diff --git a/docs/source/main_classes/audio_processor.md b/docs/source/main_classes/audio_processor.md
new file mode 100644
index 00000000..1a7bf8ae
--- /dev/null
+++ b/docs/source/main_classes/audio_processor.md
@@ -0,0 +1,25 @@
+# AudioProcessor
+
+`TTS.utils.audio.AudioProcessor` is the core class for all the audio processing routines. It provides an API for
+
+- Feature extraction.
+- Sound normalization.
+- Reading and writing audio files.
+- Sampling audio signals.
+- Normalizing and denormalizing audio signals.
+- Griffin-Lim vocoder.
+
+The `AudioProcessor` needs to be initialized with `TTS.config.shared_configs.BaseAudioConfig`. Any model config
+also must inherit or initiate `BaseAudioConfig`.
+
+## AudioProcessor
+```{eval-rst}
+.. autoclass:: TTS.utils.audio.AudioProcessor
+    :members:
+```
+
+## BaseAudioConfig
+```{eval-rst}
+.. autoclass:: TTS.config.shared_configs.BaseAudioConfig
+    :members:
+```
\ No newline at end of file
diff --git a/docs/source/main_classes/dataset.md b/docs/source/main_classes/dataset.md
new file mode 100644
index 00000000..92d381ac
--- /dev/null
+++ b/docs/source/main_classes/dataset.md
@@ -0,0 +1,25 @@
+# Datasets
+
+## TTS Dataset
+
+```{eval-rst}
+.. autoclass:: TTS.tts.datasets.TTSDataset
+    :members:
+```
+
+## Vocoder Dataset
+
+```{eval-rst}
+.. autoclass:: TTS.vocoder.datasets.gan_dataset.GANDataset
+    :members:
+```
+
+```{eval-rst}
+.. autoclass:: TTS.vocoder.datasets.wavegrad_dataset.WaveGradDataset
+    :members:
+```
+
+```{eval-rst}
+.. autoclass:: TTS.vocoder.datasets.wavernn_dataset.WaveRNNDataset
+    :members:
+```
\ No newline at end of file
diff --git a/docs/source/main_classes/gan.md b/docs/source/main_classes/gan.md
new file mode 100644
index 00000000..4524b4b5
--- /dev/null
+++ b/docs/source/main_classes/gan.md
@@ -0,0 +1,12 @@
+# GAN API
+
+The {class}`TTS.vocoder.models.gan.GAN` provides an easy way to implementing new GAN based models. You just need
+to define the model architectures for the generator and the discriminator networks and give them to the `GAN` class
+to do its ✨️.
+
+
+## GAN
+```{eval-rst}
+.. autoclass:: TTS.vocoder.models.gan.GAN
+    :members:
+```
\ No newline at end of file
diff --git a/docs/source/main_classes/model_api.md b/docs/source/main_classes/model_api.md
new file mode 100644
index 00000000..438901b7
--- /dev/null
+++ b/docs/source/main_classes/model_api.md
@@ -0,0 +1,24 @@
+# Model API
+Model API provides you a set of functions that easily make your model compatible with the `Trainer`,
+`Synthesizer` and `ModelZoo`.
+
+## Base TTS Model
+
+```{eval-rst}
+.. autoclass:: TTS.model.BaseModel
+    :members:
+```
+
+## Base `tts` Model
+
+```{eval-rst}
+.. autoclass:: TTS.tts.models.base_tts.BaseTTS
+    :members:
+```
+
+## Base `vocoder` Model
+
+```{eval-rst}
+.. autoclass:: TTS.tts.models.base_vocoder.BaseVocoder`
+    :members:
+```
\ No newline at end of file
diff --git a/docs/source/main_classes/trainer_api.md b/docs/source/main_classes/trainer_api.md
new file mode 100644
index 00000000..a5c3cfb7
--- /dev/null
+++ b/docs/source/main_classes/trainer_api.md
@@ -0,0 +1,17 @@
+# Trainer API
+
+The {class}`TTS.trainer.Trainer` provides a lightweight, extensible, and feature-complete training run-time. We optimized it for 🐸 but
+can also be used for any DL training in different domains. It supports distributed multi-gpu, mixed-precision (apex or torch.amp) training.
+
+
+## Trainer
+```{eval-rst}
+.. autoclass:: TTS.trainer.Trainer
+    :members:
+```
+
+## TrainingArgs
+```{eval-rst}
+.. autoclass:: TTS.trainer.TrainingArgs
+    :members:
+```
\ No newline at end of file