From 72f7d140d4dcfeba86f5905a7c41b1de6dc9b8e4 Mon Sep 17 00:00:00 2001
From: Ben Xu <benx.xu@mail.utoronto.ca>
Date: Tue, 11 Jun 2024 20:12:36 -0700
Subject: [PATCH] add realtime tts streaming

---
 software/poetry.lock                        | 743 +++++---------------
 software/pyproject.toml                     |   9 +-
 software/source/clients/base_device.py      |  82 ++-
 software/source/server/async_interpreter.py |  45 +-
 software/source/server/async_server.py      |  42 +-
 software/source/server/server.py            |   2 +
 software/start.py                           |  28 +-
 7 files changed, 344 insertions(+), 607 deletions(-)

diff --git a/software/poetry.lock b/software/poetry.lock
index 528ed12e..45f3b5c4 100644
--- a/software/poetry.lock
+++ b/software/poetry.lock
@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 1.8.2 and should not be changed by hand.
+# This file is automatically @generated by Poetry 1.8.3 and should not be changed by hand.
 
 [[package]]
 name = "absl-py"
@@ -11,17 +11,6 @@ files = [
     {file = "absl_py-2.1.0-py3-none-any.whl", hash = "sha256:526a04eadab8b4ee719ce68f204172ead1027549089702d99b9059f129ff1308"},
 ]
 
-[[package]]
-name = "aifs"
-version = "0.0.15"
-description = "Local semantic search. Stupidly simple."
-optional = false
-python-versions = "<4,>=3.9"
-files = [
-    {file = "aifs-0.0.15-py3-none-any.whl", hash = "sha256:ea15d7702499c1af21a49a0b32248fbf1aef57857e4ffa11107e7f834613ad49"},
-    {file = "aifs-0.0.15.tar.gz", hash = "sha256:385a975a135dbc6ab117dc9572f63faf4ac46dc594e7a8707b6f3408a0c0abab"},
-]
-
 [[package]]
 name = "aiohttp"
 version = "3.9.5"
@@ -327,17 +316,17 @@ files = [
 
 [[package]]
 name = "azure-cognitiveservices-speech"
-version = "1.36.0"
+version = "1.37.0"
 description = "Microsoft Cognitive Services Speech SDK for Python"
 optional = false
 python-versions = ">=3.7"
 files = [
-    {file = "azure_cognitiveservices_speech-1.36.0-py3-none-macosx_10_14_x86_64.whl", hash = "sha256:76542b7b0f010d9b2304382b9f146f8e57ba14c6f0c6d90580c81f55c22baf1f"},
-    {file = "azure_cognitiveservices_speech-1.36.0-py3-none-macosx_11_0_arm64.whl", hash = "sha256:81ac075c6f2cb97a35fa88306adbddabfe54a7de2b582f349a484ee2b8bd81e0"},
-    {file = "azure_cognitiveservices_speech-1.36.0-py3-none-manylinux1_x86_64.whl", hash = "sha256:ed1f6ba3dd439d8f7771d4e32a1e2224e1b4103e050f07120eb9d0cfb5aae82e"},
-    {file = "azure_cognitiveservices_speech-1.36.0-py3-none-manylinux2014_aarch64.whl", hash = "sha256:208517147f59fdf3fcce5e62584763d7710d4fbfd3af6d63d1240d3da34ff2c8"},
-    {file = "azure_cognitiveservices_speech-1.36.0-py3-none-win32.whl", hash = "sha256:ee6fbd600e025900591e2a7eca1b2bec287cb7460c8719fd564682b065d12948"},
-    {file = "azure_cognitiveservices_speech-1.36.0-py3-none-win_amd64.whl", hash = "sha256:37b1d977ab961389c89e499d00a7c3ff64ead988e16cee8c563dab3464750871"},
+    {file = "azure_cognitiveservices_speech-1.37.0-py3-none-macosx_10_14_x86_64.whl", hash = "sha256:906d6bf65176e93464e2d763dd074ca00c48cfe1a896371fcdcb155a500910f7"},
+    {file = "azure_cognitiveservices_speech-1.37.0-py3-none-macosx_11_0_arm64.whl", hash = "sha256:54ec8dd55d4dbd9058c61909e08485d3761d6d30954da189e1b17d84daf5e2e0"},
+    {file = "azure_cognitiveservices_speech-1.37.0-py3-none-manylinux1_x86_64.whl", hash = "sha256:685424689725d2d4115485998c0888c8b5b502259037ff533e5a834575f80b66"},
+    {file = "azure_cognitiveservices_speech-1.37.0-py3-none-manylinux2014_aarch64.whl", hash = "sha256:384f66786c2335165035270897b34d0b91736a1fdf38f7696e9a227075cb2489"},
+    {file = "azure_cognitiveservices_speech-1.37.0-py3-none-win32.whl", hash = "sha256:343d5f449ccd6c9b53cd37dd46a70ece0905243517df7a0c047779e55072254c"},
+    {file = "azure_cognitiveservices_speech-1.37.0-py3-none-win_amd64.whl", hash = "sha256:a18fb45490cdcd681407ccaad9560fb14dda1c8276de297e219ea1a880467e28"},
 ]
 
 [[package]]
@@ -354,28 +343,6 @@ files = [
 [package.extras]
 dev = ["freezegun (>=1.0,<2.0)", "pytest (>=6.0)", "pytest-cov"]
 
-[[package]]
-name = "backoff"
-version = "2.2.1"
-description = "Function decoration for backoff and retry"
-optional = false
-python-versions = ">=3.7,<4.0"
-files = [
-    {file = "backoff-2.2.1-py3-none-any.whl", hash = "sha256:63579f9a0628e06278f7e47b7d7d5b6ce20dc65c5e96a6f3ca99a6adca0396e8"},
-    {file = "backoff-2.2.1.tar.gz", hash = "sha256:03f829f5bb1923180821643f8753b0502c3b682293992485b0eef2807afa5cba"},
-]
-
-[[package]]
-name = "bangla"
-version = "0.0.2"
-description = "Bangla is a package for Bangla language users with various functionalities including Bangla date and Bangla numeric conversation."
-optional = false
-python-versions = "*"
-files = [
-    {file = "bangla-0.0.2-py2.py3-none-any.whl", hash = "sha256:60c52bb4614894de4a91ee997bf950d03545d1fb9b01196577ce04ed4fa00ff8"},
-    {file = "bangla-0.0.2.tar.gz", hash = "sha256:17c8fd501321660077d5ab6a79b746bba71f9e4939ef78ac0d9a75d7bd715da8"},
-]
-
 [[package]]
 name = "black"
 version = "24.4.2"
@@ -438,17 +405,6 @@ jinxed = {version = ">=1.1.0", markers = "platform_system == \"Windows\""}
 six = ">=1.9.0"
 wcwidth = ">=0.1.4"
 
-[[package]]
-name = "blinker"
-version = "1.8.2"
-description = "Fast, simple object-to-object and broadcast signaling"
-optional = false
-python-versions = ">=3.8"
-files = [
-    {file = "blinker-1.8.2-py3-none-any.whl", hash = "sha256:1779309f71bf239144b9399d06ae925637cf6634cf6bd131104184531bf67c01"},
-    {file = "blinker-1.8.2.tar.gz", hash = "sha256:8f77b09d3bf7c795e969e9486f39c2c5e9c39d4ee07424be2bc594ece9642d83"},
-]
-
 [[package]]
 name = "blis"
 version = "0.7.11"
@@ -495,27 +451,6 @@ files = [
 [package.dependencies]
 numpy = {version = ">=1.19.0", markers = "python_version >= \"3.9\""}
 
-[[package]]
-name = "bnnumerizer"
-version = "0.0.2"
-description = "Bangla Number text to String Converter"
-optional = false
-python-versions = "*"
-files = [
-    {file = "bnnumerizer-0.0.2.tar.gz", hash = "sha256:41df6fd0b7b51aa4ec4776b6643cedebee5fd11e335d7d56d4a20c08515e5f0d"},
-]
-
-[[package]]
-name = "bnunicodenormalizer"
-version = "0.1.7"
-description = "Bangla Unicode Normalization Toolkit"
-optional = false
-python-versions = "*"
-files = [
-    {file = "bnunicodenormalizer-0.1.7-py3-none-any.whl", hash = "sha256:42b6a9720bca52c02a944a0876770e86694eb081a096f3c644ccd8add40f7cee"},
-    {file = "bnunicodenormalizer-0.1.7.tar.gz", hash = "sha256:86a3489cc81c73d2afb4e265bd2d0d8bc52fc8a2374e210c899e0260940bc091"},
-]
-
 [[package]]
 name = "bottle"
 version = "0.12.25"
@@ -916,6 +851,82 @@ files = [
     {file = "coqpit-0.0.17.tar.gz", hash = "sha256:dc129c2a741f8feec35c16d0b603afafdf66064822638b4e4fd7a02a7ce05011"},
 ]
 
+[[package]]
+name = "coqui-tts"
+version = "0.24.1"
+description = "Deep learning for Text to Speech."
+optional = false
+python-versions = "<3.13,>=3.9"
+files = [
+    {file = "coqui_tts-0.24.1-cp310-cp310-manylinux1_x86_64.whl", hash = "sha256:7feb9502f03e6c3c0b5e47c0f6166335ff03aac55dece61497233168bf8ea750"},
+    {file = "coqui_tts-0.24.1-cp311-cp311-manylinux1_x86_64.whl", hash = "sha256:da2fadf99aa1556dc4a26df90d14745a2ff508be4bf6ac143b778cb2ffa3f313"},
+    {file = "coqui_tts-0.24.1-cp312-cp312-manylinux1_x86_64.whl", hash = "sha256:05b56d58c495b05738957198ea6130f0543a0c84d5b9e97872c852dd72760786"},
+    {file = "coqui_tts-0.24.1-cp39-cp39-manylinux1_x86_64.whl", hash = "sha256:09ce255368528f61cef8ce29f4718e91d7f46a348eb0696502f2c10575024eb7"},
+    {file = "coqui_tts-0.24.1.tar.gz", hash = "sha256:a6a1251bf2ffb9be8efc8fbecd54331579a1d80255aa7e18b31bd9f002e4abc5"},
+]
+
+[package.dependencies]
+anyascii = ">=0.3.0"
+coqpit = ">=0.0.16"
+coqui-tts-trainer = ">=0.1"
+cython = ">=0.29.30"
+einops = ">=0.6.0"
+encodec = ">=0.1.1"
+fsspec = {version = ">=2023.6.0", extras = ["http"]}
+gruut = {version = "2.2.3", extras = ["de", "es", "fr"]}
+inflect = ">=5.6.0"
+librosa = ">=0.10.1"
+matplotlib = ">=3.7.0"
+num2words = "*"
+numpy = ">=1.24.3"
+packaging = ">=23.1"
+pysbd = ">=0.3.4"
+pyyaml = ">=6.0"
+scipy = ">=1.11.2"
+soundfile = ">=0.12.0"
+spacy = {version = ">=3", extras = ["ja"]}
+torch = ">=2.1"
+torchaudio = "*"
+tqdm = ">=4.64.1"
+transformers = ">=4.33.0,<4.41.0"
+umap-learn = ">=0.5.1"
+
+[package.extras]
+all = ["coqui-tts[bn,ja,ko,notebooks,server,zh]"]
+bn = ["bangla", "bnnumerizer", "bnunicodenormalizer"]
+dev = ["black (==24.2.0)", "coverage[toml]", "nose2", "pre-commit", "ruff (==0.3.0)", "tomli"]
+docs = ["furo", "linkify-it-py", "myst-parser (==2.0.0)", "sphinx (==7.2.5)", "sphinx-copybutton", "sphinx-inline-tabs"]
+ja = ["cutlet", "mecab-python3", "unidic-lite (==1.0.8)"]
+ko = ["g2pkk (>=0.1.1)", "hangul-romanize", "jamo"]
+languages = ["coqui-tts[bn,ja,ko,zh]"]
+notebooks = ["bokeh (==1.4.0)", "pandas (>=1.4,<2.0)"]
+server = ["flask (>=2.0.1)"]
+zh = ["jieba", "pypinyin"]
+
+[[package]]
+name = "coqui-tts-trainer"
+version = "0.1.1"
+description = "General purpose model trainer for PyTorch that is more flexible than it should be, by 🐸Coqui."
+optional = false
+python-versions = "<3.13,>=3.6.0"
+files = [
+    {file = "coqui_tts_trainer-0.1.1-py3-none-any.whl", hash = "sha256:ffff1bbeca300c86c42e75baf427f3dd96851a141d9c7a8829634ec92e5a109f"},
+    {file = "coqui_tts_trainer-0.1.1.tar.gz", hash = "sha256:c8c73e76e48b3e5c5e348e356ffff29176a1a7646ec4087c2714d144647655d6"},
+]
+
+[package.dependencies]
+coqpit = "*"
+fsspec = "*"
+psutil = "*"
+soundfile = "*"
+tensorboard = "*"
+torch = ">=1.7"
+
+[package.extras]
+all = ["accelerate", "black (==24.2.0)", "coqpit", "coverage", "fsspec", "isort", "psutil", "pylint", "pytest", "soundfile", "tensorboard", "torch (>=1.7)", "torchvision"]
+dev = ["accelerate", "black (==24.2.0)", "coverage", "isort", "pylint", "pytest"]
+test = ["torchvision"]
+
 [[package]]
 name = "ctranslate2"
 version = "4.1.0"
@@ -1203,19 +1214,21 @@ files = [
 
 [[package]]
 name = "elevenlabs"
-version = "0.2.27"
-description = "The official elevenlabs python package."
+version = "1.2.2"
+description = ""
 optional = false
-python-versions = "*"
+python-versions = "<4.0,>=3.8"
 files = [
-    {file = "elevenlabs-0.2.27-py3-none-any.whl", hash = "sha256:c31ea892d5668002bc26d0bb46a6466b0b4e2fe5aaed75cbc1b7011f01d3fa29"},
-    {file = "elevenlabs-0.2.27.tar.gz", hash = "sha256:1b17d3c997557e5aa654b296e3960c25ea183525cfdbd0ec53070b038ba5fd95"},
+    {file = "elevenlabs-1.2.2-py3-none-any.whl", hash = "sha256:60b92b0e2aabdfba93a43569f207f8a2ad397492519b8e11a2eebb32807ddefa"},
+    {file = "elevenlabs-1.2.2.tar.gz", hash = "sha256:ebd02869b95602b8956874dd727981bb49ad16b9a3c2f5901193d838213694aa"},
 ]
 
 [package.dependencies]
+httpx = ">=0.21.2"
 ipython = ">=7.0"
-pydantic = ">=2.0"
+pydantic = ">=1.9.2"
 requests = ">=2.20"
+typing_extensions = ">=4.0.0"
 websockets = ">=11.0"
 
 [[package]]
@@ -1375,29 +1388,6 @@ docs = ["furo (>=2023.9.10)", "sphinx (>=7.2.6)", "sphinx-autodoc-typehints (>=1
 testing = ["covdefaults (>=2.3)", "coverage (>=7.3.2)", "diff-cover (>=8.0.1)", "pytest (>=7.4.3)", "pytest-cov (>=4.1)", "pytest-mock (>=3.12)", "pytest-timeout (>=2.2)"]
 typing = ["typing-extensions (>=4.8)"]
 
-[[package]]
-name = "flask"
-version = "3.0.3"
-description = "A simple framework for building complex web applications."
-optional = false
-python-versions = ">=3.8"
-files = [
-    {file = "flask-3.0.3-py3-none-any.whl", hash = "sha256:34e815dfaa43340d1d15a5c3a02b8476004037eb4840b34910c6e21679d288f3"},
-    {file = "flask-3.0.3.tar.gz", hash = "sha256:ceb27b0af3823ea2737928a4d99d125a06175b8512c445cbd9a9ce200ef76842"},
-]
-
-[package.dependencies]
-blinker = ">=1.6.2"
-click = ">=8.1.3"
-importlib-metadata = {version = ">=3.6.0", markers = "python_version < \"3.10\""}
-itsdangerous = ">=2.1.2"
-Jinja2 = ">=3.1.2"
-Werkzeug = ">=3.0.0"
-
-[package.extras]
-async = ["asgiref (>=3.2)"]
-dotenv = ["python-dotenv"]
-
 [[package]]
 name = "flatbuffers"
 version = "24.3.25"
@@ -1571,6 +1561,9 @@ files = [
     {file = "fsspec-2024.5.0.tar.gz", hash = "sha256:1d021b0b0f933e3b3029ed808eb400c08ba101ca2de4b3483fbc9ca23fcee94a"},
 ]
 
+[package.dependencies]
+aiohttp = {version = "<4.0.0a0 || >4.0.0a0,<4.0.0a1 || >4.0.0a1", optional = true, markers = "extra == \"http\""}
+
 [package.extras]
 abfs = ["adlfs"]
 adl = ["adlfs"]
@@ -1609,21 +1602,6 @@ files = [
     {file = "future-1.0.0.tar.gz", hash = "sha256:bd2968309307861edae1458a4f8a4f3598c03be43b97521076aebf5d94c07b05"},
 ]
 
-[[package]]
-name = "g2pkk"
-version = "0.1.2"
-description = "g2pkk: g2p module for Korean(cross platform)"
-optional = false
-python-versions = ">=3.6"
-files = [
-    {file = "g2pkk-0.1.2-py3-none-any.whl", hash = "sha256:f1d551f35d3b9065f75749c724e65b28731fdc3262e5e9657cb57e3f7b5dcac3"},
-    {file = "g2pkk-0.1.2.tar.gz", hash = "sha256:61aad5d41b67d71dd29b8570fc90d2c89cb76493170101d92492649521b447e4"},
-]
-
-[package.dependencies]
-jamo = "*"
-nltk = "*"
-
 [[package]]
 name = "git-python"
 version = "1.0.3"
@@ -1840,6 +1818,25 @@ files = [
     {file = "gruut_lang_fr-2.0.2.tar.gz", hash = "sha256:d2de9fc2f92ede277cb6dfe72afdba1b902d329b3cc1f1c706e66b31f0d436bd"},
 ]
 
+[[package]]
+name = "gtts"
+version = "2.5.1"
+description = "gTTS (Google Text-to-Speech), a Python library and CLI tool to interface with Google Translate text-to-speech API"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "gTTS-2.5.1-py3-none-any.whl", hash = "sha256:273ec8a5077b25e60ca5a266ed254b54d1f14032b0af3ba00092d14966148664"},
+    {file = "gTTS-2.5.1.tar.gz", hash = "sha256:02d0a9874f945dee9cd5092991c60bc88d4b7767b8cd81144b6fb49dc3de6897"},
+]
+
+[package.dependencies]
+click = ">=7.1,<8.2"
+requests = ">=2.27,<3"
+
+[package.extras]
+docs = ["sphinx", "sphinx-autobuild", "sphinx-click", "sphinx-mdinclude", "sphinx-rtd-theme"]
+tests = ["pytest (>=7.1.3,<8.1.0)", "pytest-cov", "testfixtures"]
+
 [[package]]
 name = "h11"
 version = "0.14.0"
@@ -1872,17 +1869,6 @@ termcolor = ">=1.1.0"
 [package.extras]
 ipython = ["IPython (==5.7.0)", "ipywidgets (==7.1.0)"]
 
-[[package]]
-name = "hangul-romanize"
-version = "0.1.0"
-description = "Rominize Hangul strings."
-optional = false
-python-versions = "*"
-files = [
-    {file = "hangul-romanize-0.1.0.tar.gz", hash = "sha256:fae69ba181af6e75a86460fd7f57a6b304cd5f1973d8c425ed8602fee2c9276c"},
-    {file = "hangul_romanize-0.1.0-py3-none-any.whl", hash = "sha256:7b8ba54b624ca3b17b2c9394b971cd595c4240a31cc0fc6bc1c3e971eca8c4d5"},
-]
-
 [[package]]
 name = "html2image"
 version = "2.0.4.3"
@@ -2184,28 +2170,6 @@ files = [
 [package.extras]
 colors = ["colorama (>=0.4.6)"]
 
-[[package]]
-name = "itsdangerous"
-version = "2.2.0"
-description = "Safely pass data to untrusted environments and back."
-optional = false
-python-versions = ">=3.8"
-files = [
-    {file = "itsdangerous-2.2.0-py3-none-any.whl", hash = "sha256:c6242fc49e35958c8b15141343aa660db5fc54d4f13a1db01a3f5891b98700ef"},
-    {file = "itsdangerous-2.2.0.tar.gz", hash = "sha256:e0050c0b7da1eea53ffaf149c0cfbb5c6e2e2b69c4bef22c81fa6eb73e5f6173"},
-]
-
-[[package]]
-name = "jamo"
-version = "0.4.1"
-description = "A Hangul syllable and jamo analyzer."
-optional = false
-python-versions = "*"
-files = [
-    {file = "jamo-0.4.1-py3-none-any.whl", hash = "sha256:d4b94fd23324c606ed2fbc4037c603e2c3a7ae9390c05d3473aea1ccb6b1c3fb"},
-    {file = "jamo-0.4.1.tar.gz", hash = "sha256:ea65cf9d35338d0e0af48d75ff426d8a369b0ebde6f07051c3ac37256f56d025"},
-]
-
 [[package]]
 name = "jedi"
 version = "0.19.1"
@@ -2225,16 +2189,6 @@ docs = ["Jinja2 (==2.11.3)", "MarkupSafe (==1.1.1)", "Pygments (==2.8.1)", "alab
 qa = ["flake8 (==5.0.4)", "mypy (==0.971)", "types-setuptools (==67.2.0.1)"]
 testing = ["Django", "attrs", "colorama", "docopt", "pytest (<7.0.0)"]
 
-[[package]]
-name = "jieba"
-version = "0.42.1"
-description = "Chinese Words Segmentation Utilities"
-optional = false
-python-versions = "*"
-files = [
-    {file = "jieba-0.42.1.tar.gz", hash = "sha256:055ca12f62674fafed09427f176506079bc135638a14e23e25be909131928db2"},
-]
-
 [[package]]
 name = "jinja2"
 version = "3.1.4"
@@ -2516,37 +2470,6 @@ dev = ["changelist (==0.5)"]
 lint = ["pre-commit (==3.7.0)"]
 test = ["pytest (>=7.4)", "pytest-cov (>=4.1)"]
 
-[[package]]
-name = "librosa"
-version = "0.10.0"
-description = "Python module for audio and music processing"
-optional = false
-python-versions = ">=3.7"
-files = [
-    {file = "librosa-0.10.0-py3-none-any.whl", hash = "sha256:6db29c1467168da21313203dcef405a73a678d3aad0fbc67607250b2f08a3f5a"},
-    {file = "librosa-0.10.0.tar.gz", hash = "sha256:8e8669e5084002d1a87f6c82b732f370784a368d0e55c2dd7d7aef3fa02fd058"},
-]
-
-[package.dependencies]
-audioread = ">=2.1.9"
-decorator = ">=4.3.0"
-joblib = ">=0.14"
-lazy-loader = ">=0.1"
-msgpack = ">=1.0"
-numba = ">=0.51.0"
-numpy = ">=1.20.3"
-pooch = ">=1.0"
-scikit-learn = ">=0.20.0"
-scipy = ">=1.2.0"
-soundfile = ">=0.12.1"
-soxr = ">=0.3.2"
-typing-extensions = ">=4.1.1"
-
-[package.extras]
-display = ["matplotlib (>=3.3.0)"]
-docs = ["ipython (>=7.0)", "matplotlib (>=3.3.0)", "mir-eval (>=0.5)", "numba (>=0.51)", "numpydoc", "presets", "sphinx (!=1.3.1,<6)", "sphinx-gallery (>=0.7)", "sphinx-multiversion (>=0.2.3)", "sphinx-rtd-theme (==1.*)", "sphinxcontrib-svg2pdfconverter"]
-tests = ["matplotlib (>=3.3.0)", "packaging (>=20.0)", "pytest", "pytest-cov", "pytest-mpl", "resampy (>=0.2.2)", "samplerate", "types-decorator"]
-
 [[package]]
 name = "librosa"
 version = "0.10.2.post1"
@@ -2884,55 +2807,6 @@ files = [
     {file = "MarkupSafe-2.1.5.tar.gz", hash = "sha256:d283d37a890ba4c1ae73ffadf8046435c76e7bc2247bbb63c00bd1a709c6544b"},
 ]
 
-[[package]]
-name = "matplotlib"
-version = "3.8.4"
-description = "Python plotting package"
-optional = false
-python-versions = ">=3.9"
-files = [
-    {file = "matplotlib-3.8.4-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:abc9d838f93583650c35eca41cfcec65b2e7cb50fd486da6f0c49b5e1ed23014"},
-    {file = "matplotlib-3.8.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:8f65c9f002d281a6e904976007b2d46a1ee2bcea3a68a8c12dda24709ddc9106"},
-    {file = "matplotlib-3.8.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ce1edd9f5383b504dbc26eeea404ed0a00656c526638129028b758fd43fc5f10"},
-    {file = "matplotlib-3.8.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ecd79298550cba13a43c340581a3ec9c707bd895a6a061a78fa2524660482fc0"},
-    {file = "matplotlib-3.8.4-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:90df07db7b599fe7035d2f74ab7e438b656528c68ba6bb59b7dc46af39ee48ef"},
-    {file = "matplotlib-3.8.4-cp310-cp310-win_amd64.whl", hash = "sha256:ac24233e8f2939ac4fd2919eed1e9c0871eac8057666070e94cbf0b33dd9c338"},
-    {file = "matplotlib-3.8.4-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:72f9322712e4562e792b2961971891b9fbbb0e525011e09ea0d1f416c4645661"},
-    {file = "matplotlib-3.8.4-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:232ce322bfd020a434caaffbd9a95333f7c2491e59cfc014041d95e38ab90d1c"},
-    {file = "matplotlib-3.8.4-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6addbd5b488aedb7f9bc19f91cd87ea476206f45d7116fcfe3d31416702a82fa"},
-    {file = "matplotlib-3.8.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cc4ccdc64e3039fc303defd119658148f2349239871db72cd74e2eeaa9b80b71"},
-    {file = "matplotlib-3.8.4-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:b7a2a253d3b36d90c8993b4620183b55665a429da8357a4f621e78cd48b2b30b"},
-    {file = "matplotlib-3.8.4-cp311-cp311-win_amd64.whl", hash = "sha256:8080d5081a86e690d7688ffa542532e87f224c38a6ed71f8fbed34dd1d9fedae"},
-    {file = "matplotlib-3.8.4-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:6485ac1f2e84676cff22e693eaa4fbed50ef5dc37173ce1f023daef4687df616"},
-    {file = "matplotlib-3.8.4-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:c89ee9314ef48c72fe92ce55c4e95f2f39d70208f9f1d9db4e64079420d8d732"},
-    {file = "matplotlib-3.8.4-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:50bac6e4d77e4262c4340d7a985c30912054745ec99756ce213bfbc3cb3808eb"},
-    {file = "matplotlib-3.8.4-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f51c4c869d4b60d769f7b4406eec39596648d9d70246428745a681c327a8ad30"},
-    {file = "matplotlib-3.8.4-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:b12ba985837e4899b762b81f5b2845bd1a28f4fdd1a126d9ace64e9c4eb2fb25"},
-    {file = "matplotlib-3.8.4-cp312-cp312-win_amd64.whl", hash = "sha256:7a6769f58ce51791b4cb8b4d7642489df347697cd3e23d88266aaaee93b41d9a"},
-    {file = "matplotlib-3.8.4-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:843cbde2f0946dadd8c5c11c6d91847abd18ec76859dc319362a0964493f0ba6"},
-    {file = "matplotlib-3.8.4-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:1c13f041a7178f9780fb61cc3a2b10423d5e125480e4be51beaf62b172413b67"},
-    {file = "matplotlib-3.8.4-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fb44f53af0a62dc80bba4443d9b27f2fde6acfdac281d95bc872dc148a6509cc"},
-    {file = "matplotlib-3.8.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:606e3b90897554c989b1e38a258c626d46c873523de432b1462f295db13de6f9"},
-    {file = "matplotlib-3.8.4-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:9bb0189011785ea794ee827b68777db3ca3f93f3e339ea4d920315a0e5a78d54"},
-    {file = "matplotlib-3.8.4-cp39-cp39-win_amd64.whl", hash = "sha256:6209e5c9aaccc056e63b547a8152661324404dd92340a6e479b3a7f24b42a5d0"},
-    {file = "matplotlib-3.8.4-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:c7064120a59ce6f64103c9cefba8ffe6fba87f2c61d67c401186423c9a20fd35"},
-    {file = "matplotlib-3.8.4-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a0e47eda4eb2614300fc7bb4657fced3e83d6334d03da2173b09e447418d499f"},
-    {file = "matplotlib-3.8.4-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:493e9f6aa5819156b58fce42b296ea31969f2aab71c5b680b4ea7a3cb5c07d94"},
-    {file = "matplotlib-3.8.4.tar.gz", hash = "sha256:8aac397d5e9ec158960e31c381c5ffc52ddd52bd9a47717e2a694038167dffea"},
-]
-
-[package.dependencies]
-contourpy = ">=1.0.1"
-cycler = ">=0.10"
-fonttools = ">=4.22.0"
-importlib-resources = {version = ">=3.2.0", markers = "python_version < \"3.10\""}
-kiwisolver = ">=1.3.1"
-numpy = ">=1.21"
-packaging = ">=20.0"
-pillow = ">=8"
-pyparsing = ">=2.3.1"
-python-dateutil = ">=2.7"
-
 [[package]]
 name = "matplotlib"
 version = "3.9.0"
@@ -3030,17 +2904,6 @@ files = [
     {file = "mdurl-0.1.2.tar.gz", hash = "sha256:bb413d29f5eea38f31dd4754dd7377d4465116fb207585f97bf925588687c1ba"},
 ]
 
-[[package]]
-name = "monotonic"
-version = "1.6"
-description = "An implementation of time.monotonic() for Python 2 & < 3.3"
-optional = false
-python-versions = "*"
-files = [
-    {file = "monotonic-1.6-py2.py3-none-any.whl", hash = "sha256:68687e19a14f11f26d140dd5c86f3dba4bf5df58003000ed467e0e2a69bca96c"},
-    {file = "monotonic-1.6.tar.gz", hash = "sha256:3a55207bcfed53ddd5c5bae174524062935efed17792e9de2ad0205ce9ad63f7"},
-]
-
 [[package]]
 name = "more-itertools"
 version = "10.2.0"
@@ -3433,37 +3296,6 @@ files = [
 llvmlite = "==0.42.*"
 numpy = ">=1.22,<1.27"
 
-[[package]]
-name = "numpy"
-version = "1.22.0"
-description = "NumPy is the fundamental package for array computing with Python."
-optional = false
-python-versions = ">=3.8"
-files = [
-    {file = "numpy-1.22.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:3d22662b4b10112c545c91a0741f2436f8ca979ab3d69d03d19322aa970f9695"},
-    {file = "numpy-1.22.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:11a1f3816ea82eed4178102c56281782690ab5993251fdfd75039aad4d20385f"},
-    {file = "numpy-1.22.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:5dc65644f75a4c2970f21394ad8bea1a844104f0fe01f278631be1c7eae27226"},
-    {file = "numpy-1.22.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:42c16cec1c8cf2728f1d539bd55aaa9d6bb48a7de2f41eb944697293ef65a559"},
-    {file = "numpy-1.22.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a97e82c39d9856fe7d4f9b86d8a1e66eff99cf3a8b7ba48202f659703d27c46f"},
-    {file = "numpy-1.22.0-cp310-cp310-win_amd64.whl", hash = "sha256:e41e8951749c4b5c9a2dc5fdbc1a4eec6ab2a140fdae9b460b0f557eed870f4d"},
-    {file = "numpy-1.22.0-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:bece0a4a49e60e472a6d1f70ac6cdea00f9ab80ff01132f96bd970cdd8a9e5a9"},
-    {file = "numpy-1.22.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:818b9be7900e8dc23e013a92779135623476f44a0de58b40c32a15368c01d471"},
-    {file = "numpy-1.22.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:47ee7a839f5885bc0c63a74aabb91f6f40d7d7b639253768c4199b37aede7982"},
-    {file = "numpy-1.22.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a024181d7aef0004d76fb3bce2a4c9f2e67a609a9e2a6ff2571d30e9976aa383"},
-    {file = "numpy-1.22.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f71d57cc8645f14816ae249407d309be250ad8de93ef61d9709b45a0ddf4050c"},
-    {file = "numpy-1.22.0-cp38-cp38-win32.whl", hash = "sha256:283d9de87c0133ef98f93dfc09fad3fb382f2a15580de75c02b5bb36a5a159a5"},
-    {file = "numpy-1.22.0-cp38-cp38-win_amd64.whl", hash = "sha256:2762331de395739c91f1abb88041f94a080cb1143aeec791b3b223976228af3f"},
-    {file = "numpy-1.22.0-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:76ba7c40e80f9dc815c5e896330700fd6e20814e69da9c1267d65a4d051080f1"},
-    {file = "numpy-1.22.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:0cfe07133fd00b27edee5e6385e333e9eeb010607e8a46e1cd673f05f8596595"},
-    {file = "numpy-1.22.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:6ed0d073a9c54ac40c41a9c2d53fcc3d4d4ed607670b9e7b0de1ba13b4cbfe6f"},
-    {file = "numpy-1.22.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:41388e32e40b41dd56eb37fcaa7488b2b47b0adf77c66154d6b89622c110dfe9"},
-    {file = "numpy-1.22.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b55b953a1bdb465f4dc181758570d321db4ac23005f90ffd2b434cc6609a63dd"},
-    {file = "numpy-1.22.0-cp39-cp39-win32.whl", hash = "sha256:5a311ee4d983c487a0ab546708edbdd759393a3dc9cd30305170149fedd23c88"},
-    {file = "numpy-1.22.0-cp39-cp39-win_amd64.whl", hash = "sha256:a97a954a8c2f046d3817c2bce16e3c7e9a9c2afffaf0400f5c16df5172a67c9c"},
-    {file = "numpy-1.22.0-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bb02929b0d6bfab4c48a79bd805bd7419114606947ec8284476167415171f55b"},
-    {file = "numpy-1.22.0.zip", hash = "sha256:a955e4128ac36797aaffd49ab44ec74a71c11d6938df83b1285492d277db5397"},
-]
-
 [[package]]
 name = "numpy"
 version = "1.26.4"
@@ -3694,57 +3526,54 @@ sympy = "*"
 
 [[package]]
 name = "open-interpreter"
-version = "0.2.5"
+version = "0.2.6"
 description = "Let language models run code"
 optional = false
 python-versions = "<4,>=3.9"
 files = [
-    {file = "open_interpreter-0.2.5-py3-none-any.whl", hash = "sha256:cfe97416e779e29d431900a25238a29afa78c8befd577072d92d3d38d8b6c782"},
-    {file = "open_interpreter-0.2.5.tar.gz", hash = "sha256:67eef85daa23841ba008cdb58388937beab346cfa28a9b84fa319df1fbbddfcc"},
+    {file = "open_interpreter-0.2.6-py3-none-any.whl", hash = "sha256:b00d99935bda0359f3be3a8003d66381ffcb315c2413714dcafaf516d001ed8c"},
+    {file = "open_interpreter-0.2.6.tar.gz", hash = "sha256:bd4cf9455d526bfbc300d7e6f5e3c1c342078f862d496a861235fc2465447703"},
 ]
 
 [package.dependencies]
-aifs = ">=0.0.15,<0.0.16"
 astor = ">=0.8.1,<0.9.0"
-fastapi = ">=0.110.0,<0.111.0"
 git-python = ">=1.0.3,<2.0.0"
 html2image = ">=2.0.4.3,<3.0.0.0"
 inquirer = ">=3.1.3,<4.0.0"
 ipykernel = ">=6.26.0,<7.0.0"
 jupyter-client = ">=8.6.0,<9.0.0"
-litellm = ">=1.34.38,<2.0.0"
+litellm = ">=1.35.32,<2.0.0"
 matplotlib = ">=3.8.2,<4.0.0"
 nltk = ">=3.8.1,<4.0.0"
 platformdirs = ">=4.2.0,<5.0.0"
-posthog = ">=3.1.0,<4.0.0"
-prompt-toolkit = ">=3.0.43,<4.0.0"
 psutil = ">=5.9.6,<6.0.0"
 pydantic = ">=2.6.4,<3.0.0"
 pyreadline3 = {version = ">=3.4.1,<4.0.0", markers = "sys_platform == \"win32\""}
 pyyaml = ">=6.0.1,<7.0.0"
 rich = ">=13.4.2,<14.0.0"
-screeninfo = ">=0.8.1,<0.9.0"
 send2trash = ">=1.8.2,<2.0.0"
+setuptools = "*"
 six = ">=1.16.0,<2.0.0"
 tiktoken = ">=0.6.0,<0.7.0"
 tokentrim = ">=0.1.13,<0.2.0"
 toml = ">=0.10.2,<0.11.0"
-uvicorn = ">=0.27.0,<0.28.0"
 wget = ">=3.2,<4.0"
 
 [package.extras]
-os = ["ipywidgets (>=8.1.2,<9.0.0)", "opencv-python (>=4.8.1.78,<5.0.0.0)", "plyer (>=2.1.0,<3.0.0)", "pyautogui (>=0.9.54,<0.10.0)", "pytesseract (>=0.3.10,<0.4.0)", "pywinctl (>=0.3,<0.4)", "sentence-transformers (>=2.5.1,<3.0.0)", "timm (>=0.9.16,<0.10.0)", "torch (>=2.2.1,<3.0.0)"]
+local = ["einops (>=0.8.0,<0.9.0)", "opencv-python (>=4.8.1.78,<5.0.0.0)", "pytesseract (>=0.3.10,<0.4.0)", "torch (>=2.2.1,<3.0.0)", "torchvision (>=0.18.0,<0.19.0)", "transformers (>=4.40.1,<5.0.0)"]
+os = ["ipywidgets (>=8.1.2,<9.0.0)", "opencv-python (>=4.8.1.78,<5.0.0.0)", "plyer (>=2.1.0,<3.0.0)", "pyautogui (>=0.9.54,<0.10.0)", "pytesseract (>=0.3.10,<0.4.0)", "pywinctl (>=0.3,<0.4)", "screeninfo (>=0.8.1,<0.9.0)", "sentence-transformers (>=2.5.1,<3.0.0)", "timm (>=0.9.16,<0.10.0)", "torch (>=2.2.1,<3.0.0)"]
 safe = ["semgrep (>=1.52.0,<2.0.0)", "yaspin (>=3.0.1,<4.0.0)"]
+server = ["fastapi (>=0.111.0,<0.112.0)", "pynput (>=1.7.7,<2.0.0)", "uvicorn (>=0.30.1,<0.31.0)"]
 
 [[package]]
 name = "openai"
-version = "1.13.3"
+version = "1.30.5"
 description = "The official Python library for the openai API"
 optional = false
 python-versions = ">=3.7.1"
 files = [
-    {file = "openai-1.13.3-py3-none-any.whl", hash = "sha256:5769b62abd02f350a8dd1a3a242d8972c947860654466171d60fb0972ae0a41c"},
-    {file = "openai-1.13.3.tar.gz", hash = "sha256:ff6c6b3bc7327e715e4b3592a923a5a1c7519ff5dd764a83d69f633d49e77a7b"},
+    {file = "openai-1.30.5-py3-none-any.whl", hash = "sha256:2ad95e926de0d2e09cde632a9204b0a6dca4a03c2cdcc84329b01f355784355a"},
+    {file = "openai-1.30.5.tar.gz", hash = "sha256:5366562eb2c5917e6116ae0391b7ae6e3acd62b0ae3f565ada32b35d8fcfa106"},
 ]
 
 [package.dependencies]
@@ -3795,54 +3624,6 @@ files = [
     {file = "packaging-24.0.tar.gz", hash = "sha256:eb82c5e3e56209074766e6885bb04b8c38a0c015d0a30036ebe7ece34c9989e9"},
 ]
 
-[[package]]
-name = "pandas"
-version = "1.5.3"
-description = "Powerful data structures for data analysis, time series, and statistics"
-optional = false
-python-versions = ">=3.8"
-files = [
-    {file = "pandas-1.5.3-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:3749077d86e3a2f0ed51367f30bf5b82e131cc0f14260c4d3e499186fccc4406"},
-    {file = "pandas-1.5.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:972d8a45395f2a2d26733eb8d0f629b2f90bebe8e8eddbb8829b180c09639572"},
-    {file = "pandas-1.5.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:50869a35cbb0f2e0cd5ec04b191e7b12ed688874bd05dd777c19b28cbea90996"},
-    {file = "pandas-1.5.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c3ac844a0fe00bfaeb2c9b51ab1424e5c8744f89860b138434a363b1f620f354"},
-    {file = "pandas-1.5.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7a0a56cef15fd1586726dace5616db75ebcfec9179a3a55e78f72c5639fa2a23"},
-    {file = "pandas-1.5.3-cp310-cp310-win_amd64.whl", hash = "sha256:478ff646ca42b20376e4ed3fa2e8d7341e8a63105586efe54fa2508ee087f328"},
-    {file = "pandas-1.5.3-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:6973549c01ca91ec96199e940495219c887ea815b2083722821f1d7abfa2b4dc"},
-    {file = "pandas-1.5.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:c39a8da13cede5adcd3be1182883aea1c925476f4e84b2807a46e2775306305d"},
-    {file = "pandas-1.5.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:f76d097d12c82a535fda9dfe5e8dd4127952b45fea9b0276cb30cca5ea313fbc"},
-    {file = "pandas-1.5.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e474390e60ed609cec869b0da796ad94f420bb057d86784191eefc62b65819ae"},
-    {file = "pandas-1.5.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5f2b952406a1588ad4cad5b3f55f520e82e902388a6d5a4a91baa8d38d23c7f6"},
-    {file = "pandas-1.5.3-cp311-cp311-win_amd64.whl", hash = "sha256:bc4c368f42b551bf72fac35c5128963a171b40dce866fb066540eeaf46faa003"},
-    {file = "pandas-1.5.3-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:14e45300521902689a81f3f41386dc86f19b8ba8dd5ac5a3c7010ef8d2932813"},
-    {file = "pandas-1.5.3-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:9842b6f4b8479e41968eced654487258ed81df7d1c9b7b870ceea24ed9459b31"},
-    {file = "pandas-1.5.3-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:26d9c71772c7afb9d5046e6e9cf42d83dd147b5cf5bcb9d97252077118543792"},
-    {file = "pandas-1.5.3-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5fbcb19d6fceb9e946b3e23258757c7b225ba450990d9ed63ccceeb8cae609f7"},
-    {file = "pandas-1.5.3-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:565fa34a5434d38e9d250af3c12ff931abaf88050551d9fbcdfafca50d62babf"},
-    {file = "pandas-1.5.3-cp38-cp38-win32.whl", hash = "sha256:87bd9c03da1ac870a6d2c8902a0e1fd4267ca00f13bc494c9e5a9020920e1d51"},
-    {file = "pandas-1.5.3-cp38-cp38-win_amd64.whl", hash = "sha256:41179ce559943d83a9b4bbacb736b04c928b095b5f25dd2b7389eda08f46f373"},
-    {file = "pandas-1.5.3-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:c74a62747864ed568f5a82a49a23a8d7fe171d0c69038b38cedf0976831296fa"},
-    {file = "pandas-1.5.3-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:c4c00e0b0597c8e4f59e8d461f797e5d70b4d025880516a8261b2817c47759ee"},
-    {file = "pandas-1.5.3-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:a50d9a4336a9621cab7b8eb3fb11adb82de58f9b91d84c2cd526576b881a0c5a"},
-    {file = "pandas-1.5.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:dd05f7783b3274aa206a1af06f0ceed3f9b412cf665b7247eacd83be41cf7bf0"},
-    {file = "pandas-1.5.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9f69c4029613de47816b1bb30ff5ac778686688751a5e9c99ad8c7031f6508e5"},
-    {file = "pandas-1.5.3-cp39-cp39-win32.whl", hash = "sha256:7cec0bee9f294e5de5bbfc14d0573f65526071029d036b753ee6507d2a21480a"},
-    {file = "pandas-1.5.3-cp39-cp39-win_amd64.whl", hash = "sha256:dfd681c5dc216037e0b0a2c821f5ed99ba9f03ebcf119c7dac0e9a7b960b9ec9"},
-    {file = "pandas-1.5.3.tar.gz", hash = "sha256:74a3fd7e5a7ec052f183273dc7b0acd3a863edf7520f5d3a1765c04ffdb3b0b1"},
-]
-
-[package.dependencies]
-numpy = [
-    {version = ">=1.20.3", markers = "python_version < \"3.10\""},
-    {version = ">=1.23.2", markers = "python_version >= \"3.11\""},
-    {version = ">=1.21.0", markers = "python_version >= \"3.10\" and python_version < \"3.11\""},
-]
-python-dateutil = ">=2.8.1"
-pytz = ">=2020.1"
-
-[package.extras]
-test = ["hypothesis (>=5.5.3)", "pytest (>=6.0)", "pytest-xdist (>=1.31)"]
-
 [[package]]
 name = "parso"
 version = "0.8.4"
@@ -4021,29 +3802,6 @@ progress = ["tqdm (>=4.41.0,<5.0.0)"]
 sftp = ["paramiko (>=2.7.0)"]
 xxhash = ["xxhash (>=1.4.3)"]
 
-[[package]]
-name = "posthog"
-version = "3.5.0"
-description = "Integrate PostHog into any python application."
-optional = false
-python-versions = "*"
-files = [
-    {file = "posthog-3.5.0-py2.py3-none-any.whl", hash = "sha256:3c672be7ba6f95d555ea207d4486c171d06657eb34b3ce25eb043bfe7b6b5b76"},
-    {file = "posthog-3.5.0.tar.gz", hash = "sha256:8f7e3b2c6e8714d0c0c542a2109b83a7549f63b7113a133ab2763a89245ef2ef"},
-]
-
-[package.dependencies]
-backoff = ">=1.10.0"
-monotonic = ">=1.5"
-python-dateutil = ">2.1"
-requests = ">=2.7,<3.0"
-six = ">=1.5"
-
-[package.extras]
-dev = ["black", "flake8", "flake8-print", "isort", "pre-commit"]
-sentry = ["django", "sentry-sdk"]
-test = ["coverage", "flake8", "freezegun (==0.3.15)", "mock (>=2.0.0)", "pylint", "pytest", "pytest-timeout"]
-
 [[package]]
 name = "pre-commit"
 version = "3.7.1"
@@ -7130,17 +6888,6 @@ files = [
     {file = "pyperclip-1.8.2.tar.gz", hash = "sha256:105254a8b04934f0bc84e9c24eb360a591aaf6535c9def5f29d92af107a9bf57"},
 ]
 
-[[package]]
-name = "pypinyin"
-version = "0.51.0"
-description = "汉字拼音转换模块/工具."
-optional = false
-python-versions = ">=2.6, !=3.0.*, !=3.1.*, !=3.2.*, <4"
-files = [
-    {file = "pypinyin-0.51.0-py2.py3-none-any.whl", hash = "sha256:ae8878f08fee15d0c5c11053a737e68a4158c22c63dc632b4de060af5c95bf84"},
-    {file = "pypinyin-0.51.0.tar.gz", hash = "sha256:cede34fc35a79ef6c799f161e2c280e7b6755ee072fb741cae5ce2a60c4ae0c5"},
-]
-
 [[package]]
 name = "pypiwin32"
 version = "223"
@@ -7691,26 +7438,27 @@ webrtcvad = "2.0.10"
 
 [[package]]
 name = "realtimetts"
-version = "0.3.46"
+version = "0.4.1"
 description = "*Stream text into audio with an easy-to-use, highly configurable library delivering voice output with minimal latency."
 optional = false
 python-versions = "<3.12,>=3.9"
 files = [
-    {file = "RealTimeTTS-0.3.46-py3-none-any.whl", hash = "sha256:40b39b0cd38bfae22093df14069ce77d121992c5f9383690abad55bd3f2923c6"},
-    {file = "RealTimeTTS-0.3.46.tar.gz", hash = "sha256:e4a618d7784606e7cbc661c392700cd0f691c70314661f1b7f89eb153b5e655d"},
+    {file = "RealTimeTTS-0.4.1-py3-none-any.whl", hash = "sha256:916483016ffabbf7c3e6fb489dc1bd693ff08fb4cd139ea634cacc88bce7c7d2"},
+    {file = "RealTimeTTS-0.4.1.tar.gz", hash = "sha256:4564400c5a96a3e79b251956f2585849ca1494cdbc36737733b86f64e71e4032"},
 ]
 
 [package.dependencies]
-azure-cognitiveservices-speech = "1.36.0"
-elevenlabs = "0.2.27"
-openai = "1.13.3"
+azure-cognitiveservices-speech = "1.37.0"
+coqui-tts = "0.24.1"
+elevenlabs = "1.2.2"
+gtts = "2.5.1"
+openai = "1.30.5"
 PyAudio = "0.2.14"
 pydub = "0.25.1"
 pyttsx3 = "2.90"
-requests = "2.31.0"
+requests = "2.32.3"
 stream2sentence = "0.2.3"
-tqdm = "4.66.2"
-TTS = "0.22.0"
+tqdm = "4.66.4"
 
 [[package]]
 name = "regex"
@@ -7802,13 +7550,13 @@ files = [
 
 [[package]]
 name = "requests"
-version = "2.31.0"
+version = "2.32.3"
 description = "Python HTTP for Humans."
 optional = false
-python-versions = ">=3.7"
+python-versions = ">=3.8"
 files = [
-    {file = "requests-2.31.0-py3-none-any.whl", hash = "sha256:58cd2187c01e70e6e26505bca751777aa9f2ee0b7f4300988b709f44e013003f"},
-    {file = "requests-2.31.0.tar.gz", hash = "sha256:942c5a758f98d790eaed1a29cb6eefc7ffb0d1cf7af05c3d2791656dbd6ad1e1"},
+    {file = "requests-2.32.3-py3-none-any.whl", hash = "sha256:70761cfe03c773ceb22aa2f671b4757976145175cdfca038c02654d061d6dcc6"},
+    {file = "requests-2.32.3.tar.gz", hash = "sha256:55365417734eb18255590a9ff9eb97e9e1da868d4ccd6402399eaf68af20a760"},
 ]
 
 [package.dependencies]
@@ -8035,48 +7783,6 @@ install = ["joblib (>=1.2.0)", "numpy (>=1.19.5)", "scipy (>=1.6.0)", "threadpoo
 maintenance = ["conda-lock (==2.5.6)"]
 tests = ["black (>=24.3.0)", "matplotlib (>=3.3.4)", "mypy (>=1.9)", "numpydoc (>=1.2.0)", "pandas (>=1.1.5)", "polars (>=0.20.23)", "pooch (>=1.6.0)", "pyamg (>=4.0.0)", "pyarrow (>=12.0.0)", "pytest (>=7.1.2)", "pytest-cov (>=2.9.0)", "ruff (>=0.2.1)", "scikit-image (>=0.17.2)"]
 
-[[package]]
-name = "scipy"
-version = "1.11.4"
-description = "Fundamental algorithms for scientific computing in Python"
-optional = false
-python-versions = ">=3.9"
-files = [
-    {file = "scipy-1.11.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:bc9a714581f561af0848e6b69947fda0614915f072dfd14142ed1bfe1b806710"},
-    {file = "scipy-1.11.4-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:cf00bd2b1b0211888d4dc75656c0412213a8b25e80d73898083f402b50f47e41"},
-    {file = "scipy-1.11.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b9999c008ccf00e8fbcce1236f85ade5c569d13144f77a1946bef8863e8f6eb4"},
-    {file = "scipy-1.11.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:933baf588daa8dc9a92c20a0be32f56d43faf3d1a60ab11b3f08c356430f6e56"},
-    {file = "scipy-1.11.4-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:8fce70f39076a5aa62e92e69a7f62349f9574d8405c0a5de6ed3ef72de07f446"},
-    {file = "scipy-1.11.4-cp310-cp310-win_amd64.whl", hash = "sha256:6550466fbeec7453d7465e74d4f4b19f905642c89a7525571ee91dd7adabb5a3"},
-    {file = "scipy-1.11.4-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:f313b39a7e94f296025e3cffc2c567618174c0b1dde173960cf23808f9fae4be"},
-    {file = "scipy-1.11.4-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:1b7c3dca977f30a739e0409fb001056484661cb2541a01aba0bb0029f7b68db8"},
-    {file = "scipy-1.11.4-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:00150c5eae7b610c32589dda259eacc7c4f1665aedf25d921907f4d08a951b1c"},
-    {file = "scipy-1.11.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:530f9ad26440e85766509dbf78edcfe13ffd0ab7fec2560ee5c36ff74d6269ff"},
-    {file = "scipy-1.11.4-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:5e347b14fe01003d3b78e196e84bd3f48ffe4c8a7b8a1afbcb8f5505cb710993"},
-    {file = "scipy-1.11.4-cp311-cp311-win_amd64.whl", hash = "sha256:acf8ed278cc03f5aff035e69cb511741e0418681d25fbbb86ca65429c4f4d9cd"},
-    {file = "scipy-1.11.4-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:028eccd22e654b3ea01ee63705681ee79933652b2d8f873e7949898dda6d11b6"},
-    {file = "scipy-1.11.4-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:2c6ff6ef9cc27f9b3db93a6f8b38f97387e6e0591600369a297a50a8e96e835d"},
-    {file = "scipy-1.11.4-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b030c6674b9230d37c5c60ab456e2cf12f6784596d15ce8da9365e70896effc4"},
-    {file = "scipy-1.11.4-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ad669df80528aeca5f557712102538f4f37e503f0c5b9541655016dd0932ca79"},
-    {file = "scipy-1.11.4-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:ce7fff2e23ab2cc81ff452a9444c215c28e6305f396b2ba88343a567feec9660"},
-    {file = "scipy-1.11.4-cp312-cp312-win_amd64.whl", hash = "sha256:36750b7733d960d7994888f0d148d31ea3017ac15eef664194b4ef68d36a4a97"},
-    {file = "scipy-1.11.4-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:6e619aba2df228a9b34718efb023966da781e89dd3d21637b27f2e54db0410d7"},
-    {file = "scipy-1.11.4-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:f3cd9e7b3c2c1ec26364856f9fbe78695fe631150f94cd1c22228456404cf1ec"},
-    {file = "scipy-1.11.4-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d10e45a6c50211fe256da61a11c34927c68f277e03138777bdebedd933712fea"},
-    {file = "scipy-1.11.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:91af76a68eeae0064887a48e25c4e616fa519fa0d38602eda7e0f97d65d57937"},
-    {file = "scipy-1.11.4-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:6df1468153a31cf55ed5ed39647279beb9cfb5d3f84369453b49e4b8502394fd"},
-    {file = "scipy-1.11.4-cp39-cp39-win_amd64.whl", hash = "sha256:ee410e6de8f88fd5cf6eadd73c135020bfbbbdfcd0f6162c36a7638a1ea8cc65"},
-    {file = "scipy-1.11.4.tar.gz", hash = "sha256:90a2b78e7f5733b9de748f589f09225013685f9b218275257f8a8168ededaeaa"},
-]
-
-[package.dependencies]
-numpy = ">=1.21.6,<1.28.0"
-
-[package.extras]
-dev = ["click", "cython-lint (>=0.12.2)", "doit (>=0.36.0)", "mypy", "pycodestyle", "pydevtool", "rich-click", "ruff", "types-psutil", "typing_extensions"]
-doc = ["jupytext", "matplotlib (>2)", "myst-nb", "numpydoc", "pooch", "pydata-sphinx-theme (==0.9.0)", "sphinx (!=4.1.0)", "sphinx-design (>=0.2.0)"]
-test = ["asv", "gmpy2", "mpmath", "pooch", "pytest", "pytest-cov", "pytest-timeout", "pytest-xdist", "scikit-umfpack", "threadpoolctl"]
-
 [[package]]
 name = "scipy"
 version = "1.13.1"
@@ -8119,21 +7825,6 @@ dev = ["cython-lint (>=0.12.2)", "doit (>=0.36.0)", "mypy", "pycodestyle", "pyde
 doc = ["jupyterlite-pyodide-kernel", "jupyterlite-sphinx (>=0.12.0)", "jupytext", "matplotlib (>=3.5)", "myst-nb", "numpydoc", "pooch", "pydata-sphinx-theme (>=0.15.2)", "sphinx (>=5.0.0)", "sphinx-design (>=0.4.0)"]
 test = ["array-api-strict", "asv", "gmpy2", "hypothesis (>=6.30)", "mpmath", "pooch", "pytest", "pytest-cov", "pytest-timeout", "pytest-xdist", "scikit-umfpack", "threadpoolctl"]
 
-[[package]]
-name = "screeninfo"
-version = "0.8.1"
-description = "Fetch location and size of physical screens."
-optional = false
-python-versions = ">=3.6.2,<4.0.0"
-files = [
-    {file = "screeninfo-0.8.1-py3-none-any.whl", hash = "sha256:e97d6b173856edcfa3bd282f81deb528188aff14b11ec3e195584e7641be733c"},
-    {file = "screeninfo-0.8.1.tar.gz", hash = "sha256:9983076bcc7e34402a1a9e4d7dabf3729411fd2abb3f3b4be7eba73519cd2ed1"},
-]
-
-[package.dependencies]
-Cython = {version = "*", markers = "sys_platform == \"darwin\""}
-pyobjc-framework-Cocoa = {version = "*", markers = "sys_platform == \"darwin\""}
-
 [[package]]
 name = "send2trash"
 version = "1.8.3"
@@ -8150,6 +7841,56 @@ nativelib = ["pyobjc-framework-Cocoa", "pywin32"]
 objc = ["pyobjc-framework-Cocoa"]
 win32 = ["pywin32"]
 
+[[package]]
+name = "sentry-sdk"
+version = "2.4.0"
+description = "Python client for Sentry (https://sentry.io)"
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "sentry_sdk-2.4.0-py2.py3-none-any.whl", hash = "sha256:a42b70981cd4ed7da3c85d0360502d2ac932a15a4a420b360e1ebded2fc19a92"},
+    {file = "sentry_sdk-2.4.0.tar.gz", hash = "sha256:62b9bb0489e731ecbce008f9647899b51d220067a75c3adfd46f8187660c0029"},
+]
+
+[package.dependencies]
+certifi = "*"
+urllib3 = ">=1.26.11"
+
+[package.extras]
+aiohttp = ["aiohttp (>=3.5)"]
+anthropic = ["anthropic (>=0.16)"]
+arq = ["arq (>=0.23)"]
+asyncpg = ["asyncpg (>=0.23)"]
+beam = ["apache-beam (>=2.12)"]
+bottle = ["bottle (>=0.12.13)"]
+celery = ["celery (>=3)"]
+celery-redbeat = ["celery-redbeat (>=2)"]
+chalice = ["chalice (>=1.16.0)"]
+clickhouse-driver = ["clickhouse-driver (>=0.2.0)"]
+django = ["django (>=1.8)"]
+falcon = ["falcon (>=1.4)"]
+fastapi = ["fastapi (>=0.79.0)"]
+flask = ["blinker (>=1.1)", "flask (>=0.11)", "markupsafe"]
+grpcio = ["grpcio (>=1.21.1)", "protobuf (>=3.8.0)"]
+httpx = ["httpx (>=0.16.0)"]
+huey = ["huey (>=2)"]
+huggingface-hub = ["huggingface-hub (>=0.22)"]
+langchain = ["langchain (>=0.0.210)"]
+loguru = ["loguru (>=0.5)"]
+openai = ["openai (>=1.0.0)", "tiktoken (>=0.3.0)"]
+opentelemetry = ["opentelemetry-distro (>=0.35b0)"]
+opentelemetry-experimental = ["opentelemetry-distro (>=0.40b0,<1.0)", "opentelemetry-instrumentation-aiohttp-client (>=0.40b0,<1.0)", "opentelemetry-instrumentation-django (>=0.40b0,<1.0)", "opentelemetry-instrumentation-fastapi (>=0.40b0,<1.0)", "opentelemetry-instrumentation-flask (>=0.40b0,<1.0)", "opentelemetry-instrumentation-requests (>=0.40b0,<1.0)", "opentelemetry-instrumentation-sqlite3 (>=0.40b0,<1.0)", "opentelemetry-instrumentation-urllib (>=0.40b0,<1.0)"]
+pure-eval = ["asttokens", "executing", "pure-eval"]
+pymongo = ["pymongo (>=3.1)"]
+pyspark = ["pyspark (>=2.4.4)"]
+quart = ["blinker (>=1.1)", "quart (>=0.16.1)"]
+rq = ["rq (>=0.6)"]
+sanic = ["sanic (>=0.8)"]
+sqlalchemy = ["sqlalchemy (>=1.2)"]
+starlette = ["starlette (>=0.19.1)"]
+starlite = ["starlite (>=1.48)"]
+tornado = ["tornado (>=5)"]
+
 [[package]]
 name = "setuptools"
 version = "70.0.0"
@@ -9100,13 +8841,13 @@ files = [
 
 [[package]]
 name = "tqdm"
-version = "4.66.2"
+version = "4.66.4"
 description = "Fast, Extensible Progress Meter"
 optional = false
 python-versions = ">=3.7"
 files = [
-    {file = "tqdm-4.66.2-py3-none-any.whl", hash = "sha256:1ee4f8a893eb9bef51c6e35730cebf234d5d0b6bd112b0271e10ed7c24a02bd9"},
-    {file = "tqdm-4.66.2.tar.gz", hash = "sha256:6cd52cdf0fef0e0f543299cfc96fec90d7b8a7e88745f411ec33eb44d5ed3531"},
+    {file = "tqdm-4.66.4-py3-none-any.whl", hash = "sha256:b75ca56b413b030bc3f00af51fd2c1a1a5eac6a0c1cca83cbb37a5c52abce644"},
+    {file = "tqdm-4.66.4.tar.gz", hash = "sha256:e4d936c9de8727928f3be6079590e97d9abfe8d39a590be678eb5919ffc186bb"},
 ]
 
 [package.dependencies]
@@ -9118,30 +8859,6 @@ notebook = ["ipywidgets (>=6)"]
 slack = ["slack-sdk"]
 telegram = ["requests"]
 
-[[package]]
-name = "trainer"
-version = "0.0.36"
-description = "General purpose model trainer for PyTorch that is more flexible than it should be, by 🐸Coqui."
-optional = false
-python-versions = ">=3.6.0, <3.12"
-files = [
-    {file = "trainer-0.0.36-py3-none-any.whl", hash = "sha256:d986702c6d6d988e74a4f8da0f9c11a8c7d89274a11436957e91217a19b487a6"},
-    {file = "trainer-0.0.36.tar.gz", hash = "sha256:3afff4d1ce70f828d32ba698331768bca5be1cc21a60c2b8acd8fa117eb95c5a"},
-]
-
-[package.dependencies]
-coqpit = "*"
-fsspec = "*"
-psutil = "*"
-soundfile = "*"
-tensorboard = "*"
-torch = ">=1.7"
-
-[package.extras]
-all = ["accelerate", "black", "coqpit", "coverage", "fsspec", "isort", "psutil", "pylint", "pytest", "soundfile", "tensorboard", "torch (>=1.7)", "torchvision"]
-dev = ["accelerate", "black", "coverage", "isort", "pylint", "pytest"]
-test = ["torchvision"]
-
 [[package]]
 name = "traitlets"
 version = "5.14.3"
@@ -9248,69 +8965,6 @@ build = ["cmake (>=3.20)", "lit"]
 tests = ["autopep8", "flake8", "isort", "numpy", "pytest", "scipy (>=1.7.1)", "torch"]
 tutorials = ["matplotlib", "pandas", "tabulate", "torch"]
 
-[[package]]
-name = "tts"
-version = "0.22.0"
-description = "Deep learning for Text to Speech by Coqui."
-optional = false
-python-versions = ">=3.9.0, <3.12"
-files = [
-    {file = "TTS-0.22.0-cp310-cp310-manylinux1_x86_64.whl", hash = "sha256:6dce2e3a9434bd4d3815b51f4080ccdddd82466cf40fc0e0a70eff14b7cc1d3f"},
-    {file = "TTS-0.22.0-cp311-cp311-manylinux1_x86_64.whl", hash = "sha256:332cdf63a7d9f91dcb38c50c3e778a8080b3551cd4e1a901cfc58acb90cd3f58"},
-    {file = "TTS-0.22.0-cp39-cp39-manylinux1_x86_64.whl", hash = "sha256:9d75e27e5998f379d72f04192e3cf0f5cf939c08c0f71bb74ef1cf9ccc4fa499"},
-    {file = "TTS-0.22.0.tar.gz", hash = "sha256:b91119da7ff2ae7b3dae7328edf9af4db3b48c40eb4ce15d11ed8f5ee9bd7086"},
-]
-
-[package.dependencies]
-aiohttp = ">=3.8.1"
-anyascii = ">=0.3.0"
-bangla = "*"
-bnnumerizer = "*"
-bnunicodenormalizer = "*"
-coqpit = ">=0.0.16"
-cython = ">=0.29.30"
-einops = ">=0.6.0"
-encodec = ">=0.1.1"
-flask = ">=2.0.1"
-fsspec = ">=2023.6.0"
-g2pkk = ">=0.1.1"
-gruut = {version = "2.2.3", extras = ["de", "es", "fr"]}
-hangul-romanize = "*"
-inflect = ">=5.6.0"
-jamo = "*"
-jieba = "*"
-librosa = ">=0.10.0"
-matplotlib = ">=3.7.0"
-nltk = "*"
-num2words = "*"
-numba = {version = ">=0.57.0", markers = "python_version >= \"3.9\""}
-numpy = [
-    {version = "1.22.0", markers = "python_version <= \"3.10\""},
-    {version = ">=1.24.3", markers = "python_version > \"3.10\""},
-]
-packaging = ">=23.1"
-pandas = ">=1.4,<2.0"
-pypinyin = "*"
-pysbd = ">=0.3.4"
-pyyaml = ">=6.0"
-scikit-learn = ">=1.3.0"
-scipy = ">=1.11.2"
-soundfile = ">=0.12.0"
-spacy = {version = ">=3", extras = ["ja"]}
-torch = ">=2.1"
-torchaudio = "*"
-tqdm = ">=4.64.1"
-trainer = ">=0.0.32"
-transformers = ">=4.33.0"
-umap-learn = ">=0.5.1"
-unidecode = ">=1.3.2"
-
-[package.extras]
-all = ["black", "bokeh (==1.4.0)", "coverage", "cutlet", "isort", "mecab-python3 (==1.0.6)", "nose2", "pylint (==2.10.2)", "unidic-lite (==1.0.8)"]
-dev = ["black", "coverage", "isort", "nose2", "pylint (==2.10.2)"]
-ja = ["cutlet", "mecab-python3 (==1.0.6)", "unidic-lite (==1.0.8)"]
-notebooks = ["bokeh (==1.4.0)"]
-
 [[package]]
 name = "typeguard"
 version = "4.3.0"
@@ -9428,17 +9082,6 @@ parametric-umap = ["tensorflow (>=2.1)"]
 plot = ["bokeh", "colorcet", "datashader", "holoviews", "matplotlib", "pandas", "scikit-image", "seaborn"]
 tbb = ["tbb (>=2019.0)"]
 
-[[package]]
-name = "unidecode"
-version = "1.3.8"
-description = "ASCII transliterations of Unicode text"
-optional = false
-python-versions = ">=3.5"
-files = [
-    {file = "Unidecode-1.3.8-py3-none-any.whl", hash = "sha256:d130a61ce6696f8148a3bd8fe779c99adeb4b870584eeb9526584e9aa091fd39"},
-    {file = "Unidecode-1.3.8.tar.gz", hash = "sha256:cfdb349d46ed3873ece4586b96aa75258726e2fa8ec21d6f00a591d98806c2f4"},
-]
-
 [[package]]
 name = "urllib3"
 version = "2.2.1"
@@ -9811,4 +9454,4 @@ testing = ["big-O", "jaraco.functools", "jaraco.itertools", "jaraco.test", "more
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.9,<3.12"
-content-hash = "4485960e763dd7bfc94c700a5858750a1d6abb660455fe6ee51896779bfac4f5"
+content-hash = "de07d24f74d39335d2c89d83cbe681bacbeaeffdb30227cb9f6955dc4614dfca"
diff --git a/software/pyproject.toml b/software/pyproject.toml
index 44498175..ab54d5c6 100644
--- a/software/pyproject.toml
+++ b/software/pyproject.toml
@@ -33,19 +33,20 @@ python-crontab = "^3.0.0"
 inquirer = "^3.2.4"
 pyqrcode = "^1.2.1"
 realtimestt = "^0.1.12"
-realtimetts = "^0.3.44"
+realtimetts = "^0.4.1"
 keyboard = "^0.13.5"
 pyautogui = "^0.9.54"
 ctranslate2 = "4.1.0"
 py3-tts = "^3.5"
-elevenlabs = "0.2.27"
+elevenlabs = "1.2.2"
 groq = "^0.5.0"
-open-interpreter = "^0.2.5"
+open-interpreter = "^0.2.6"
 litellm = "1.35.35"
-openai = "1.13.3"
+openai = "1.30.5"
 pywebview = "*"
 pyobjc = "*"
 
+sentry-sdk = "^2.4.0"
 [build-system]
 requires = ["poetry-core"]
 build-backend = "poetry.core.masonry.api"
diff --git a/software/source/clients/base_device.py b/software/source/clients/base_device.py
index 9013e07b..923ee9e1 100644
--- a/software/source/clients/base_device.py
+++ b/software/source/clients/base_device.py
@@ -2,6 +2,7 @@
 
 load_dotenv()  # take environment variables from .env.
 
+import subprocess
 import os
 import sys
 import asyncio
@@ -46,7 +47,7 @@
 CHUNK = 1024  # Record in chunks of 1024 samples
 FORMAT = pyaudio.paInt16  # 16 bits per sample
 CHANNELS = 1  # Mono
-RATE = 44100  # Sample rate
+RATE = 16000  # Sample rate
 RECORDING = False  # Flag to control recording state
 SPACEBAR_PRESSED = False  # Flag to track spacebar press state
 
@@ -86,10 +87,10 @@ class Device:
     def __init__(self):
         self.pressed_keys = set()
         self.captured_images = []
-        self.audiosegments = []
+        self.audiosegments = asyncio.Queue()
         self.server_url = ""
         self.ctrl_pressed = False
-        # self.latency = None
+        self.playback_latency = None
 
     def fetch_image_from_camera(self, camera_index=CAMERA_DEVICE_INDEX):
         """Captures an image from the specified camera device and saves it to a temporary file. Adds the image to the captured_images list."""
@@ -153,14 +154,26 @@ async def play_audiosegments(self):
         """Plays them sequentially."""
         while True:
             try:
-                for audio in self.audiosegments:
-                    # if self.latency:
-                    #    elapsed_time = time.time() - self.latency
-                    #    print(f"Time from request to playback: {elapsed_time} seconds")
-                    #    self.latency = None
-                    play(audio)
-                    self.audiosegments.remove(audio)
-                await asyncio.sleep(0.1)
+                audio = await self.audiosegments.get()
+                # print("got audio segment!!!!")
+                if self.playback_latency:
+                    elapsed_time = time.time() - self.playback_latency
+                    print(f"Time from request to playback: {elapsed_time} seconds")
+                    self.playback_latency = None
+
+                args = ["ffplay", "-autoexit", "-", "-nodisp"]
+                proc = subprocess.Popen(
+                    args=args,
+                    stdout=subprocess.PIPE,
+                    stdin=subprocess.PIPE,
+                    stderr=subprocess.PIPE,
+                )
+                out, err = proc.communicate(input=audio)
+                proc.poll()
+
+                # play(audio)
+                # self.audiosegments.remove(audio)
+                # await asyncio.sleep(0.1)
             except asyncio.exceptions.CancelledError:
                 # This happens once at the start?
                 pass
@@ -208,7 +221,7 @@ def record_audio(self):
         stream.stop_stream()
         stream.close()
         print("Recording stopped.")
-        # self.latency = time.time()
+        self.playback_latency = time.time()
 
         duration = wav_file.getnframes() / RATE
         if duration < 0.3:
@@ -315,18 +328,21 @@ def on_release(self, key):
 
     async def message_sender(self, websocket):
         while True:
-            message = await asyncio.get_event_loop().run_in_executor(
-                None, send_queue.get
-            )
+            try:
+                message = await asyncio.get_event_loop().run_in_executor(
+                    None, send_queue.get
+                )
 
-            if isinstance(message, bytes):
-                await websocket.send(message)
+                if isinstance(message, bytes):
+                    await websocket.send(message)
 
-            else:
-                await websocket.send(json.dumps(message))
+                else:
+                    await websocket.send(json.dumps(message))
 
-            send_queue.task_done()
-            await asyncio.sleep(0.01)
+                send_queue.task_done()
+                await asyncio.sleep(0.01)
+            except:
+                traceback.print_exc()
 
     async def websocket_communication(self, WS_URL):
         print("websocket communication was called!!!!")
@@ -343,7 +359,7 @@ async def exec_ws_communication(websocket):
             asyncio.create_task(self.message_sender(websocket))
 
             while True:
-                await asyncio.sleep(0.01)
+                await asyncio.sleep(0.0001)
                 chunk = await websocket.recv()
 
                 logger.debug(f"Got this message from the server: {type(chunk)} {chunk}")
@@ -351,31 +367,38 @@ async def exec_ws_communication(websocket):
                 if type(chunk) == str:
                     chunk = json.loads(chunk)
 
-                message = accumulator.accumulate(chunk)
+                # message = accumulator.accumulate(chunk)
+                message = chunk
                 if message == None:
                     # Will be None until we have a full message ready
                     continue
 
                 # At this point, we have our message
+                # print("checkpoint reached!", message)
+                if isinstance(message, bytes):
 
-                if message["type"] == "audio" and message["format"].startswith("bytes"):
+                    # if message["type"] == "audio" and message["format"].startswith("bytes"):
                     # Convert bytes to audio file
 
-                    audio_bytes = message["content"]
+                    # audio_bytes = message["content"]
+                    audio_bytes = message
 
                     # Create an AudioSegment instance with the raw data
+                    """
                     audio = AudioSegment(
                         # raw audio data (bytes)
                         data=audio_bytes,
                         # signed 16-bit little-endian format
                         sample_width=2,
-                        # 16,000 Hz frame rate
-                        frame_rate=16000,
+                        # 24,000 Hz frame rate
+                        frame_rate=24000,
                         # mono sound
                         channels=1,
                     )
+                    """
 
-                    self.audiosegments.append(audio)
+                    # print("audio segment was created")
+                    await self.audiosegments.put(audio_bytes)
 
                 # Run the code if that's the client's job
                 if os.getenv("CODE_RUNNER") == "client":
@@ -399,6 +422,7 @@ async def exec_ws_communication(websocket):
             while True:
                 try:
                     async with websockets.connect(WS_URL) as websocket:
+                        print("awaiting exec_ws_communication")
                         await exec_ws_communication(websocket)
                 except:
                     logger.info(traceback.format_exc())
@@ -410,7 +434,7 @@ async def exec_ws_communication(websocket):
     async def start_async(self):
         print("start async was called!!!!!")
         # Configuration for WebSocket
-        WS_URL = f"ws://{self.server_url}"
+        WS_URL = f"ws://{self.server_url}/ws"
         # Start the WebSocket communication
         asyncio.create_task(self.websocket_communication(WS_URL))
 
diff --git a/software/source/server/async_interpreter.py b/software/source/server/async_interpreter.py
index e601e561..b4a11d3f 100644
--- a/software/source/server/async_interpreter.py
+++ b/software/source/server/async_interpreter.py
@@ -12,7 +12,14 @@
 ###
 
 from pynput import keyboard
-from RealtimeTTS import TextToAudioStream, OpenAIEngine, CoquiEngine
+from RealtimeTTS import (
+    TextToAudioStream,
+    OpenAIEngine,
+    CoquiEngine,
+    ElevenlabsEngine,
+    SystemEngine,
+    GTTSEngine,
+)
 from RealtimeSTT import AudioToTextRecorder
 import time
 import asyncio
@@ -21,11 +28,14 @@
 
 class AsyncInterpreter:
     def __init__(self, interpreter):
+        self.stt_latency = None
+        self.tts_latency = None
+        self.interpreter_latency = None
         self.interpreter = interpreter
 
         # STT
         self.stt = AudioToTextRecorder(
-            model="tiny", spinner=False, use_microphone=False
+            model="tiny.en", spinner=False, use_microphone=False
         )
         self.stt.stop()  # It needs this for some reason
 
@@ -34,6 +44,16 @@ def __init__(self, interpreter):
             engine = CoquiEngine()
         elif self.interpreter.tts == "openai":
             engine = OpenAIEngine()
+        elif self.interpreter.tts == "gtts":
+            engine = GTTSEngine()
+        elif self.interpreter.tts == "elevenlabs":
+            engine = ElevenlabsEngine(
+                api_key="sk_077cb1cabdf67e62b85f8782e66e5d8e11f78b450c7ce171"
+            )
+        elif self.interpreter.tts == "system":
+            engine = SystemEngine()
+        else:
+            raise ValueError(f"Unsupported TTS engine: {self.interpreter.tts}")
         self.tts = TextToAudioStream(engine)
 
         self.active_chat_messages = []
@@ -112,7 +132,11 @@ async def run(self):
 
         # print("INPUT QUEUE:", input_queue)
         # message = [i for i in input_queue if i["type"] == "message"][0]["content"]
+        start_stt = time.time()
         message = self.stt.text()
+        end_stt = time.time()
+        self.stt_latency = end_stt - start_stt
+        print("STT LATENCY", self.stt_latency)
 
         # print(message)
 
@@ -141,7 +165,7 @@ def generate(message):
 
                         # Experimental: The AI voice sounds better with replacements like these, but it should happen at the TTS layer
                         # content = content.replace(". ", ". ... ").replace(", ", ", ... ").replace("!", "! ... ").replace("?", "? ... ")
-
+                        print("yielding this", content)
                         yield content
 
                 # Handle code blocks
@@ -172,17 +196,24 @@ def generate(message):
                             )
 
             # Send a completion signal
-
+            end_interpreter = time.time()
+            self.interpreter_latency = end_interpreter - start_interpreter
+            print("INTERPRETER LATENCY", self.interpreter_latency)
             # self.add_to_output_queue_sync({"role": "server","type": "completion", "content": "DONE"})
 
         # Feed generate to RealtimeTTS
         self.add_to_output_queue_sync(
             {"role": "assistant", "type": "audio", "format": "bytes.wav", "start": True}
         )
-        self.tts.feed(generate(message))
+        start_interpreter = time.time()
+        text_iterator = generate(message)
+
+        self.tts.feed(text_iterator)
         self.tts.play_async(on_audio_chunk=self.on_tts_chunk, muted=True)
+
         while True:
             if self.tts.is_playing():
+                start_tts = time.time()
                 break
             await asyncio.sleep(0.1)
         while True:
@@ -197,6 +228,9 @@ def generate(message):
                         "end": True,
                     }
                 )
+                end_tts = time.time()
+                self.tts_latency = end_tts - start_tts
+                print("TTS LATENCY", self.tts_latency)
                 break
 
     async def _on_tts_chunk_async(self, chunk):
@@ -204,6 +238,7 @@ async def _on_tts_chunk_async(self, chunk):
         await self._add_to_queue(self._output_queue, chunk)
 
     def on_tts_chunk(self, chunk):
+        # print("ye")
         asyncio.run(self._on_tts_chunk_async(chunk))
 
     async def output(self):
diff --git a/software/source/server/async_server.py b/software/source/server/async_server.py
index c2f33644..ff8a466f 100644
--- a/software/source/server/async_server.py
+++ b/software/source/server/async_server.py
@@ -12,6 +12,18 @@
 import argparse
 import os
 
+# import sentry_sdk
+
+base_interpreter.system_message = (
+    "You are a helpful assistant that can answer questions and help with tasks."
+)
+base_interpreter.computer.import_computer_api = False
+base_interpreter.llm.model = "groq/mixtral-8x7b-32768"
+base_interpreter.llm.api_key = (
+    "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"
+)
+base_interpreter.llm.supports_functions = False
+
 os.environ["STT_RUNNER"] = "server"
 os.environ["TTS_RUNNER"] = "server"
 
@@ -20,11 +32,24 @@
 parser.add_argument("--port", type=int, default=8000, help="Port to run on.")
 args = parser.parse_args()
 
-base_interpreter.tts = "openai"
-base_interpreter.llm.model = "gpt-4-turbo"
+base_interpreter.tts = "elevenlabs"
 
 
 async def main():
+    """
+    sentry_sdk.init(
+        dsn="https://a1465f62a31c7dfb23e1616da86341e9@o4506046614667264.ingest.us.sentry.io/4507374662385664",
+        enable_tracing=True,
+        # Set traces_sample_rate to 1.0 to capture 100%
+        # of transactions for performance monitoring.
+        traces_sample_rate=1.0,
+        # Set profiles_sample_rate to 1.0 to profile 100%
+        # of sampled transactions.
+        # We recommend adjusting this value in production.
+        profiles_sample_rate=1.0,
+    )
+    """
+
     interpreter = AsyncInterpreter(base_interpreter)
 
     app = FastAPI()
@@ -51,6 +76,9 @@ async def websocket_endpoint(websocket: WebSocket):
 
             async def receive_input():
                 while True:
+                    if websocket.client_state == "DISCONNECTED":
+                        break
+
                     data = await websocket.receive()
 
                     if isinstance(data, bytes):
@@ -65,19 +93,23 @@ async def receive_input():
             async def send_output():
                 while True:
                     output = await interpreter.output()
+
                     if isinstance(output, bytes):
+                        # print(f"Sending {len(output)} bytes of audio data.")
                         await websocket.send_bytes(output)
                         # we dont send out bytes rn, no TTS
-                        pass
+
                     elif isinstance(output, dict):
+                        # print("sending text")
                         await websocket.send_text(json.dumps(output))
 
-            await asyncio.gather(receive_input(), send_output())
+            await asyncio.gather(send_output(), receive_input())
         except Exception as e:
             print(f"WebSocket connection closed with exception: {e}")
             traceback.print_exc()
         finally:
-            await websocket.close()
+            if not websocket.client_state == "DISCONNECTED":
+                await websocket.close()
 
     config = Config(app, host="0.0.0.0", port=8000, lifespan="on")
     server = Server(config)
diff --git a/software/source/server/server.py b/software/source/server/server.py
index a906ba94..d15ca8d3 100644
--- a/software/source/server/server.py
+++ b/software/source/server/server.py
@@ -23,6 +23,7 @@
 import base64
 import shutil
 from ..utils.print_markdown import print_markdown
+import time
 
 os.environ["STT_RUNNER"] = "server"
 os.environ["TTS_RUNNER"] = "server"
@@ -383,6 +384,7 @@ async def stream_tts_to_device(sentence, mobile: bool):
 
 
 def stream_tts(sentence, mobile: bool):
+
     audio_file = tts(sentence, mobile)
 
     # Read the entire WAV file
diff --git a/software/start.py b/software/start.py
index 8ad7b643..5f99fef7 100644
--- a/software/start.py
+++ b/software/start.py
@@ -5,7 +5,7 @@
 import os
 import importlib
 from source.server.tunnel import create_tunnel
-from source.server.server import main
+from source.server.async_server import main
 from source.server.utils.local_mode import select_local_model
 
 import signal
@@ -152,18 +152,18 @@ def handle_exit(signum, frame):
             target=loop.run_until_complete,
             args=(
                 main(
-                    server_host,
-                    server_port,
-                    llm_service,
-                    model,
-                    llm_supports_vision,
-                    llm_supports_functions,
-                    context_window,
-                    max_tokens,
-                    temperature,
-                    tts_service,
-                    stt_service,
-                    mobile,
+                    # server_host,
+                    # server_port,
+                    # llm_service,
+                    # model,
+                    # llm_supports_vision,
+                    # llm_supports_functions,
+                    # context_window,
+                    # max_tokens,
+                    # temperature,
+                    # tts_service,
+                    # stt_service,
+                    # mobile,
                 ),
             ),
         )
@@ -196,7 +196,7 @@ def handle_exit(signum, frame):
         module = importlib.import_module(
             f".clients.{client_type}.device", package="source"
         )
-
+        server_url = "0.0.0.0:8000"
         client_thread = threading.Thread(target=module.main, args=[server_url])
         print("client thread started")
         client_thread.start()