Resolve *almost* all pylint complaints and setup pylint

.github/workflows/code-quality.yml

@@ -19,6 +19,8 @@ jobs:
       run: pip install .[dev]
     - name: Run mypy
       run: mypy --pretty src examples
+    - name: Run pylint
+      run: pylint examples src
     - name: Run isort
       run: isort --check-only --diff .
     - name: Run black

examples/basic_audio_streaming.py

@@ -15,12 +15,12 @@ import asyncio
 
 import edge_tts
 
+TEXT = "Hello World!"
+VOICE = "en-GB-SoniaNeural"
+OUTPUT_FILE = "test.mp3"
 
-async def main() -> None:
-    TEXT = "Hello World!"
-    VOICE = "en-GB-SoniaNeural"
-    OUTPUT_FILE = "test.mp3"
 
+async def _main() -> None:
     communicate = edge_tts.Communicate(TEXT, VOICE)
     with open(OUTPUT_FILE, "wb") as file:
         async for chunk in communicate.stream():
@@ -31,4 +31,4 @@ async def main() -> None:
 
 
 if __name__ == "__main__":
-    asyncio.get_event_loop().run_until_complete(main())
+    asyncio.get_event_loop().run_until_complete(_main())

examples/basic_generation.py

@@ -8,15 +8,15 @@ import asyncio
 
 import edge_tts
 
+TEXT = "Hello World!"
+VOICE = "en-GB-SoniaNeural"
+OUTPUT_FILE = "test.mp3"
 
-async def main() -> None:
-    TEXT = "Hello World!"
-    VOICE = "en-GB-SoniaNeural"
-    OUTPUT_FILE = "test.mp3"
 
+async def _main() -> None:
     communicate = edge_tts.Communicate(TEXT, VOICE)
     await communicate.save(OUTPUT_FILE)
 
 
 if __name__ == "__main__":
-    asyncio.get_event_loop().run_until_complete(main())
+    asyncio.get_event_loop().run_until_complete(_main())

examples/dynamic_voice_selection.py

@@ -10,19 +10,19 @@ import random
 import edge_tts
 from edge_tts import VoicesManager
 
+TEXT = "Hoy es un buen día."
+OUTPUT_FILE = "spanish.mp3"
 
-async def main() -> None:
+
+async def _main() -> None:
     voices = await VoicesManager.create()
     voice = voices.find(Gender="Male", Language="es")
     # Also supports Locales
     # voice = voices.find(Gender="Female", Locale="es-AR")
-    VOICE = random.choice(voice)["ShortName"]
-    TEXT = "Hoy es un buen día."
-    OUTPUT_FILE = "spanish.mp3"
 
-    communicate = edge_tts.Communicate(TEXT, VOICE)
+    communicate = edge_tts.Communicate(TEXT, random.choice(voice)["Name"])
     await communicate.save(OUTPUT_FILE)
 
 
 if __name__ == "__main__":
-    asyncio.get_event_loop().run_until_complete(main())
+    asyncio.get_event_loop().run_until_complete(_main())

examples/streaming_with_subtitles.py

@@ -11,13 +11,13 @@ import asyncio
 
 import edge_tts
 
+TEXT = "Hello World!"
+VOICE = "en-GB-SoniaNeural"
+OUTPUT_FILE = "test.mp3"
+WEBVTT_FILE = "test.vtt"
 
-async def main() -> None:
-    TEXT = "Hello World!"
-    VOICE = "en-GB-SoniaNeural"
-    OUTPUT_FILE = "test.mp3"
-    WEBVTT_FILE = "test.vtt"
 
+async def _main() -> None:
     communicate = edge_tts.Communicate(TEXT, VOICE)
     submaker = edge_tts.SubMaker()
     with open(OUTPUT_FILE, "wb") as file:
@@ -32,4 +32,4 @@ async def main() -> None:
 
 
 if __name__ == "__main__":
-    asyncio.get_event_loop().run_until_complete(main())
+    asyncio.get_event_loop().run_until_complete(_main())

pylintrc

@@ -0,0 +1,612 @@
+[MAIN]
+
+# Analyse import fallback blocks. This can be used to support both Python 2 and
+# 3 compatible code, which means that the block might have code that exists
+# only in one or another interpreter, leading to false positives when analysed.
+analyse-fallback-blocks=no
+
+# Load and enable all available extensions. Use --list-extensions to see a list
+# all available extensions.
+#enable-all-extensions=
+
+# In error mode, messages with a category besides ERROR or FATAL are
+# suppressed, and no reports are done by default. Error mode is compatible with
+# disabling specific errors.
+#errors-only=
+
+# Always return a 0 (non-error) status code, even if lint errors are found.
+# This is primarily useful in continuous integration scripts.
+#exit-zero=
+
+# A comma-separated list of package or module names from where C extensions may
+# be loaded. Extensions are loading into the active Python interpreter and may
+# run arbitrary code.
+extension-pkg-allow-list=
+
+# A comma-separated list of package or module names from where C extensions may
+# be loaded. Extensions are loading into the active Python interpreter and may
+# run arbitrary code. (This is an alternative name to extension-pkg-allow-list
+# for backward compatibility.)
+extension-pkg-whitelist=
+
+# Return non-zero exit code if any of these messages/categories are detected,
+# even if score is above --fail-under value. Syntax same as enable. Messages
+# specified are enabled, while categories only check already-enabled messages.
+fail-on=
+
+# Specify a score threshold under which the program will exit with error.
+fail-under=10
+
+# Interpret the stdin as a python script, whose filename needs to be passed as
+# the module_or_package argument.
+#from-stdin=
+
+# Files or directories to be skipped. They should be base names, not paths.
+ignore=CVS
+
+# Add files or directories matching the regular expressions patterns to the
+# ignore-list. The regex matches against paths and can be in Posix or Windows
+# format. Because '\' represents the directory delimiter on Windows systems, it
+# can't be used as an escape character.
+ignore-paths=
+
+# Files or directories matching the regular expression patterns are skipped.
+# The regex matches against base names, not paths. The default value ignores
+# Emacs file locks
+ignore-patterns=^\.#
+
+# List of module names for which member attributes should not be checked
+# (useful for modules/projects where namespaces are manipulated during runtime
+# and thus existing member attributes cannot be deduced by static analysis). It
+# supports qualified module names, as well as Unix pattern matching.
+ignored-modules=
+
+# Python code to execute, usually for sys.path manipulation such as
+# pygtk.require().
+#init-hook=
+
+# Use multiple processes to speed up Pylint. Specifying 0 will auto-detect the
+# number of processors available to use, and will cap the count on Windows to
+# avoid hangs.
+jobs=1
+
+# Control the amount of potential inferred values when inferring a single
+# object. This can help the performance when dealing with large functions or
+# complex, nested conditions.
+limit-inference-results=100
+
+# List of plugins (as comma separated values of python module names) to load,
+# usually to register additional checkers.
+load-plugins=
+
+# Pickle collected data for later comparisons.
+persistent=yes
+
+# Minimum Python version to use for version dependent checks. Will default to
+# the version used to run pylint.
+py-version=3.10
+
+# Discover python modules and packages in the file system subtree.
+recursive=no
+
+# When enabled, pylint would attempt to guess common misconfiguration and emit
+# user-friendly hints instead of false-positive error messages.
+suggestion-mode=yes
+
+# Allow loading of arbitrary C extensions. Extensions are imported into the
+# active Python interpreter and may run arbitrary code.
+unsafe-load-any-extension=no
+
+# In verbose mode, extra non-checker-related info will be displayed.
+#verbose=
+
+
+[BASIC]
+
+# Naming style matching correct argument names.
+argument-naming-style=snake_case
+
+# Regular expression matching correct argument names. Overrides argument-
+# naming-style. If left empty, argument names will be checked with the set
+# naming style.
+#argument-rgx=
+
+# Naming style matching correct attribute names.
+attr-naming-style=snake_case
+
+# Regular expression matching correct attribute names. Overrides attr-naming-
+# style. If left empty, attribute names will be checked with the set naming
+# style.
+#attr-rgx=
+
+# Bad variable names which should always be refused, separated by a comma.
+bad-names=foo,
+          bar,
+          baz,
+          toto,
+          tutu,
+          tata
+
+# Bad variable names regexes, separated by a comma. If names match any regex,
+# they will always be refused
+bad-names-rgxs=
+
+# Naming style matching correct class attribute names.
+class-attribute-naming-style=any
+
+# Regular expression matching correct class attribute names. Overrides class-
+# attribute-naming-style. If left empty, class attribute names will be checked
+# with the set naming style.
+#class-attribute-rgx=
+
+# Naming style matching correct class constant names.
+class-const-naming-style=UPPER_CASE
+
+# Regular expression matching correct class constant names. Overrides class-
+# const-naming-style. If left empty, class constant names will be checked with
+# the set naming style.
+#class-const-rgx=
+
+# Naming style matching correct class names.
+class-naming-style=PascalCase
+
+# Regular expression matching correct class names. Overrides class-naming-
+# style. If left empty, class names will be checked with the set naming style.
+#class-rgx=
+
+# Naming style matching correct constant names.
+const-naming-style=UPPER_CASE
+
+# Regular expression matching correct constant names. Overrides const-naming-
+# style. If left empty, constant names will be checked with the set naming
+# style.
+#const-rgx=
+
+# Minimum line length for functions/classes that require docstrings, shorter
+# ones are exempt.
+docstring-min-length=-1
+
+# Naming style matching correct function names.
+function-naming-style=snake_case
+
+# Regular expression matching correct function names. Overrides function-
+# naming-style. If left empty, function names will be checked with the set
+# naming style.
+#function-rgx=
+
+# Good variable names which should always be accepted, separated by a comma.
+good-names=i,
+           j,
+           k,
+           ex,
+           Run,
+           _
+
+# Good variable names regexes, separated by a comma. If names match any regex,
+# they will always be accepted
+good-names-rgxs=
+
+# Include a hint for the correct naming format with invalid-name.
+include-naming-hint=no
+
+# Naming style matching correct inline iteration names.
+inlinevar-naming-style=any
+
+# Regular expression matching correct inline iteration names. Overrides
+# inlinevar-naming-style. If left empty, inline iteration names will be checked
+# with the set naming style.
+#inlinevar-rgx=
+
+# Naming style matching correct method names.
+method-naming-style=snake_case
+
+# Regular expression matching correct method names. Overrides method-naming-
+# style. If left empty, method names will be checked with the set naming style.
+#method-rgx=
+
+# Naming style matching correct module names.
+module-naming-style=snake_case
+
+# Regular expression matching correct module names. Overrides module-naming-
+# style. If left empty, module names will be checked with the set naming style.
+#module-rgx=
+
+# Colon-delimited sets of names that determine each other's naming style when
+# the name regexes allow several styles.
+name-group=
+
+# Regular expression which should only match function or class names that do
+# not require a docstring.
+no-docstring-rgx=^_
+
+# List of decorators that produce properties, such as abc.abstractproperty. Add
+# to this list to register other decorators that produce valid properties.
+# These decorators are taken in consideration only for invalid-name.
+property-classes=abc.abstractproperty
+
+# Regular expression matching correct type variable names. If left empty, type
+# variable names will be checked with the set naming style.
+#typevar-rgx=
+
+# Naming style matching correct variable names.
+variable-naming-style=snake_case
+
+# Regular expression matching correct variable names. Overrides variable-
+# naming-style. If left empty, variable names will be checked with the set
+# naming style.
+#variable-rgx=
+
+
+[CLASSES]
+
+# Warn about protected attribute access inside special methods
+check-protected-access-in-special-methods=no
+
+# List of method names used to declare (i.e. assign) instance attributes.
+defining-attr-methods=__init__,
+                      __new__,
+                      setUp,
+                      __post_init__
+
+# List of member names, which should be excluded from the protected access
+# warning.
+exclude-protected=_asdict,
+                  _fields,
+                  _replace,
+                  _source,
+                  _make
+
+# List of valid names for the first argument in a class method.
+valid-classmethod-first-arg=cls
+
+# List of valid names for the first argument in a metaclass class method.
+valid-metaclass-classmethod-first-arg=cls
+
+
+[DESIGN]
+
+# List of regular expressions of class ancestor names to ignore when counting
+# public methods (see R0903)
+exclude-too-few-public-methods=
+
+# List of qualified class names to ignore when counting class parents (see
+# R0901)
+ignored-parents=
+
+# Maximum number of arguments for function / method.
+max-args=5
+
+# Maximum number of attributes for a class (see R0902).
+max-attributes=7
+
+# Maximum number of boolean expressions in an if statement (see R0916).
+max-bool-expr=5
+
+# Maximum number of branch for function / method body.
+max-branches=15
+
+# Maximum number of locals for function / method body.
+max-locals=15
+
+# Maximum number of parents for a class (see R0901).
+max-parents=7
+
+# Maximum number of public methods for a class (see R0904).
+max-public-methods=20
+
+# Maximum number of return / yield for function / method body.
+max-returns=6
+
+# Maximum number of statements in function / method body.
+max-statements=50
+
+# Minimum number of public methods for a class (see R0903).
+min-public-methods=2
+
+
+[EXCEPTIONS]
+
+# Exceptions that will emit a warning when caught.
+overgeneral-exceptions=BaseException,
+                       Exception
+
+
+[FORMAT]
+
+# Expected format of line ending, e.g. empty (any line ending), LF or CRLF.
+expected-line-ending-format=
+
+# Regexp for a line that is allowed to be longer than the limit.
+ignore-long-lines=^\s*(# )?<?https?://\S+>?$
+
+# Number of spaces of indent required inside a hanging or continued line.
+indent-after-paren=4
+
+# String used as indentation unit. This is usually "    " (4 spaces) or "\t" (1
+# tab).
+indent-string='    '
+
+# Maximum number of characters on a single line.
+max-line-length=100
+
+# Maximum number of lines in a module.
+max-module-lines=1000
+
+# Allow the body of a class to be on the same line as the declaration if body
+# contains single statement.
+single-line-class-stmt=no
+
+# Allow the body of an if to be on the same line as the test if there is no
+# else.
+single-line-if-stmt=no
+
+
+[IMPORTS]
+
+# List of modules that can be imported at any level, not just the top level
+# one.
+allow-any-import-level=
+
+# Allow wildcard imports from modules that define __all__.
+allow-wildcard-with-all=no
+
+# Deprecated modules which should not be used, separated by a comma.
+deprecated-modules=
+
+# Output a graph (.gv or any supported image format) of external dependencies
+# to the given file (report RP0402 must not be disabled).
+ext-import-graph=
+
+# Output a graph (.gv or any supported image format) of all (i.e. internal and
+# external) dependencies to the given file (report RP0402 must not be
+# disabled).
+import-graph=
+
+# Output a graph (.gv or any supported image format) of internal dependencies
+# to the given file (report RP0402 must not be disabled).
+int-import-graph=
+
+# Force import order to recognize a module as part of the standard
+# compatibility libraries.
+known-standard-library=
+
+# Force import order to recognize a module as part of a third party library.
+known-third-party=enchant
+
+# Couples of modules and preferred modules, separated by a comma.
+preferred-modules=
+
+
+[LOGGING]
+
+# The type of string formatting that logging methods do. `old` means using %
+# formatting, `new` is for `{}` formatting.
+logging-format-style=old
+
+# Logging modules to check that the string format arguments are in logging
+# function parameter format.
+logging-modules=logging
+
+
+[MESSAGES CONTROL]
+
+# Only show warnings with the listed confidence levels. Leave empty to show
+# all. Valid levels: HIGH, CONTROL_FLOW, INFERENCE, INFERENCE_FAILURE,
+# UNDEFINED.
+confidence=HIGH,
+           CONTROL_FLOW,
+           INFERENCE,
+           INFERENCE_FAILURE,
+           UNDEFINED
+
+# Disable the message, report, category or checker with the given id(s). You
+# can either give multiple identifiers separated by comma (,) or put this
+# option multiple times (only on the command line, not in the configuration
+# file where it should appear only once). You can also use "--disable=all" to
+# disable everything first and then re-enable specific checks. For example, if
+# you want to run only the similarities checker, you can use "--disable=all
+# --enable=similarities". If you want to run only the classes checker, but have
+# no Warning level messages displayed, use "--disable=all --enable=classes
+# --disable=W".
+disable=duplicate-code,
+        consider-using-with
+
+# Enable the message, report, category or checker with the given id(s). You can
+# either give multiple identifier separated by comma (,) or put this option
+# multiple time (only on the command line, not in the configuration file where
+# it should appear only once). See also the "--disable" option for examples.
+enable=c-extension-no-member
+
+
+[METHOD_ARGS]
+
+# List of qualified names (i.e., library.method) which require a timeout
+# parameter e.g. 'requests.api.get,requests.api.post'
+timeout-methods=requests.api.delete,requests.api.get,requests.api.head,requests.api.options,requests.api.patch,requests.api.post,requests.api.put,requests.api.request
+
+
+[MISCELLANEOUS]
+
+# List of note tags to take in consideration, separated by a comma.
+notes=FIXME,
+      XXX,
+      TODO
+
+# Regular expression of note tags to take in consideration.
+notes-rgx=
+
+
+[REFACTORING]
+
+# Maximum number of nested blocks for function / method body
+max-nested-blocks=5
+
+# Complete name of functions that never returns. When checking for
+# inconsistent-return-statements if a never returning function is called then
+# it will be considered as an explicit return statement and no message will be
+# printed.
+never-returning-functions=sys.exit,argparse.parse_error
+
+
+[REPORTS]
+
+# Python expression which should return a score less than or equal to 10. You
+# have access to the variables 'fatal', 'error', 'warning', 'refactor',
+# 'convention', and 'info' which contain the number of messages in each
+# category, as well as 'statement' which is the total number of statements
+# analyzed. This score is used by the global evaluation report (RP0004).
+evaluation=max(0, 0 if fatal else 10.0 - ((float(5 * error + warning + refactor + convention) / statement) * 10))
+
+# Template used to display messages. This is a python new-style format string
+# used to format the message information. See doc for all details.
+msg-template=
+
+# Set the output format. Available formats are text, parseable, colorized, json
+# and msvs (visual studio). You can also give a reporter class, e.g.
+# mypackage.mymodule.MyReporterClass.
+#output-format=
+
+# Tells whether to display a full report or only the messages.
+reports=no
+
+# Activate the evaluation score.
+score=yes
+
+
+[SIMILARITIES]
+
+# Comments are removed from the similarity computation
+ignore-comments=yes
+
+# Docstrings are removed from the similarity computation
+ignore-docstrings=yes
+
+# Imports are removed from the similarity computation
+ignore-imports=yes
+
+# Signatures are removed from the similarity computation
+ignore-signatures=yes
+
+# Minimum lines number of a similarity.
+min-similarity-lines=4
+
+
+[SPELLING]
+
+# Limits count of emitted suggestions for spelling mistakes.
+max-spelling-suggestions=4
+
+# Spelling dictionary name. Available dictionaries: none. To make it work,
+# install the 'python-enchant' package.
+spelling-dict=
+
+# List of comma separated words that should be considered directives if they
+# appear at the beginning of a comment and should not be checked.
+spelling-ignore-comment-directives=fmt: on,fmt: off,noqa:,noqa,nosec,isort:skip,mypy:
+
+# List of comma separated words that should not be checked.
+spelling-ignore-words=
+
+# A path to a file that contains the private dictionary; one word per line.
+spelling-private-dict-file=
+
+# Tells whether to store unknown words to the private dictionary (see the
+# --spelling-private-dict-file option) instead of raising a message.
+spelling-store-unknown-words=no
+
+
+[STRING]
+
+# This flag controls whether inconsistent-quotes generates a warning when the
+# character used as a quote delimiter is used inconsistently within a module.
+check-quote-consistency=no
+
+# This flag controls whether the implicit-str-concat should generate a warning
+# on implicit string concatenation in sequences defined over several lines.
+check-str-concat-over-line-jumps=no
+
+
+[TYPECHECK]
+
+# List of decorators that produce context managers, such as
+# contextlib.contextmanager. Add to this list to register other decorators that
+# produce valid context managers.
+contextmanager-decorators=contextlib.contextmanager
+
+# List of members which are set dynamically and missed by pylint inference
+# system, and so shouldn't trigger E1101 when accessed. Python regular
+# expressions are accepted.
+generated-members=
+
+# Tells whether to warn about missing members when the owner of the attribute
+# is inferred to be None.
+ignore-none=yes
+
+# This flag controls whether pylint should warn about no-member and similar
+# checks whenever an opaque object is returned when inferring. The inference
+# can return multiple potential results while evaluating a Python object, but
+# some branches might not be evaluated, which results in partial inference. In
+# that case, it might be useful to still emit no-member and other checks for
+# the rest of the inferred objects.
+ignore-on-opaque-inference=yes
+
+# List of symbolic message names to ignore for Mixin members.
+ignored-checks-for-mixins=no-member,
+                          not-async-context-manager,
+                          not-context-manager,
+                          attribute-defined-outside-init
+
+# List of class names for which member attributes should not be checked (useful
+# for classes with dynamically set attributes). This supports the use of
+# qualified names.
+ignored-classes=optparse.Values,thread._local,_thread._local,argparse.Namespace
+
+# Show a hint with possible names when a member name was not found. The aspect
+# of finding the hint is based on edit distance.
+missing-member-hint=yes
+
+# The minimum edit distance a name should have in order to be considered a
+# similar match for a missing member name.
+missing-member-hint-distance=1
+
+# The total number of similar names that should be taken in consideration when
+# showing a hint for a missing member.
+missing-member-max-choices=1
+
+# Regex pattern to define which classes are considered mixins.
+mixin-class-rgx=.*[Mm]ixin
+
+# List of decorators that change the signature of a decorated function.
+signature-mutators=
+
+
+[VARIABLES]
+
+# List of additional names supposed to be defined in builtins. Remember that
+# you should avoid defining new builtins when possible.
+additional-builtins=
+
+# Tells whether unused global variables should be treated as a violation.
+allow-global-unused-variables=yes
+
+# List of names allowed to shadow builtins
+allowed-redefined-builtins=
+
+# List of strings which can identify a callback function by name. A callback
+# name must start or end with one of those strings.
+callbacks=cb_,
+          _cb
+
+# A regular expression matching the name of dummy variables (i.e. expected to
+# not be used).
+dummy-variables-rgx=_+$|(_[a-zA-Z0-9_]*[a-zA-Z0-9]+?$)|dummy|^ignored_|^unused_
+
+# Argument names that match this expression will be ignored.
+ignored-argument-names=_.*|^ignored_|^unused_
+
+# Tells whether we should check for unused import in __init__ files.
+init-import=no
+
+# List of qualified module names which can have objects that can redefine
+# builtins.
+redefining-builtins-modules=six.moves,past.builtins,future.builtins,builtins,io

setup.cfg

@@ -27,7 +27,7 @@ where=src
 [options.entry_points]
 console_scripts =
     edge-tts = edge_tts.__main__:main
-    edge-playback = edge_playback.__main__:main
+    edge-playback = edge_playback.__main__:_main
 
 [options.extras_require]
 dev =

src/edge_playback/__init__.py

@@ -4,6 +4,6 @@
 Init file for the package.
 """
 
-from .__main__ import main
+from .__main__ import _main
 
-__all__ = ["main"]
+__all__ = ["_main"]

src/edge_playback/__main__.py

@@ -4,14 +4,13 @@
 Playback TTS with subtitles using edge-tts and mpv.
 """
 
-import os
 import subprocess
 import sys
 import tempfile
 from shutil import which
 
 
-def main() -> None:
+def _main() -> None:
     depcheck_failed = False
     if not which("mpv"):
         print("mpv is not installed.", file=sys.stderr)
@@ -23,13 +22,10 @@ def main() -> None:
         print("Please install the missing dependencies.", file=sys.stderr)
         sys.exit(1)
 
-    media = None
-    subtitle = None
-    try:
-        media = tempfile.NamedTemporaryFile(delete=False)
+    with tempfile.NamedTemporaryFile(
+        suffix=".mp3", delete=False
+    ) as media, tempfile.NamedTemporaryFile(suffix=".vtt", delete=False) as subtitle:
         media.close()
-
-        subtitle = tempfile.NamedTemporaryFile(delete=False)
         subtitle.close()
 
         print(f"Media file: {media.name}")
@@ -52,12 +48,7 @@ def main() -> None:
             ]
         ) as process:
             process.communicate()
-    finally:
-        if media is not None:
-            os.unlink(media.name)
-        if subtitle is not None:
-            os.unlink(subtitle.name)
 
 
 if __name__ == "__main__":
-    main()
+    _main()

src/edge_tts/communicate.py

@@ -7,12 +7,29 @@ import json
 import re
 import time
 import uuid
-from typing import Any, AsyncGenerator, Dict, Generator, List, Optional, Tuple, Union
+from contextlib import nullcontext
+from io import TextIOWrapper
+from typing import (
+    Any,
+    AsyncGenerator,
+    ContextManager,
+    Dict,
+    Generator,
+    List,
+    Optional,
+    Tuple,
+    Union,
+)
 from xml.sax.saxutils import escape
 
 import aiohttp
 
-from edge_tts.exceptions import NoAudioReceived, UnexpectedResponse, UnknownResponse
+from edge_tts.exceptions import (
+    NoAudioReceived,
+    UnexpectedResponse,
+    UnknownResponse,
+    WebSocketError,
+)
 
 from .constants import WSS_URL
 
@@ -161,8 +178,6 @@ def date_to_string() -> str:
     # without having to use a library. We'll just use UTC and hope for the best.
     # For example, right now %Z would return EEST when we need it to return
     # Eastern European Summer Time.
-    #
-    # return time.strftime("%a %b %d %Y %H:%M:%S GMT%z (%Z)")
     return time.strftime(
         "%a %b %d %Y %H:%M:%S GMT+0000 (Coordinated Universal Time)", time.gmtime()
     )
@@ -185,6 +200,26 @@ def ssml_headers_plus_data(request_id: str, timestamp: str, ssml: str) -> str:
     )
 
 
+def calc_max_mesg_size(voice: str, rate: str, volume: str) -> int:
+    """Calculates the maximum message size for the given voice, rate, and volume.
+
+    Returns:
+        int: The maximum message size.
+    """
+    websocket_max_size: int = 2**16
+    overhead_per_message: int = (
+        len(
+            ssml_headers_plus_data(
+                connect_id(),
+                date_to_string(),
+                mkssml("", voice, rate, volume),
+            )
+        )
+        + 50  # margin of error
+    )
+    return websocket_max_size - overhead_per_message
+
+
 class Communicate:
     """
     Class for communicating with the service.
@@ -206,7 +241,6 @@ class Communicate:
             ValueError: If the voice is not valid.
         """
         self.text: str = text
-        self.codec: str = "audio-24khz-48kbitrate-mono-mp3"
         self.voice: str = voice
         # Possible values for voice are:
         # - Microsoft Server Speech Text to Speech Voice (cy-GB, NiaNeural)
@@ -241,158 +275,123 @@ class Communicate:
     async def stream(self) -> AsyncGenerator[Dict[str, Any], None]:
         """Streams audio and metadata from the service."""
 
-        websocket_max_size = 2**16
-        overhead_per_message = (
-            len(
-                ssml_headers_plus_data(
-                    connect_id(),
-                    date_to_string(),
-                    mkssml("", self.voice, self.rate, self.volume),
-                )
-            )
-            + 50  # margin of error
-        )
         texts = split_text_by_byte_length(
             escape(remove_incompatible_characters(self.text)),
-            websocket_max_size - overhead_per_message,
+            calc_max_mesg_size(self.voice, self.rate, self.volume),
         )
 
-        async with aiohttp.ClientSession(trust_env=True) as session:
-            async with session.ws_connect(
-                f"{WSS_URL}&ConnectionId={connect_id()}",
-                compress=15,
-                autoclose=True,
-                autoping=True,
-                proxy=self.proxy,
-                headers={
-                    "Pragma": "no-cache",
-                    "Cache-Control": "no-cache",
-                    "Origin": "chrome-extension://jdiccldimpdaibmpdkjnbmckianbfold",
-                    "Accept-Encoding": "gzip, deflate, br",
-                    "Accept-Language": "en-US,en;q=0.9",
-                    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"
-                    " (KHTML, like Gecko) Chrome/91.0.4472.77 Safari/537.36 Edg/91.0.864.41",
-                },
-            ) as websocket:
-                for text in texts:
-                    # download indicates whether we should be expecting audio data,
-                    # this is so what we avoid getting binary data from the websocket
-                    # and falsely thinking it's audio data.
-                    download_audio = False
+        async with aiohttp.ClientSession(trust_env=True) as session, session.ws_connect(
+            f"{WSS_URL}&ConnectionId={connect_id()}",
+            compress=15,
+            autoclose=True,
+            autoping=True,
+            proxy=self.proxy,
+            headers={
+                "Pragma": "no-cache",
+                "Cache-Control": "no-cache",
+                "Origin": "chrome-extension://jdiccldimpdaibmpdkjnbmckianbfold",
+                "Accept-Encoding": "gzip, deflate, br",
+                "Accept-Language": "en-US,en;q=0.9",
+                "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"
+                " (KHTML, like Gecko) Chrome/91.0.4472.77 Safari/537.36 Edg/91.0.864.41",
+            },
+        ) as websocket:
+            for text in texts:
+                # download indicates whether we should be expecting audio data,
+                # this is so what we avoid getting binary data from the websocket
+                # and falsely thinking it's audio data.
+                download_audio = False
 
-                    # audio_was_received indicates whether we have received audio data
-                    # from the websocket. This is so we can raise an exception if we
-                    # don't receive any audio data.
-                    audio_was_received = False
+                # audio_was_received indicates whether we have received audio data
+                # from the websocket. This is so we can raise an exception if we
+                # don't receive any audio data.
+                audio_was_received = False
 
-                    # Each message needs to have the proper date
-                    date = date_to_string()
+                # Each message needs to have the proper date.
+                date = date_to_string()
 
-                    # Prepare the request to be sent to the service.
-                    #
-                    # Note sentenceBoundaryEnabled and wordBoundaryEnabled are actually supposed
-                    # to be booleans, but Edge Browser seems to send them as strings.
-                    #
-                    # This is a bug in Edge as Azure Cognitive Services actually sends them as
-                    # bool and not string. For now I will send them as bool unless it causes
-                    # any problems.
-                    #
-                    # Also pay close attention to double { } in request (escape for f-string).
-                    request = (
-                        f"X-Timestamp:{date}\r\n"
-                        "Content-Type:application/json; charset=utf-8\r\n"
-                        "Path:speech.config\r\n\r\n"
-                        '{"context":{"synthesis":{"audio":{"metadataoptions":{'
-                        '"sentenceBoundaryEnabled":false,"wordBoundaryEnabled":true},'
-                        f'"outputFormat":"{self.codec}"'
-                        "}}}}\r\n"
+                # Prepare the request to be sent to the service.
+                #
+                # Note sentenceBoundaryEnabled and wordBoundaryEnabled are actually supposed
+                # to be booleans, but Edge Browser seems to send them as strings.
+                #
+                # This is a bug in Edge as Azure Cognitive Services actually sends them as
+                # bool and not string. For now I will send them as bool unless it causes
+                # any problems.
+                #
+                # Also pay close attention to double { } in request (escape for f-string).
+                await websocket.send_str(
+                    f"X-Timestamp:{date}\r\n"
+                    "Content-Type:application/json; charset=utf-8\r\n"
+                    "Path:speech.config\r\n\r\n"
+                    '{"context":{"synthesis":{"audio":{"metadataoptions":{'
+                    '"sentenceBoundaryEnabled":false,"wordBoundaryEnabled":true},'
+                    '"outputFormat":"audio-24khz-48kbitrate-mono-mp3"'
+                    "}}}}\r\n"
+                )
+
+                await websocket.send_str(
+                    ssml_headers_plus_data(
+                        connect_id(),
+                        date,
+                        mkssml(text, self.voice, self.rate, self.volume),
                     )
-                    await websocket.send_str(request)
+                )
 
-                    await websocket.send_str(
-                        ssml_headers_plus_data(
-                            connect_id(),
-                            date,
-                            mkssml(text, self.voice, self.rate, self.volume),
-                        )
+                async for received in websocket:
+                    if received.type == aiohttp.WSMsgType.TEXT:
+                        parameters, data = get_headers_and_data(received.data)
+                        if parameters.get("Path") == "turn.start":
+                            download_audio = True
+                        elif parameters.get("Path") == "turn.end":
+                            download_audio = False
+                            break  # End of audio data
+                        elif parameters.get("Path") == "audio.metadata":
+                            meta = json.loads(data)
+                            for i in range(len(meta["Metadata"])):
+                                meta_obj = meta["Metadata"][i]
+                                meta_type = meta_obj["Type"]
+                                if meta_type == "WordBoundary":
+                                    yield {
+                                        "type": meta_type,
+                                        "offset": meta_obj["Data"]["Offset"],
+                                        "duration": meta_obj["Data"]["Duration"],
+                                        "text": meta_obj["Data"]["text"]["Text"],
+                                    }
+                                elif meta_type == "SessionEnd":
+                                    continue
+                                else:
+                                    raise UnknownResponse(
+                                        f"Unknown metadata type: {meta_type}"
+                                    )
+                        elif parameters.get("Path") == "response":
+                            pass
+                        else:
+                            raise UnknownResponse(
+                                "The response from the service is not recognized.\n"
+                                + received.data
+                            )
+                    elif received.type == aiohttp.WSMsgType.BINARY:
+                        if not download_audio:
+                            raise UnexpectedResponse(
+                                "We received a binary message, but we are not expecting one."
+                            )
+
+                        yield {
+                            "type": "audio",
+                            "data": b"Path:audio\r\n".join(
+                                received.data.split(b"Path:audio\r\n")[1:]
+                            ),
+                        }
+                        audio_was_received = True
+                    elif received.type == aiohttp.WSMsgType.ERROR:
+                        raise WebSocketError(received.data)
+
+                if not audio_was_received:
+                    raise NoAudioReceived(
+                        "No audio was received. Please verify that your parameters are correct."
                     )
 
-                    async for received in websocket:
-                        if received.type == aiohttp.WSMsgType.TEXT:
-                            parameters, data = get_headers_and_data(received.data)
-                            if (
-                                "Path" in parameters
-                                and parameters["Path"] == "turn.start"
-                            ):
-                                download_audio = True
-                            elif (
-                                "Path" in parameters
-                                and parameters["Path"] == "turn.end"
-                            ):
-                                download_audio = False
-                                break
-                            elif (
-                                "Path" in parameters
-                                and parameters["Path"] == "audio.metadata"
-                            ):
-                                metadata = json.loads(data)
-                                for i in range(len(metadata["Metadata"])):
-                                    metadata_type = metadata["Metadata"][i]["Type"]
-                                    metadata_offset = metadata["Metadata"][i]["Data"][
-                                        "Offset"
-                                    ]
-                                    if metadata_type == "WordBoundary":
-                                        metadata_duration = metadata["Metadata"][i][
-                                            "Data"
-                                        ]["Duration"]
-                                        metadata_text = metadata["Metadata"][i]["Data"][
-                                            "text"
-                                        ]["Text"]
-                                        yield {
-                                            "type": metadata_type,
-                                            "offset": metadata_offset,
-                                            "duration": metadata_duration,
-                                            "text": metadata_text,
-                                        }
-                                    elif metadata_type == "SentenceBoundary":
-                                        raise UnknownResponse(
-                                            "SentenceBoundary is not supported due to being broken."
-                                        )
-                                    elif metadata_type == "SessionEnd":
-                                        continue
-                                    else:
-                                        raise UnknownResponse(
-                                            f"Unknown metadata type: {metadata_type}"
-                                        )
-                            elif (
-                                "Path" in parameters
-                                and parameters["Path"] == "response"
-                            ):
-                                pass
-                            else:
-                                raise UnknownResponse(
-                                    "The response from the service is not recognized.\n"
-                                    + received.data
-                                )
-                        elif received.type == aiohttp.WSMsgType.BINARY:
-                            if download_audio:
-                                yield {
-                                    "type": "audio",
-                                    "data": b"Path:audio\r\n".join(
-                                        received.data.split(b"Path:audio\r\n")[1:]
-                                    ),
-                                }
-                                audio_was_received = True
-                            else:
-                                raise UnexpectedResponse(
-                                    "We received a binary message, but we are not expecting one."
-                                )
-
-                    if not audio_was_received:
-                        raise NoAudioReceived(
-                            "No audio was received. Please verify that your parameters are correct."
-                        )
-
     async def save(
         self,
         audio_fname: Union[str, bytes],
@@ -401,24 +400,23 @@ class Communicate:
         """
         Save the audio and metadata to the specified files.
         """
-        written_audio = False
-        try:
-            audio = open(audio_fname, "wb")
-            metadata = None
-            if metadata_fname is not None:
-                metadata = open(metadata_fname, "w", encoding="utf-8")
-
+        written_audio: bool = False
+        metadata: Union[TextIOWrapper, ContextManager[None]] = (
+            open(metadata_fname, "w", encoding="utf-8")
+            if metadata_fname is not None
+            else nullcontext()
+        )
+        with metadata, open(audio_fname, "wb") as audio:
             async for message in self.stream():
                 if message["type"] == "audio":
                     audio.write(message["data"])
                     written_audio = True
-                elif metadata is not None and message["type"] == "WordBoundary":
+                elif (
+                    isinstance(metadata, TextIOWrapper)
+                    and message["type"] == "WordBoundary"
+                ):
                     json.dump(message, metadata)
                     metadata.write("\n")
-        finally:
-            audio.close()
-            if metadata is not None:
-                metadata.close()
 
         if not written_audio:
             raise NoAudioReceived(

src/edge_tts/exceptions.py

@@ -14,3 +14,7 @@ class UnexpectedResponse(Exception):
 
 class NoAudioReceived(Exception):
     """Raised when no audio is received from the server."""
+
+
+class WebSocketError(Exception):
+    """Raised when a WebSocket error occurs."""

src/edge_tts/util.py

@@ -6,8 +6,8 @@ Main package.
 import argparse
 import asyncio
 import sys
-from io import BufferedWriter
-from typing import Any
+from io import TextIOWrapper
+from typing import Any, TextIO, Union
 
 from edge_tts import Communicate, SubMaker, list_voices
 
@@ -34,36 +34,30 @@ async def _print_voices(*, proxy: str) -> None:
 
 async def _run_tts(args: Any) -> None:
     """Run TTS after parsing arguments from command line."""
-    tts = Communicate(
+    tts: Communicate = Communicate(
         args.text,
         args.voice,
         proxy=args.proxy,
         rate=args.rate,
         volume=args.volume,
     )
-    try:
-        media_file = None
-        if args.write_media:
-            media_file = open(args.write_media, "wb")
+    subs: SubMaker = SubMaker(args.overlapping)
+    with open(
+        args.write_media, "wb"
+    ) if args.write_media else sys.stdout.buffer as audio_file:
+        async for chunk in tts.stream():
+            if chunk["type"] == "audio":
+                audio_file.write(chunk["data"])
+            elif chunk["type"] == "WordBoundary":
+                subs.create_sub((chunk["offset"], chunk["duration"]), chunk["text"])
 
-        subs = SubMaker(args.overlapping)
-        async for data in tts.stream():
-            if data["type"] == "audio":
-                if isinstance(media_file, BufferedWriter):
-                    media_file.write(data["data"])
-                else:
-                    sys.stdout.buffer.write(data["data"])
-            elif data["type"] == "WordBoundary":
-                subs.create_sub((data["offset"], data["duration"]), data["text"])
-
-        if not args.write_subtitles:
-            sys.stderr.write(subs.generate_subs())
-        else:
-            with open(args.write_subtitles, "w", encoding="utf-8") as file:
-                file.write(subs.generate_subs())
-    finally:
-        if media_file is not None:
-            media_file.close()
+    sub_file: Union[TextIOWrapper, TextIO] = (
+        open(args.write_subtitles, "w", encoding="utf-8")
+        if args.write_subtitles
+        else sys.stderr
+    )
+    with sub_file:
+        sub_file.write(subs.generate_subs())
 
 
 async def _async_main() -> None: