
+mdurl==0.1.2
+mpmath==1.3.0
+networkx==3.6.1
+numpy==2.4.6
+opencc-python-reimplemented==0.1.7
+orjson==3.11.9
+packaging==26.2
+pandas==3.0.3
+pillow==12.2.0
+pluggy==1.6.0
+proxy_tools==0.1.0; sys_platform == "win32"
+pycparser==3.0
+pydantic==2.13.4
+pydantic_core==2.46.4
+pydub==0.25.1
+Pygments==2.20.0
+pyperclip==1.11.0
+pytest==9.1.1
+python-dateutil==2.9.0.post0
+python-dotenv==1.2.2
+python-multipart==0.0.32
+pythonnet==3.1.0; sys_platform == "win32"
+pytz==2026.2
+pywebview==6.2.1; sys_platform == "win32"
+pywin32==312; sys_platform == "win32"
+PyYAML==6.0.3
+requests==2.34.2
+rich==15.0.0
+safehttpx==0.1.7
+safetensors==0.8.0
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.17.0
+sounddevice==0.5.5
+starlette==1.3.1
+sympy==1.14.0
+tomlkit==0.14.0
+torch==2.12.1
+torchaudio==2.11.0
+tqdm==4.68.3
+typer==0.25.1
+typing-inspection==0.4.2
+typing_extensions==4.15.0
+tzdata==2026.2
+urllib3==2.7.0
+uvicorn==0.49.0
+watchfiles==1.2.0
+websockets==16.0

run_webui.bat

@@ -0,0 +1,32 @@
+@echo off
+setlocal
+chcp 65001 >nul
+cd /d "%~dp0"
+call "%~dp0_env.bat"
+
+REM _env.bat auto-detected BACKEND (cuda|cpu) from the NVIDIA driver + bundled exes;
+REM hand it to webui.py unless the user already chose via AUDIOCPP_BACKEND.
+if not defined AUDIOCPP_BACKEND (
+  if /I "%BACKEND%"=="cuda" ( set "AUDIOCPP_BACKEND=gpu" ) else ( set "AUDIOCPP_BACKEND=cpu" )
+)
+
+REM Python (with gradio/requests/torch/safetensors/...) is located by _env.bat (PY).
+if not exist "%PY%" (
+  echo [run_webui] no Python with deps found. Looked for:
+  echo   %BUNDLE%\venv\python.exe                  ^(bundle venv^)
+  echo   %ROOT%\venv\python.exe                      ^(root venv^)
+  echo   %ROOT%\venv\Scripts\python.exe              ^(project venv^)
+  echo Install into one of them: gradio requests torch safetensors pyyaml huggingface_hub
+  pause
+  exit /b 1
+)
+echo [run_webui] python: %PY%
+
+echo [run_webui] the WebUI starts/switches audiocpp_server on demand
+echo [run_webui]   pick a model in the UI and click "load" (no need to run run_server.bat)
+echo [run_webui]   backend: %AUDIOCPP_BACKEND%  (auto-detected; override with AUDIOCPP_BACKEND=gpu or cpu)
+echo [run_webui] UI -^> http://127.0.0.1:7860
+"%PY%" "%WEBUI_DIR%\webui.py"
+
+endlocal
+pause

run_webui.sh

@@ -0,0 +1,35 @@
+#!/usr/bin/env bash
+# Launch the audio.cpp WebUI on Linux/macOS (POSIX counterpart of run_webui.bat).
+#
+# The WebUI starts/switches audiocpp_server on demand — pick a model in the UI and
+# click load; no need to start a server separately. Backend (cuda|cpu) is auto-detected
+# by webui.py from nvidia-smi and the available build; override with AUDIOCPP_BACKEND=gpu|cpu.
+# UI language: English by default, with 中文 / 中文繁體 selectable from the picker in the
+# UI. That pick is saved to webui/configs/ui_language.json and wins on later runs, so
+# AUDIOCPP_LANG (en|zh|zh-Hant) only sets the default before anything has been picked.
+set -euo pipefail
+
+ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+WEBUI_DIR="$ROOT/webui"
+
+# Locate a Python that has the deps (gradio/requests/torch/safetensors/opencc/...).
+PY=""
+for cand in \
+    "${AUDIOCPP_PYTHON:-}" \
+    "$ROOT/venv/bin/python" \
+    "$ROOT/.venv/bin/python" \
+    "$(command -v python3 || true)" \
+    "$(command -v python || true)"; do
+    if [ -n "$cand" ] && [ -x "$cand" ]; then PY="$cand"; break; fi
+done
+
+if [ -z "$PY" ]; then
+    echo "[run_webui] no Python found. Create a venv and install deps:" >&2
+    echo "  python3 -m venv venv && ./venv/bin/pip install -r requirements.txt" >&2
+    exit 1
+fi
+
+echo "[run_webui] python: $PY"
+echo "[run_webui] backend: ${AUDIOCPP_BACKEND:-auto}  language: ${AUDIOCPP_LANG:-en (unless already picked in the UI)}"
+echo "[run_webui] UI -> http://127.0.0.1:7860"
+exec "$PY" "$WEBUI_DIR/webui.py"