diff --git a/node-hub/dora-microphone/README.md b/node-hub/dora-microphone/README.md
index 465a6243..021d9db6 100644
--- a/node-hub/dora-microphone/README.md
+++ b/node-hub/dora-microphone/README.md
@@ -1,5 +1,48 @@
-# Dora Node for recording data from microphone
+# Collect data from microphone
This node will send data as soon as the microphone volume is higher than a threshold.
-Check example at [examples/speech-to-text](examples/speech-to-text)
+This is using python Sounddevice.
+
+It detects beginning and ending of voice activity within a stream of audio and returns the parts that contains activity.
+
+There's a maximum amount of voice duration, to avoid having no input for too long.
+
+## Input/Output Specification
+
+- inputs:
+ - tick: This is used to detect when the dataflow is finished.
+- outputs:
+ - audio: 16kHz sampled audio sent by chunk
+
+## YAML Specification
+
+```yaml
+- id: dora-vad
+ description: Voice activity detection. See; sidero
+ build: pip install dora-vad
+ path: dora-vad
+ inputs:
+ audio: dora-microphone/audio
+ outputs:
+ - audio
+```
+
+## Reference documentation
+
+- dora-microphone
+ - github: https://github.com/dora-rs/dora/blob/main/node-hub/dora-microphone
+ - website: http://dora-rs.ai/docs/nodes/microphone
+- sounddevice
+ - website: https://python-sounddevice.readthedocs.io/en/0.5.1/
+ - github: https://github.com/spatialaudio/python-sounddevice/tree/master
+
+## Examples
+
+- Speech to Text
+ - github: https://github.com/dora-rs/dora/blob/main/examples/speech-to-text
+ - website: https://dora-rs.ai/docs/examples/stt
+
+## License
+
+The code and model weights are released under the MIT License.
diff --git a/node-hub/dora-rerun/README.md b/node-hub/dora-rerun/README.md
index 5a6ee21f..0082cad9 100644
--- a/node-hub/dora-rerun/README.md
+++ b/node-hub/dora-rerun/README.md
@@ -7,25 +7,27 @@ This nodes is still experimental and format for passing Images, Bounding boxes,
## Getting Started
```bash
-cargo install --force rerun-cli@0.15.1
-
-## To install this package
-git clone git@github.com:dora-rs/dora.git
-cargo install --git https://github.com/dora-rs/dora dora-rerun
+pip install dora-rerun
```
## Adding to existing graph:
```yaml
-- id: rerun
- custom:
- source: dora-rerun
- inputs:
- image: webcam/image
- text: webcam/text
- boxes2d: object_detection/bbox
- envs:
- RERUN_MEMORY_LIMIT: 25%
+- id: plot
+ build: pip install dora-rerun
+ path: dora-rerun
+ inputs:
+ image:
+ source: camera/image
+ queue_size: 1
+ text_qwenvl: dora-qwenvl/text
+ text_whisper: dora-distil-whisper/text
+ env:
+ IMAGE_WIDTH: 640
+ IMAGE_HEIGHT: 480
+ README: |
+ # Visualization
+ RERUN_MEMORY_LIMIT: 25%
```
## Input definition
@@ -67,3 +69,25 @@ Make sure to name the dataflow as follows:
## Configurations
- RERUN_MEMORY_LIMIT: Rerun memory limit
+
+## Reference documentation
+
+- dora-rerun
+ - github: https://github.com/dora-rs/dora/blob/main/node-hub/dora-rerun
+ - website: http://dora-rs.ai/docs/nodes/rerun
+- rerun
+ - github: https://github.com/rerun-io/rerun
+ - website: https://rerun.io
+
+## Examples
+
+- speech to text
+ - github: https://github.com/dora-rs/dora/blob/main/examples/speech-to-text
+ - website: https://dora-rs.ai/docs/examples/stt
+- vision language model
+ - github: https://github.com/dora-rs/dora/blob/main/examples/vlm
+ - website: https://dora-rs.ai/docs/examples/vlm
+
+## License
+
+The code and model weights are released under the MIT License.
diff --git a/node-hub/dora-vad/README.md b/node-hub/dora-vad/README.md
index b5e7ad8a..ba41cb10 100644
--- a/node-hub/dora-vad/README.md
+++ b/node-hub/dora-vad/README.md
@@ -1,3 +1,45 @@
# Speech Activity Detection(VAD)
This is using Silero VAD.
+
+It detects beginning and ending of voice activity within a stream of audio and returns the parts that contains activity.
+
+There's a maximum amount of voice duration, to avoid having no input for too long.
+
+## Input/Output Specification
+
+- inputs:
+ - audio: 8kHz or 16kHz sample rate.
+- outputs:
+ - audio: Same as input but truncated
+
+## YAML Specification
+
+```yaml
+- id: dora-vad
+ description: Voice activity detection. See; sidero
+ build: pip install dora-vad
+ path: dora-vad
+ inputs:
+ audio: dora-microphone/audio
+ outputs:
+ - audio
+```
+
+## Reference documentation
+
+- dora-sidero
+ - github: https://github.com/dora-rs/dora/blob/main/node-hub/dora-vad
+ - website: http://dora-rs.ai/docs/nodes/sidero
+- Sidero
+ - github https://github.com/snakers4/silero-vad
+
+## Examples
+
+- Speech to Text
+ - github: https://github.com/dora-rs/dora/blob/main/examples/speech-to-text
+ - website: https://dora-rs.ai/docs/examples/stt
+
+## License
+
+The code and model weights are released under the MIT License.
diff --git a/node-hub/dora_rdt_1b/__init__.py b/node-hub/dora_rdt_1b/__init__.py
deleted file mode 100644
index ed4e2191..00000000
--- a/node-hub/dora_rdt_1b/__init__.py
+++ /dev/null
@@ -1,19 +0,0 @@
-import os
-import sys
-from pathlib import Path
-
-# Define the path to the README file relative to the package directory
-readme_path = os.path.join(os.path.dirname(os.path.dirname(__file__)), "README.md")
-
-# Read the content of the README file
-try:
- with open(readme_path, "r", encoding="utf-8") as f:
- __doc__ = f.read()
-except FileNotFoundError:
- __doc__ = "README file not found."
-
-
-# Set up the import hook
-
-submodule_path = Path(__file__).resolve().parent / "RoboticsDiffusionTransformer"
-sys.path.insert(0, str(submodule_path))