ManimCommunity · osolmaz · Jun 14, 2026 · Jun 14, 2026 · Jun 14, 2026 · Jun 14, 2026
@@ -22,7 +22,8 @@ https://user-images.githubusercontent.com/2453968/198145393-6a1bd709-4441-4821-8
 
 Currently supported TTS services (aside from the CLI that allows you to records your own voice):
 
-- [Azure Text to Speech](https://azure.microsoft.com/en-us/services/cognitive-services/text-to-speech/) (Recommended for AI voices)
+- [Gemini Text to Speech](https://ai.google.dev/gemini-api/docs/speech-generation) (Recommended for AI voices)
+- [Azure Text to Speech](https://azure.microsoft.com/en-us/services/cognitive-services/text-to-speech/)
 - [gTTS](https://github.com/pndurette/gTTS/)
 - [pyttsx3](https://github.com/nateshmbhat/pyttsx3)
 

@@ -26,27 +26,27 @@ Speech services
    :members:
    :show-inheritance:
 
-.. automodule:: manim_voiceover.services.azure
+.. automodule:: manim_voiceover.services.gemini
    :members:
    :show-inheritance:
 
 .. automodule:: manim_voiceover.services.gtts
    :members:
    :show-inheritance:
 
-.. automodule:: manim_voiceover.services.openai
+.. automodule:: manim_voiceover.services.azure
    :members:
    :show-inheritance:
 
-.. automodule:: manim_voiceover.services.pyttsx3
+.. automodule:: manim_voiceover.services.openai
    :members:
    :show-inheritance:
 
-.. automodule:: manim_voiceover.services.elevenlabs
+.. automodule:: manim_voiceover.services.pyttsx3
    :members:
    :show-inheritance:
 
-.. automodule:: manim_voiceover.services.gemini
+.. automodule:: manim_voiceover.services.elevenlabs
    :members:
    :show-inheritance:
 

@@ -141,8 +141,8 @@
 
 # external links
 extlinks = {
-    "issue": ("https://github.com/ManimCommunity/manim/issues/%s", "#"),
-    "pr": ("https://github.com/ManimCommunity/manim/pull/%s", "#"),
+    "issue": ("https://github.com/ManimCommunity/manim/issues/%s", "#%s"),
+    "pr": ("https://github.com/ManimCommunity/manim/pull/%s", "#%s"),
 }
 
 # opengraph settings

@@ -1,11 +1,11 @@
 Installation
 ============
 
-Install Manim Voiceover from PyPI with the extras ``azure`` and ``gtts``:
+Install Manim Voiceover from PyPI with the extras ``gemini`` and ``gtts``:
 
 .. code:: sh
 
-   pip install --upgrade "manim-voiceover[azure,gtts]"
+   pip install --upgrade "manim-voiceover[gemini,gtts]"
 
 Check whether your installation works correctly:
 
@@ -107,4 +107,4 @@ On macOS, you can install it using `Homebrew <https://brew.sh/>`__:
 
 .. code:: sh
 
-   brew install gettext
+   brew install gettext
@@ -37,19 +37,19 @@ You can also inherit from multiple scene classes:
 This should work as long as the variables or methods of parent classes do not collide.
 
 Manim Voiceover can use various text-to-speech engines, some
-proprietary and some free. A good one to start with is gTTS, which uses
-the Google Translate API. We found out that this is the best
-for beginning to use the library owing to its cross-platform compatibility—however it still needs
-an internet connection.
+proprietary and some free. For generated AI voices, the recommended
+starting point is Gemini text-to-speech. It requires an internet
+connection and a Gemini API key or Google Cloud Application Default
+Credentials.
 
 .. code:: py
 
    from manim_voiceover import VoiceoverScene
-   from manim_voiceover.services.gtts import GTTSService
+   from manim_voiceover.services.gemini import GeminiService
 
    class MyAwesomeScene(VoiceoverScene):
        def construct(self):
-           self.set_speech_service(GTTSService())
+           self.set_speech_service(GeminiService(voice="Kore"))
 
 The logic for adding a voiceover is pretty simple. Wrap the animation
 inside a ``with`` block that calls ``self.voiceover()``:
@@ -85,8 +85,8 @@ The ``text`` argument is automatically reused for video subcaptions. Alternative
        self.play(Create(circle))
 
 See :doc:`examples` and the `examples directory <https://github.com/ManimCommunity/manim-voiceover/blob/main/examples>`__
-for more examples. We recommend starting with the `gTTS
-example <https://github.com/ManimCommunity/manim-voiceover/blob/main/examples/gtts-example.py>`__.
+for more examples. We recommend starting with the `Gemini demo
+example <https://github.com/ManimCommunity/manim-voiceover/blob/main/examples/voiceover-demo.py>`__.
 
 Bookmarks
 *********
@@ -104,16 +104,16 @@ Record your own voiceover
 
 Manim Voiceover can record your voiceover directly from the command line. We recommend the following workflow:
 
-1. Develop your animation with one of the text-to-speech engines, e.g. :py:class:`services.gtts.GTTSService`:
+1. Develop your animation with one of the text-to-speech engines, e.g. :py:class:`services.gemini.GeminiService`:
 
 .. code:: py
 
    from manim_voiceover import VoiceoverScene
-   from manim_voiceover.services.gtts import GTTSService
+   from manim_voiceover.services.gemini import GeminiService
 
    class MyAwesomeScene(VoiceoverScene):
        def construct(self):
-           self.set_speech_service(GTTSService())
+           self.set_speech_service(GeminiService(voice="Kore"))
 
            with self.voiceover(text="This circle is drawn as I speak.") as tracker:
                self.play(Create(circle))
@@ -124,12 +124,12 @@ Manim Voiceover can record your voiceover directly from the command line. We rec
 .. code:: py
 
    from manim_voiceover import VoiceoverScene
-   # from manim_voiceover.services.gtts import GTTSService
+   # from manim_voiceover.services.gemini import GeminiService
    from manim_voiceover.services.recorder import RecorderService
 
    class MyAwesomeScene(VoiceoverScene):
        def construct(self):
-           # self.set_speech_service(GTTSService())
+           # self.set_speech_service(GeminiService(voice="Kore"))
            self.set_speech_service(RecorderService())
 
            with self.voiceover(text="This circle is drawn as I speak.") as tracker:
@@ -158,4 +158,4 @@ The `gTTS example <https://github.com/ManimCommunity/manim-voiceover/blob/main/e
 implements the same scene in English and Vietnamese as a demonstration.
 
 If you can't find a good text-to-speech engine for your language, you can directly
-record your own voiceover using :py:class:`services.recorder.RecorderService`.
+record your own voiceover using :py:class:`services.recorder.RecorderService`.
@@ -27,6 +27,11 @@ Manim Voiceover defines the :py:class:`~~base.SpeechService` class for adding ne
      - N/A
      - N/A
      - This is a utility class to record your own voiceovers with a microphone.
+   * - :py:class:`~gemini.GeminiService`
+     - Very good, human-like
+     - No
+     - Yes
+     - Recommended for generated AI voices. Requires a Gemini API key or Google Cloud ADC, and Python 3.11 or newer.
    * - :py:class:`~azure.AzureService`
      - Very good, human-like
      - No
@@ -42,11 +47,6 @@ Manim Voiceover defines the :py:class:`~~base.SpeechService` class for adding ne
      - No
      - No
      - It's a free API subsidized by Google, so there is a likelihood it may stop working in the future.
-   * - :py:class:`~gemini.GeminiService`
-     - Very good, human-like
-     - No
-     - Yes
-     - Requires a Gemini API key or Google Cloud ADC, and Python 3.10 or newer.
    * - :py:class:`~openai.OpenAIService`
      - Very good, human-like
      - No
@@ -73,11 +73,43 @@ Install Manim Voiceover with the ``recorder`` extra in order to use :py:class:`~
 
 Refer to the `example usage <https://github.com/ManimCommunity/manim-voiceover/blob/main/examples/recorder-example.py>`__ to get started.
 
+:py:class:`~gemini.GeminiService`
+*********************************
+
+`Gemini text-to-speech <https://ai.google.dev/gemini-api/docs/speech-generation>`__ is the recommended service for generated AI voices in Manim Voiceover. It provides controllable text-to-speech through the Google Gen AI SDK, and requires an internet connection and Python 3.11 or newer.
+
+Install Manim Voiceover with the ``gemini`` extra in order to use :py:class:`~gemini.GeminiService`:
+
+.. code:: sh
+
+   pip install "manim-voiceover[gemini]"
+
+For Gemini Developer API authentication, create a file called ``.env``
+that contains your API key in the same directory where you call Manim.
+
+.. code:: sh
+
+   GEMINI_API_KEY="..." # insert the API key here
+
+Gemini uses API-key authentication by default:
+
+.. code:: python
+
+   self.set_speech_service(GeminiService(voice="Kore"))
+
+For Google Cloud Vertex AI authentication, use Application Default
+Credentials and set ``auth_mode="adc"``:
+
+.. code:: python
+
+   self.set_speech_service(
+       GeminiService(voice="Kore", auth_mode="adc", project="my-project-id")
+   )
 
 :py:class:`~azure.AzureService`
 *******************************
 
-As of now, the highest quality text-to-speech service available in Manim Voiceover is `Microsoft Azure Speech Service <https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/overview>`__. To use it, you will need to `create an
+`Microsoft Azure Speech Service <https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/overview>`__ is also available for generated voices. To use it, you will need to `create an
 Azure account <https://azure.microsoft.com/en-us/free/>`__.
 
 .. tip::
@@ -123,39 +155,6 @@ Install Manim Voiceover with the ``gtts`` extra in order to use :py:class:`~gtts
 
 Refer to the `example usage <https://github.com/ManimCommunity/manim-voiceover/blob/main/examples/gtts-example.py>`__ to get started.
 
-:py:class:`~gemini.GeminiService`
-*********************************
-
-`Gemini text-to-speech <https://ai.google.dev/gemini-api/docs/speech-generation>`__ provides controllable text-to-speech through the Google Gen AI SDK. It requires an internet connection and Python 3.10 or newer.
-
-Install Manim Voiceover with the ``gemini`` extra in order to use :py:class:`~gemini.GeminiService`:
-
-.. code:: sh
-
-   pip install "manim-voiceover[gemini]"
-
-For Gemini Developer API authentication, create a file called ``.env``
-that contains your API key in the same directory where you call Manim.
-
-.. code:: sh
-
-   GEMINI_API_KEY="..." # insert the API key here
-
-Gemini uses API-key authentication by default:
-
-.. code:: python
-
-   self.set_speech_service(GeminiService(voice="Kore"))
-
-For Google Cloud Vertex AI authentication, use Application Default
-Credentials and set ``auth_mode="adc"``:
-
-.. code:: python
-
-   self.set_speech_service(
-       GeminiService(voice="Kore", auth_mode="adc", project="my-project-id")
-   )
-
 :py:class:`~openai.OpenAIService`
 *************************************
 `OpenAI <https://platform.openai.com/docs/api-reference/audio/createSpeech/>`__ provides a text-to-speech service. It is through an API, so it requires an internet connection to work. It also requires an API key to use. Register for one `here <https://platform.openai.com/>`__.

@@ -3,7 +3,7 @@ name = "manim-voiceover"
 version = "0.3.8"
 description = "Manim plugin for all things voiceover"
 readme = "README.md"
-requires-python = ">=3.8"
+requires-python = ">=3.11"
 license = "MIT"
 authors = [
     { name = "The Manim Community Developers", email = "contact@manim.community" },
@@ -28,20 +28,19 @@ classifiers = [
     "Topic :: Multimedia :: Sound/Audio :: Speech",
     "Topic :: Scientific/Engineering :: Artificial Intelligence",
     "Topic :: Scientific/Engineering :: Visualization",
-    "Programming Language :: Python :: 3.8",
-    "Programming Language :: Python :: 3.9",
-    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
     "Natural Language :: English",
 ]
 dependencies = [
     "manim",
     "sox>=1.4.1,<2",
-    "python-dotenv>=0.21.0,<0.22; python_version < '3.10'",
-    "python-dotenv>=1.2.2,<2; python_version >= '3.10'",
+    "python-dotenv>=1.2.2,<2",
     "mutagen>=1.46.0,<2",
     "pydub>=0.25.1,<0.26",
-    "pip>=21.0.1; python_version < '3.10'",
-    "pip>=26.1.2; python_version >= '3.10'",
+    "pip>=26.1.2",
+    "pydantic>=2.10,<3",
     "python-slugify>=8.0.1,<9",
 ]
 
@@ -53,7 +52,7 @@ pyttsx3 = ["pyttsx3>=2.90,<3"]
 recorder = ["PyAudio>=0.2.12,<0.3", "pynput>=1.7.6,<2"]
 translate = ["deepl>=1.12.0,<2"]
 elevenlabs = ["elevenlabs>=0.2.27,<0.3"]
-gemini = ["google-genai>=1.0,<3; python_version >= '3.10'"]
+gemini = ["google-genai>=1.0,<3"]
 transcribe = ["openai-whisper>=20230314", "stable-ts>=2.6.2,<3"]
 all = [
     "azure-cognitiveservices-speech>=1.24.0,<2",
@@ -66,7 +65,7 @@ all = [
     "openai-whisper>=20230314",
     "stable-ts>=2.6.2,<3",
     "elevenlabs>=0.2.27,<0.3",
-    "google-genai>=1.0,<3; python_version >= '3.10'",
+    "google-genai>=1.0,<3",
 ]
 
 [project.urls]
@@ -94,8 +93,7 @@ dev = [
     "pip-audit>=2.7",
     "PyAudio>=0.2.12,<0.3",
     "pytest-cov>=5.0.0,<7",
-    "pytest>=8.3.5,<9; python_version < '3.10'",
-    "pytest>=9.0.3,<10; python_version >= '3.10'",
+    "pytest>=9.0.3,<10",
     "pynput>=1.7.6,<2",
     "pyttsx3>=2.90,<3",
     "pylint>=2.12.2,<3",
@@ -108,7 +106,7 @@ dev = [
     "matplotlib>=3.3.2,<4",
     "pre-commit>=2.11.1,<3",
     "gitpython>=3,<4",
-    "google-genai>=1.0,<3; python_version >= '3.10'",
+    "google-genai>=1.0,<3",
     "pygithub>=1,<2",
     "isort>=5.8.0,<6",
     "pytest-xdist>=3.6,<4",
@@ -124,7 +122,7 @@ dev = [
 
 [tool.ruff]
 line-length = 127
-target-version = "py38"
+target-version = "py311"
 src = ["src", "tests"]
 extend-exclude = ["docs", "examples", "mutants"]
 
@@ -159,7 +157,7 @@ show_missing = true
 source_paths = ["src/manim_voiceover"]
 
 [tool.mypy]
-python_version = "3.8"
+python_version = "3.11"
 strict = true
 show_error_codes = true
 files = ["src/manim_voiceover"]