From ed7bdda0001e231724c5af40bc329137e7ca7e2e Mon Sep 17 00:00:00 2001
From: michelia <michelia@seal.io>
Date: Fri, 22 Nov 2024 09:58:01 +0800
Subject: [PATCH] refactor: rename speech-box to vox-box

---
 .flake8                                       |  2 +-
 hack/build.sh                                 | 28 +++++++++----------
 hack/ci.sh                                    |  4 +--
 hack/install.sh                               |  6 ++--
 hack/lib/init.sh                              |  4 +--
 hack/lib/log.sh                               | 20 ++++++-------
 hack/lib/util.sh                              | 12 ++++----
 hack/lib/version.sh                           |  2 +-
 hack/lint.sh                                  |  8 +++---
 hack/test.sh                                  |  4 +--
 hack/windows/build.ps1                        |  4 +--
 hack/windows/install.ps1                      |  2 +-
 hack/windows/lint.ps1                         |  2 +-
 pyproject.toml                                |  6 ++--
 {speech_box => vox_box}/__init__.py           |  0
 {speech_box => vox_box}/backends/stt/base.py  |  2 +-
 .../backends/stt/faster_whisper.py            |  8 +++---
 .../backends/stt/funasr.py                    |  8 +++---
 {speech_box => vox_box}/backends/tts/bark.py  | 10 +++----
 {speech_box => vox_box}/backends/tts/base.py  |  4 +--
 .../backends/tts/cosyvoice.py                 | 10 +++----
 {speech_box => vox_box}/cmd/__init__.py       |  0
 {speech_box => vox_box}/cmd/start.py          | 14 +++++-----
 {speech_box => vox_box}/cmd/version.py        |  2 +-
 {speech_box => vox_box}/config/__init__.py    |  0
 {speech_box => vox_box}/config/config.py      |  2 +-
 .../downloader/downloaders.py                 |  2 +-
 {speech_box => vox_box}/downloader/hub.py     |  0
 {speech_box => vox_box}/elstimator/bark.py    |  8 +++---
 {speech_box => vox_box}/elstimator/base.py    |  2 +-
 .../elstimator/cosyvoice.py                   |  8 +++---
 .../elstimator/estimate.py                    | 14 +++++-----
 .../elstimator/faster_whisper.py              | 10 +++----
 {speech_box => vox_box}/elstimator/funasr.py  |  8 +++---
 {speech_box => vox_box}/logging.py            |  0
 {speech_box => vox_box}/main.py               |  4 +--
 {speech_box => vox_box}/server/app.py         |  6 ++--
 {speech_box => vox_box}/server/model.py       | 18 ++++++------
 {speech_box => vox_box}/server/routers.py     |  6 ++--
 {speech_box => vox_box}/server/server.py      |  6 ++--
 .../utils/compat_importlib.py                 |  0
 {speech_box => vox_box}/utils/ffmpeg.py       |  0
 {speech_box => vox_box}/utils/file.py         |  0
 {speech_box => vox_box}/utils/log.py          |  0
 {speech_box => vox_box}/utils/model.py        |  4 +--
 45 files changed, 130 insertions(+), 130 deletions(-)
 rename {speech_box => vox_box}/__init__.py (100%)
 rename {speech_box => vox_box}/backends/stt/base.py (93%)
 rename {speech_box => vox_box}/backends/stt/faster_whisper.py (95%)
 rename {speech_box => vox_box}/backends/stt/funasr.py (93%)
 rename {speech_box => vox_box}/backends/tts/bark.py (91%)
 rename {speech_box => vox_box}/backends/tts/base.py (87%)
 rename {speech_box => vox_box}/backends/tts/cosyvoice.py (91%)
 rename {speech_box => vox_box}/cmd/__init__.py (100%)
 rename {speech_box => vox_box}/cmd/start.py (92%)
 rename {speech_box => vox_box}/cmd/version.py (91%)
 rename {speech_box => vox_box}/config/__init__.py (100%)
 rename {speech_box => vox_box}/config/config.py (93%)
 rename {speech_box => vox_box}/downloader/downloaders.py (99%)
 rename {speech_box => vox_box}/downloader/hub.py (100%)
 rename {speech_box => vox_box}/elstimator/bark.py (92%)
 rename {speech_box => vox_box}/elstimator/base.py (83%)
 rename {speech_box => vox_box}/elstimator/cosyvoice.py (89%)
 rename {speech_box => vox_box}/elstimator/estimate.py (58%)
 rename {speech_box => vox_box}/elstimator/faster_whisper.py (93%)
 rename {speech_box => vox_box}/elstimator/funasr.py (92%)
 rename {speech_box => vox_box}/logging.py (100%)
 rename {speech_box => vox_box}/main.py (88%)
 rename {speech_box => vox_box}/server/app.py (86%)
 rename {speech_box => vox_box}/server/model.py (80%)
 rename {speech_box => vox_box}/server/routers.py (96%)
 rename {speech_box => vox_box}/server/server.py (86%)
 rename {speech_box => vox_box}/utils/compat_importlib.py (100%)
 rename {speech_box => vox_box}/utils/ffmpeg.py (100%)
 rename {speech_box => vox_box}/utils/file.py (100%)
 rename {speech_box => vox_box}/utils/log.py (100%)
 rename {speech_box => vox_box}/utils/model.py (81%)

diff --git a/.flake8 b/.flake8
index 1571611..2b47343 100644
--- a/.flake8
+++ b/.flake8
@@ -11,4 +11,4 @@ exclude =
     .venv,
     .pytest_cache,
     .mypy_cache
-    speech_box/third_party
+    vox_box/third_party
diff --git a/hack/build.sh b/hack/build.sh
index e6252c0..65a3bfd 100755
--- a/hack/build.sh
+++ b/hack/build.sh
@@ -8,9 +8,9 @@ ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd -P)"
 source "${ROOT_DIR}/hack/lib/init.sh"
 
 function build() {
-  if speech_box::util::is_darwin; then
+  if vox_box::util::is_darwin; then
     build_platform "macosx_11_0_universal2"
-  elif speech_box::util::is_linux; then
+  elif vox_box::util::is_linux; then
     # This is a temporary workaround to make the wheel files different.
     echo >> "${ROOT_DIR}/README.md"
     build_platform "manylinux2014_x86_64"
@@ -18,7 +18,7 @@ function build() {
     build_platform "manylinux2014_aarch64"
     # Remove the extra newline.
     # shellcheck disable=SC2016
-    speech_box::util::sed '${/^$/d;}' "${ROOT_DIR}/README.md"
+    vox_box::util::sed '${/^$/d;}' "${ROOT_DIR}/README.md"
   fi
 }
 
@@ -26,7 +26,7 @@ function build() {
 function build_platform() {
   platform="${1:-}"
   if [ -z "$platform" ]; then
-    speech_box::log::fatal "undefined platform to build"
+    vox_box::log::fatal "undefined platform to build"
   fi
 
   poetry build
@@ -34,7 +34,7 @@ function build_platform() {
   dist_dir="$ROOT_DIR/dist"
   whl_files=$(find "$dist_dir" -name "*.whl")
   if [ -z "$whl_files" ]; then
-      speech_box::log::fatal "no wheel files found in $dist_dir"
+      vox_box::log::fatal "no wheel files found in $dist_dir"
   fi
 
   for whl_file in $whl_files; do
@@ -42,7 +42,7 @@ function build_platform() {
           original_name=$(basename "$whl_file")
           new_name="${original_name/any/$platform}"
           mv -f "$whl_file" "$dist_dir/$new_name"
-          speech_box::log::info "renamed $original_name to $new_name"
+          vox_box::log::info "renamed $original_name to $new_name"
       fi
   done
 }
@@ -52,23 +52,23 @@ function prepare_dependencies() {
 }
 
 function set_version() {  
-  local version_file="${ROOT_DIR}/speech_box/__init__.py"
+  local version_file="${ROOT_DIR}/vox_box/__init__.py"
   local git_commit="${GIT_COMMIT:-HEAD}"
   local git_commit_short="${git_commit:0:7}"
 
-  speech_box::log::info "setting version to $GIT_VERSION"
-  speech_box::log::info "setting git commit to $git_commit_short"
+  vox_box::log::info "setting version to $GIT_VERSION"
+  vox_box::log::info "setting git commit to $git_commit_short"
 
   # Replace the __version__ variable in the __init__.py file
-  speech_box::util::sed "s/__version__ = .*/__version__ = '${GIT_VERSION}'/" "${version_file}"
-  speech_box::util::sed "s/__git_commit__ = .*/__git_commit__ = '${git_commit_short}'/" "${version_file}"
+  vox_box::util::sed "s/__version__ = .*/__version__ = '${GIT_VERSION}'/" "${version_file}"
+  vox_box::util::sed "s/__git_commit__ = .*/__git_commit__ = '${git_commit_short}'/" "${version_file}"
 
   # Update the poetry version
   poetry version "${GIT_VERSION}"
 }
 
 function restore_version_file() {
-  local version_file="${ROOT_DIR}/speech_box/__init__.py"
+  local version_file="${ROOT_DIR}/vox_box/__init__.py"
   git checkout -- "${version_file}"
 }
 
@@ -76,9 +76,9 @@ function restore_version_file() {
 # main
 #
 
-speech_box::log::info "+++ BUILD +++"
+vox_box::log::info "+++ BUILD +++"
 prepare_dependencies
 set_version
 build
 restore_version_file
-speech_box::log::info "--- BUILD ---"
+vox_box::log::info "--- BUILD ---"
diff --git a/hack/ci.sh b/hack/ci.sh
index 964cafa..e0b4ceb 100755
--- a/hack/ci.sh
+++ b/hack/ci.sh
@@ -18,6 +18,6 @@ function ci() {
 # main
 #
 
-speech_box::log::info "+++ CI +++"
+vox_box::log::info "+++ CI +++"
 ci "$@"
-speech_box::log::info "--- CI ---"
+vox_box::log::info "--- CI ---"
diff --git a/hack/install.sh b/hack/install.sh
index 69abcf3..3bf8b0b 100755
--- a/hack/install.sh
+++ b/hack/install.sh
@@ -13,7 +13,7 @@ source "${ROOT_DIR}/hack/lib/init.sh"
 
 function download_deps() {
   git submodule update --init --recursive
-  rm -rf "${ROOT_DIR}/speech_box/third_party/CosyVoice/third_party/Matcha-TTS/data"
+  rm -rf "${ROOT_DIR}/vox_box/third_party/CosyVoice/third_party/Matcha-TTS/data"
   
   pip install poetry==1.8.3 pre-commit==4.0.1
   poetry install  
@@ -24,6 +24,6 @@ function download_deps() {
 # main
 #
 
-speech_box::log::info "+++ DEPENDENCIES +++"
+vox_box::log::info "+++ DEPENDENCIES +++"
 download_deps
-speech_box::log::info "--- DEPENDENCIES ---"
+vox_box::log::info "--- DEPENDENCIES ---"
diff --git a/hack/lib/init.sh b/hack/lib/init.sh
index 6594392..0d85340 100755
--- a/hack/lib/init.sh
+++ b/hack/lib/init.sh
@@ -19,5 +19,5 @@ for file in "${ROOT_DIR}/hack/lib/"*; do
   fi
 done
 
-speech_box::log::install_errexit
-speech_box::version::get_version_vars
+vox_box::log::install_errexit
+vox_box::version::get_version_vars
diff --git a/hack/lib/log.sh b/hack/lib/log.sh
index ccba323..79b33a2 100755
--- a/hack/lib/log.sh
+++ b/hack/lib/log.sh
@@ -14,7 +14,7 @@ log_level="${LOG_LEVEL:-"debug"}"
 log_colorful="${LOG_COLORFUL:-"true"}"
 
 # Handler for when we exit automatically on an error.
-speech_box::log::errexit() {
+vox_box::log::errexit() {
   local err="${PIPESTATUS[*]}"
 
   # if the shell we are in doesn't have errexit set (common in subshells) then
@@ -22,13 +22,13 @@ speech_box::log::errexit() {
   set +o | grep -qe "-o errexit" || return
 
   set +o xtrace
-  speech_box::log::panic "${BASH_SOURCE[1]}:${BASH_LINENO[0]} '${BASH_COMMAND}' exited with status ${err}" "${1:-1}"
+  vox_box::log::panic "${BASH_SOURCE[1]}:${BASH_LINENO[0]} '${BASH_COMMAND}' exited with status ${err}" "${1:-1}"
 }
 
-speech_box::log::install_errexit() {
+vox_box::log::install_errexit() {
   # trap ERR to provide an error handler whenever a command exits nonzero, this
   # is a more verbose version of set -o errexit
-  trap 'speech_box::log::errexit' ERR
+  trap 'vox_box::log::errexit' ERR
 
   # setting errtrace allows our ERR trap handler to be propagated to functions,
   # expansions and subshells
@@ -36,7 +36,7 @@ speech_box::log::install_errexit() {
 }
 
 # Debug level logging.
-speech_box::log::debug() {
+vox_box::log::debug() {
   [[ ${log_level} == "debug" ]] || return 0
   local message="${2:-}"
 
@@ -50,7 +50,7 @@ speech_box::log::debug() {
 }
 
 # Info level logging.
-speech_box::log::info() {
+vox_box::log::info() {
   [[ ${log_level} == "debug" ]] || [[ ${log_level} == "info" ]] || return 0
   local message="${2:-}"
 
@@ -68,7 +68,7 @@ speech_box::log::info() {
 }
 
 # Warn level logging.
-speech_box::log::warn() {
+vox_box::log::warn() {
   local message="${2:-}"
 
   local timestamp
@@ -85,7 +85,7 @@ speech_box::log::warn() {
 }
 
 # Error level logging, log an error but keep going, don't dump the stack or exit.
-speech_box::log::error() {
+vox_box::log::error() {
   local message="${2:-}"
 
   local timestamp
@@ -102,7 +102,7 @@ speech_box::log::error() {
 }
 
 # Fatal level logging, log an error but exit with 1, don't dump the stack or exit.
-speech_box::log::fatal() {
+vox_box::log::fatal() {
   local message="${2:-}"
 
   local timestamp
@@ -125,7 +125,7 @@ speech_box::log::fatal() {
 #   $1 Message to log with the error
 #   $2 The error code to return
 #   $3 The number of stack frames to skip when printing.
-speech_box::log::panic() {
+vox_box::log::panic() {
   local message="${1:-}"
   local code="${2:-1}"
 
diff --git a/hack/lib/util.sh b/hack/lib/util.sh
index a43f7b9..b71fef5 100644
--- a/hack/lib/util.sh
+++ b/hack/lib/util.sh
@@ -1,14 +1,14 @@
 #!/usr/bin/env bash
 
 
-function speech_box::util::sed() {
+function vox_box::util::sed() {
   if ! sed -i "$@" >/dev/null 2>&1; then
     # back off none GNU sed
     sed -i "" "$@"
   fi
 }
 
-function speech_box::util::get_os_name() {
+function vox_box::util::get_os_name() {
   # Support overriding by BUILD_OS for cross-building
   local os_name="${BUILD_OS:-}"
   if [[ -n "$os_name" ]]; then
@@ -18,10 +18,10 @@ function speech_box::util::get_os_name() {
   fi
 }
 
-function speech_box::util::is_darwin() {
-  [[ "$(speech_box::util::get_os_name)" == "darwin" ]]
+function vox_box::util::is_darwin() {
+  [[ "$(vox_box::util::get_os_name)" == "darwin" ]]
 }
 
-function speech_box::util::is_linux() {
-  [[ "$(speech_box::util::get_os_name)" == "linux" ]]
+function vox_box::util::is_linux() {
+  [[ "$(vox_box::util::get_os_name)" == "linux" ]]
 }
diff --git a/hack/lib/version.sh b/hack/lib/version.sh
index 3ac62a3..263ba8f 100755
--- a/hack/lib/version.sh
+++ b/hack/lib/version.sh
@@ -18,7 +18,7 @@
 #                       it can be specified via "VERSION".
 #        BUILD_DATE  -  The build date of the version.
 
-function speech_box::version::get_version_vars() {
+function vox_box::version::get_version_vars() {
   #shellcheck disable=SC2034
   BUILD_DATE=$(date -u '+%Y-%m-%dT%H:%M:%SZ')
   GIT_TREE_STATE="unknown"
diff --git a/hack/lint.sh b/hack/lint.sh
index 699bc11..1cdccb8 100755
--- a/hack/lint.sh
+++ b/hack/lint.sh
@@ -10,7 +10,7 @@ source "${ROOT_DIR}/hack/lib/init.sh"
 function lint() {
   local path="$1"
 
-  speech_box::log::info "linting ${path}"
+  vox_box::log::info "linting ${path}"
   pre-commit run --all-files
 }
 
@@ -18,6 +18,6 @@ function lint() {
 # main
 #
 
-speech_box::log::info "+++ LINT +++"
-lint "speech_box"
-speech_box::log::info "--- LINT ---"
+vox_box::log::info "+++ LINT +++"
+lint "vox_box"
+vox_box::log::info "--- LINT ---"
diff --git a/hack/test.sh b/hack/test.sh
index 85eb703..fd39262 100755
--- a/hack/test.sh
+++ b/hack/test.sh
@@ -15,6 +15,6 @@ function test() {
 # main
 #
 
-speech_box::log::info "+++ TEST +++"
+vox_box::log::info "+++ TEST +++"
 test
-speech_box::log::info "--- TEST ---"
+vox_box::log::info "--- TEST ---"
diff --git a/hack/windows/build.ps1 b/hack/windows/build.ps1
index 0c714c8..c94a84b 100644
--- a/hack/windows/build.ps1
+++ b/hack/windows/build.ps1
@@ -36,7 +36,7 @@ function Install-Dependency {
 }
 
 function Set-Version {
-    $versionFile = Join-Path -Path $ROOT_DIR -ChildPath "speech_box\__init__.py"
+    $versionFile = Join-Path -Path $ROOT_DIR -ChildPath "vox_box\__init__.py"
     $version = if ($null -ne $global:GIT_VERSION) { $global:GIT_VERSION } else { "0.0.0" }
     $gitCommit = if ($null -ne $global:GIT_COMMIT) { $global:GIT_COMMIT } else { "HEAD" }
     $gitCommitShort = $gitCommit.Substring(0, [Math]::Min(7, $gitCommit.Length))
@@ -55,7 +55,7 @@ function Set-Version {
 }
 
 function Restore-Version-File {
-    $versionFile = Join-Path -Path $ROOT_DIR -ChildPath "speech_box\__init__.py"
+    $versionFile = Join-Path -Path $ROOT_DIR -ChildPath "vox_box\__init__.py"
 
     git checkout -- $versionFile
     if ($LASTEXITCODE -ne 0) {
diff --git a/hack/windows/install.ps1 b/hack/windows/install.ps1
index 18a5340..54f834e 100644
--- a/hack/windows/install.ps1
+++ b/hack/windows/install.ps1
@@ -9,7 +9,7 @@ $ROOT_DIR = Split-Path -Path $MyInvocation.MyCommand.Definition -Parent | Split-
 
 function Install-Dependency {
     git submodule update --init --recursive
-    Remove-Item -Recurse -Force "$ROOT_DIR/speech_box/third_party/CosyVoice/third_party/Matcha-TTS/data"
+    Remove-Item -Recurse -Force "$ROOT_DIR/vox_box/third_party/CosyVoice/third_party/Matcha-TTS/data"
 
     pip install poetry==1.8.3 pre-commit==4.0.1
     if ($LASTEXITCODE -ne 0) {
diff --git a/hack/windows/lint.ps1 b/hack/windows/lint.ps1
index 57053d0..28809b6 100644
--- a/hack/windows/lint.ps1
+++ b/hack/windows/lint.ps1
@@ -55,7 +55,7 @@ function Lint {
 SpeechBox.Log.Info "+++ LINT +++"
 try {
     Get-PSScriptAnalyzer
-    Lint "speech_box"
+    Lint "vox_box"
 }
 catch {
     SpeechBox.Log.Fatal "failed to lint: $($_.Exception.Message)"
diff --git a/pyproject.toml b/pyproject.toml
index a83a60f..6bb57d2 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,7 +1,7 @@
 [tool.poetry]
-name = "speech_box"
+name = "vox_box"
 version = "0.0.0"
-description = "Speech box"
+description = "Vox box"
 authors = ["GPUStack Authors <contact@gpustack.ai>"]
 readme = "README.md"
 
@@ -87,4 +87,4 @@ requires = ["poetry-core"]
 build-backend = "poetry.core.masonry.api"
 
 [tool.poetry.scripts]
-speech-box = "speech_box.main:main"
+vox-box = "vox_box.main:main"
diff --git a/speech_box/__init__.py b/vox_box/__init__.py
similarity index 100%
rename from speech_box/__init__.py
rename to vox_box/__init__.py
diff --git a/speech_box/backends/stt/base.py b/vox_box/backends/stt/base.py
similarity index 93%
rename from speech_box/backends/stt/base.py
rename to vox_box/backends/stt/base.py
index ae8723d..48d5fa9 100644
--- a/speech_box/backends/stt/base.py
+++ b/vox_box/backends/stt/base.py
@@ -1,6 +1,6 @@
 from abc import ABC, abstractmethod
 from typing import Dict, List, Optional
-from speech_box.config.config import Config
+from vox_box.config.config import Config
 
 
 class STTBackend(ABC):
diff --git a/speech_box/backends/stt/faster_whisper.py b/vox_box/backends/stt/faster_whisper.py
similarity index 95%
rename from speech_box/backends/stt/faster_whisper.py
rename to vox_box/backends/stt/faster_whisper.py
index ae25139..7f80ae3 100644
--- a/speech_box/backends/stt/faster_whisper.py
+++ b/vox_box/backends/stt/faster_whisper.py
@@ -6,10 +6,10 @@
 from typing import Dict, List, Optional
 import tempfile
 import io
-from speech_box.backends.stt.base import STTBackend
-from speech_box.config.config import BackendEnum, Config, TaskTypeEnum
-from speech_box.utils.log import log_method
-from speech_box.utils.model import create_model_dict
+from vox_box.backends.stt.base import STTBackend
+from vox_box.config.config import BackendEnum, Config, TaskTypeEnum
+from vox_box.utils.log import log_method
+from vox_box.utils.model import create_model_dict
 from faster_whisper.transcribe import WhisperModel
 
 logger = logging.getLogger(__name__)
diff --git a/speech_box/backends/stt/funasr.py b/vox_box/backends/stt/funasr.py
similarity index 93%
rename from speech_box/backends/stt/funasr.py
rename to vox_box/backends/stt/funasr.py
index d63d3c5..9f16c4f 100644
--- a/speech_box/backends/stt/funasr.py
+++ b/vox_box/backends/stt/funasr.py
@@ -3,10 +3,10 @@
 import os
 from typing import Dict, List, Optional
 import tempfile
-from speech_box.backends.stt.base import STTBackend
-from speech_box.config.config import BackendEnum, Config, TaskTypeEnum
-from speech_box.utils.log import log_method
-from speech_box.utils.model import create_model_dict
+from vox_box.backends.stt.base import STTBackend
+from vox_box.config.config import BackendEnum, Config, TaskTypeEnum
+from vox_box.utils.log import log_method
+from vox_box.utils.model import create_model_dict
 
 
 logger = logging.getLogger(__name__)
diff --git a/speech_box/backends/tts/bark.py b/vox_box/backends/tts/bark.py
similarity index 91%
rename from speech_box/backends/tts/bark.py
rename to vox_box/backends/tts/bark.py
index 38b591f..2341b17 100644
--- a/speech_box/backends/tts/bark.py
+++ b/vox_box/backends/tts/bark.py
@@ -3,14 +3,14 @@
 import tempfile
 from typing import Dict, List, Optional
 
-from speech_box.backends.tts.base import TTSBackend
-from speech_box.config.config import BackendEnum, Config, TaskTypeEnum
+from vox_box.backends.tts.base import TTSBackend
+from vox_box.config.config import BackendEnum, Config, TaskTypeEnum
 from transformers import AutoProcessor, BarkModel
 from scipy.io.wavfile import write as write_wav
 
-from speech_box.utils.ffmpeg import convert
-from speech_box.utils.log import log_method
-from speech_box.utils.model import create_model_dict
+from vox_box.utils.ffmpeg import convert
+from vox_box.utils.log import log_method
+from vox_box.utils.model import create_model_dict
 
 
 class Bark(TTSBackend):
diff --git a/speech_box/backends/tts/base.py b/vox_box/backends/tts/base.py
similarity index 87%
rename from speech_box/backends/tts/base.py
rename to vox_box/backends/tts/base.py
index 945e082..dab637e 100644
--- a/speech_box/backends/tts/base.py
+++ b/vox_box/backends/tts/base.py
@@ -1,8 +1,8 @@
 from abc import ABC, abstractmethod
 import logging
 from typing import Dict, Optional
-from speech_box.config.config import Config
-from speech_box.utils.log import log_method
+from vox_box.config.config import Config
+from vox_box.utils.log import log_method
 
 logger = logging.getLogger(__name__)
 
diff --git a/speech_box/backends/tts/cosyvoice.py b/vox_box/backends/tts/cosyvoice.py
similarity index 91%
rename from speech_box/backends/tts/cosyvoice.py
rename to vox_box/backends/tts/cosyvoice.py
index a6e969d..b517a17 100644
--- a/speech_box/backends/tts/cosyvoice.py
+++ b/vox_box/backends/tts/cosyvoice.py
@@ -5,11 +5,11 @@
 import tempfile
 from typing import Dict, List, Optional
 
-from speech_box.backends.tts.base import TTSBackend
-from speech_box.utils.log import log_method
-from speech_box.config.config import BackendEnum, Config, TaskTypeEnum
-from speech_box.utils.ffmpeg import convert
-from speech_box.utils.model import create_model_dict
+from vox_box.backends.tts.base import TTSBackend
+from vox_box.utils.log import log_method
+from vox_box.config.config import BackendEnum, Config, TaskTypeEnum
+from vox_box.utils.ffmpeg import convert
+from vox_box.utils.model import create_model_dict
 
 paths_to_insert = [
     os.path.join(os.path.dirname(__file__), "../../third_party/CosyVoice"),
diff --git a/speech_box/cmd/__init__.py b/vox_box/cmd/__init__.py
similarity index 100%
rename from speech_box/cmd/__init__.py
rename to vox_box/cmd/__init__.py
diff --git a/speech_box/cmd/start.py b/vox_box/cmd/start.py
similarity index 92%
rename from speech_box/cmd/start.py
rename to vox_box/cmd/start.py
index fd4ca0d..0653c7a 100644
--- a/speech_box/cmd/start.py
+++ b/vox_box/cmd/start.py
@@ -3,10 +3,10 @@
 import logging
 import os
 
-from speech_box.logging import setup_logging
-from speech_box.config import Config
-from speech_box.server.model import ModelInstance
-from speech_box.server.server import Server
+from vox_box.logging import setup_logging
+from vox_box.config import Config
+from vox_box.server.model import ModelInstance
+from vox_box.server.server import Server
 
 
 logger = logging.getLogger(__name__)
@@ -28,8 +28,8 @@ def __call__(self, parser, namespace, values, option_string=None):
 def setup_start_cmd(subparsers: argparse._SubParsersAction):
     parser_server: argparse.ArgumentParser = subparsers.add_parser(
         "start",
-        help="Run speech-box api server.",
-        description="Run speech-box api server.",
+        help="Run vox-box api server.",
+        description="Run vox-box api server.",
     )
 
     group = parser_server.add_argument_group("Common settings")
@@ -137,7 +137,7 @@ def validate_args(args: argparse.Namespace):
 
 
 def get_data_dir():
-    app_name = "speech-box"
+    app_name = "vox-box"
     if os.name == "nt":  # Windows
         data_dir = os.path.join(os.environ["APPDATA"], app_name)
     elif os.name == "posix":
diff --git a/speech_box/cmd/version.py b/vox_box/cmd/version.py
similarity index 91%
rename from speech_box/cmd/version.py
rename to vox_box/cmd/version.py
index 0abe06b..832825b 100644
--- a/speech_box/cmd/version.py
+++ b/vox_box/cmd/version.py
@@ -1,5 +1,5 @@
 import argparse
-from speech_box import __version__, __git_commit__
+from vox_box import __version__, __git_commit__
 
 
 def setup_version_cmd(subparsers: argparse._SubParsersAction):
diff --git a/speech_box/config/__init__.py b/vox_box/config/__init__.py
similarity index 100%
rename from speech_box/config/__init__.py
rename to vox_box/config/__init__.py
diff --git a/speech_box/config/config.py b/vox_box/config/config.py
similarity index 93%
rename from speech_box/config/config.py
rename to vox_box/config/config.py
index 4bf04ac..ccbb413 100644
--- a/speech_box/config/config.py
+++ b/vox_box/config/config.py
@@ -3,7 +3,7 @@
 
 
 class Config:
-    """A class used to define speech-box configuration.
+    """A class used to define vox-box configuration.
 
     Attributes:
         debug: Enable debug mode.
diff --git a/speech_box/downloader/downloaders.py b/vox_box/downloader/downloaders.py
similarity index 99%
rename from speech_box/downloader/downloaders.py
rename to vox_box/downloader/downloaders.py
index f94dff5..92cea67 100644
--- a/speech_box/downloader/downloaders.py
+++ b/vox_box/downloader/downloaders.py
@@ -12,7 +12,7 @@
     snapshot_download as modelscope_snapshot_download,
 )
 from modelscope.hub.utils.utils import model_id_to_group_owner_name
-from speech_box.downloader.hub import (
+from vox_box.downloader.hub import (
     match_hugging_face_files,
     match_model_scope_file_paths,
 )
diff --git a/speech_box/downloader/hub.py b/vox_box/downloader/hub.py
similarity index 100%
rename from speech_box/downloader/hub.py
rename to vox_box/downloader/hub.py
diff --git a/speech_box/elstimator/bark.py b/vox_box/elstimator/bark.py
similarity index 92%
rename from speech_box/elstimator/bark.py
rename to vox_box/elstimator/bark.py
index 08744a4..8aae0ee 100644
--- a/speech_box/elstimator/bark.py
+++ b/vox_box/elstimator/bark.py
@@ -2,10 +2,10 @@
 import logging
 import os
 from typing import Dict
-from speech_box.config.config import BackendEnum, Config, TaskTypeEnum
-from speech_box.downloader.downloaders import download_model
-from speech_box.elstimator.base import Elstimator
-from speech_box.utils.model import create_model_dict
+from vox_box.config.config import BackendEnum, Config, TaskTypeEnum
+from vox_box.downloader.downloaders import download_model
+from vox_box.elstimator.base import Elstimator
+from vox_box.utils.model import create_model_dict
 
 logger = logging.getLogger(__name__)
 
diff --git a/speech_box/elstimator/base.py b/vox_box/elstimator/base.py
similarity index 83%
rename from speech_box/elstimator/base.py
rename to vox_box/elstimator/base.py
index 9375d2d..088de42 100644
--- a/speech_box/elstimator/base.py
+++ b/vox_box/elstimator/base.py
@@ -1,6 +1,6 @@
 from abc import ABC, abstractmethod
 from typing import Dict
-from speech_box.config.config import Config
+from vox_box.config.config import Config
 
 
 class Elstimator(ABC):
diff --git a/speech_box/elstimator/cosyvoice.py b/vox_box/elstimator/cosyvoice.py
similarity index 89%
rename from speech_box/elstimator/cosyvoice.py
rename to vox_box/elstimator/cosyvoice.py
index 6b8f264..2d51a39 100644
--- a/speech_box/elstimator/cosyvoice.py
+++ b/vox_box/elstimator/cosyvoice.py
@@ -2,11 +2,11 @@
 import os
 from typing import Dict
 
-from speech_box.downloader.downloaders import download_model
-from speech_box.elstimator.base import Elstimator
+from vox_box.downloader.downloaders import download_model
+from vox_box.elstimator.base import Elstimator
 
-from speech_box.config.config import BackendEnum, Config, TaskTypeEnum
-from speech_box.utils.model import create_model_dict
+from vox_box.config.config import BackendEnum, Config, TaskTypeEnum
+from vox_box.utils.model import create_model_dict
 
 logger = logging.getLogger(__name__)
 
diff --git a/speech_box/elstimator/estimate.py b/vox_box/elstimator/estimate.py
similarity index 58%
rename from speech_box/elstimator/estimate.py
rename to vox_box/elstimator/estimate.py
index a2bc8d2..7a02d87 100644
--- a/speech_box/elstimator/estimate.py
+++ b/vox_box/elstimator/estimate.py
@@ -1,11 +1,11 @@
 from typing import Dict, List
-from speech_box.config.config import Config
-from speech_box.elstimator.bark import Bark
-from speech_box.elstimator.base import Elstimator
-from speech_box.elstimator.cosyvoice import CosyVoice
-from speech_box.elstimator.faster_whisper import FasterWhisper
-from speech_box.elstimator.funasr import FunASR
-from speech_box.utils.model import create_model_dict
+from vox_box.config.config import Config
+from vox_box.elstimator.bark import Bark
+from vox_box.elstimator.base import Elstimator
+from vox_box.elstimator.cosyvoice import CosyVoice
+from vox_box.elstimator.faster_whisper import FasterWhisper
+from vox_box.elstimator.funasr import FunASR
+from vox_box.utils.model import create_model_dict
 
 
 def estimate_model(cfg: Config) -> Dict:
diff --git a/speech_box/elstimator/faster_whisper.py b/vox_box/elstimator/faster_whisper.py
similarity index 93%
rename from speech_box/elstimator/faster_whisper.py
rename to vox_box/elstimator/faster_whisper.py
index e10da6e..3f5172d 100644
--- a/speech_box/elstimator/faster_whisper.py
+++ b/vox_box/elstimator/faster_whisper.py
@@ -2,11 +2,11 @@
 import logging
 import os
 from typing import Dict, List
-from speech_box.config.config import BackendEnum, Config, TaskTypeEnum
-from speech_box.downloader.downloaders import download_model
-from speech_box.downloader.hub import match_files
-from speech_box.elstimator.base import Elstimator
-from speech_box.utils.model import create_model_dict
+from vox_box.config.config import BackendEnum, Config, TaskTypeEnum
+from vox_box.downloader.downloaders import download_model
+from vox_box.downloader.hub import match_files
+from vox_box.elstimator.base import Elstimator
+from vox_box.utils.model import create_model_dict
 from faster_whisper.transcribe import WhisperModel
 
 logger = logging.getLogger(__name__)
diff --git a/speech_box/elstimator/funasr.py b/vox_box/elstimator/funasr.py
similarity index 92%
rename from speech_box/elstimator/funasr.py
rename to vox_box/elstimator/funasr.py
index 5bd2603..c448bf2 100644
--- a/speech_box/elstimator/funasr.py
+++ b/vox_box/elstimator/funasr.py
@@ -2,10 +2,10 @@
 import logging
 import os
 from typing import Dict
-from speech_box.config.config import BackendEnum, Config, TaskTypeEnum
-from speech_box.downloader.downloaders import download_model
-from speech_box.elstimator.base import Elstimator
-from speech_box.utils.model import create_model_dict
+from vox_box.config.config import BackendEnum, Config, TaskTypeEnum
+from vox_box.downloader.downloaders import download_model
+from vox_box.elstimator.base import Elstimator
+from vox_box.utils.model import create_model_dict
 
 
 logger = logging.getLogger(__name__)
diff --git a/speech_box/logging.py b/vox_box/logging.py
similarity index 100%
rename from speech_box/logging.py
rename to vox_box/logging.py
diff --git a/speech_box/main.py b/vox_box/main.py
similarity index 88%
rename from speech_box/main.py
rename to vox_box/main.py
index d8b5492..90ba095 100644
--- a/speech_box/main.py
+++ b/vox_box/main.py
@@ -2,8 +2,8 @@
 import signal
 import sys
 
-from speech_box.cmd import setup_start_cmd
-from speech_box.cmd.version import setup_version_cmd
+from vox_box.cmd import setup_start_cmd
+from vox_box.cmd.version import setup_version_cmd
 
 
 def handle_signal(sig, frame):
diff --git a/speech_box/server/app.py b/vox_box/server/app.py
similarity index 86%
rename from speech_box/server/app.py
rename to vox_box/server/app.py
index f9eaddf..cd712d2 100644
--- a/speech_box/server/app.py
+++ b/vox_box/server/app.py
@@ -3,8 +3,8 @@
 from fastapi.responses import JSONResponse
 import httpx
 
-from speech_box import __version__
-from speech_box.server.routers import router
+from vox_box import __version__
+from vox_box.server.routers import router
 
 
 @asynccontextmanager
@@ -15,7 +15,7 @@ async def lifespan(app: FastAPI):
 
 
 app = FastAPI(
-    title="speech-box",
+    title="vox-box",
     lifespan=lifespan,
     response_model_exclude_unset=True,
     version=__version__,
diff --git a/speech_box/server/model.py b/vox_box/server/model.py
similarity index 80%
rename from speech_box/server/model.py
rename to vox_box/server/model.py
index 376d26c..980523c 100644
--- a/speech_box/server/model.py
+++ b/vox_box/server/model.py
@@ -1,13 +1,13 @@
 from typing import Union
-from speech_box.backends.stt.base import STTBackend
-from speech_box.backends.stt.faster_whisper import FasterWhisper
-from speech_box.backends.stt.funasr import FunASR
-from speech_box.backends.tts.bark import Bark
-from speech_box.backends.tts.base import TTSBackend
-from speech_box.backends.tts.cosyvoice import CosyVoice
-from speech_box.config.config import BackendEnum, Config
-from speech_box.downloader import downloaders
-from speech_box.elstimator.estimate import estimate_model
+from vox_box.backends.stt.base import STTBackend
+from vox_box.backends.stt.faster_whisper import FasterWhisper
+from vox_box.backends.stt.funasr import FunASR
+from vox_box.backends.tts.bark import Bark
+from vox_box.backends.tts.base import TTSBackend
+from vox_box.backends.tts.cosyvoice import CosyVoice
+from vox_box.config.config import BackendEnum, Config
+from vox_box.downloader import downloaders
+from vox_box.elstimator.estimate import estimate_model
 
 _instance = None
 
diff --git a/speech_box/server/routers.py b/vox_box/server/routers.py
similarity index 96%
rename from speech_box/server/routers.py
rename to vox_box/server/routers.py
index f0fd413..b69d071 100644
--- a/speech_box/server/routers.py
+++ b/vox_box/server/routers.py
@@ -3,9 +3,9 @@
 from pydantic import BaseModel
 from fastapi.responses import FileResponse
 
-from speech_box.backends.stt.base import STTBackend
-from speech_box.backends.tts.base import TTSBackend
-from speech_box.server.model import get_model_instance
+from vox_box.backends.stt.base import STTBackend
+from vox_box.backends.tts.base import TTSBackend
+from vox_box.server.model import get_model_instance
 from concurrent.futures import ThreadPoolExecutor
 
 router = APIRouter()
diff --git a/speech_box/server/server.py b/vox_box/server/server.py
similarity index 86%
rename from speech_box/server/server.py
rename to vox_box/server/server.py
index ecd5a50..f260cb7 100644
--- a/speech_box/server/server.py
+++ b/vox_box/server/server.py
@@ -1,9 +1,9 @@
 import logging
-from speech_box.config.config import Config
+from vox_box.config.config import Config
 import uvicorn
 
-from speech_box.logging import setup_logging
-from speech_box.server.app import app
+from vox_box.logging import setup_logging
+from vox_box.server.app import app
 
 logger = logging.getLogger(__name__)
 
diff --git a/speech_box/utils/compat_importlib.py b/vox_box/utils/compat_importlib.py
similarity index 100%
rename from speech_box/utils/compat_importlib.py
rename to vox_box/utils/compat_importlib.py
diff --git a/speech_box/utils/ffmpeg.py b/vox_box/utils/ffmpeg.py
similarity index 100%
rename from speech_box/utils/ffmpeg.py
rename to vox_box/utils/ffmpeg.py
diff --git a/speech_box/utils/file.py b/vox_box/utils/file.py
similarity index 100%
rename from speech_box/utils/file.py
rename to vox_box/utils/file.py
diff --git a/speech_box/utils/log.py b/vox_box/utils/log.py
similarity index 100%
rename from speech_box/utils/log.py
rename to vox_box/utils/log.py
diff --git a/speech_box/utils/model.py b/vox_box/utils/model.py
similarity index 81%
rename from speech_box/utils/model.py
rename to vox_box/utils/model.py
index 2f6ba27..d2d472e 100644
--- a/speech_box/utils/model.py
+++ b/vox_box/utils/model.py
@@ -7,8 +7,8 @@ def create_model_dict(id: str, **kwargs) -> Dict:
         "id": id,
         "object": "model",
         "created": int(time.time()),
-        "owner": "speech-box",
-        "backend": "speech-box",
+        "owner": "vox-box",
+        "backend": "vox-box",
     }
 
     for k, v in kwargs.items():