Use supertone tts (#754)

Author: jaagut

.vscode/settings.json

@@ -100,6 +100,7 @@
         "rsyncignore",
         "rtype",
         "rviz",
+        "samplerate",
         "scipy",
         "sdev",
         "seaborn",

pixi.lock

@@ -44,6 +44,7 @@ breathe = ">=4.36.0,<5"
 cmake = "<3.30"  # Constraint to avoid issues with deprecated features in newer cmake versions
 colorama = ">=0.4.6,<0.5"
 compilers = ">=1.11.0,<2"
+construct = ">=2.10.70,<3"
 eigen = ">=3.4.0,<4"
 fabric = ">=3.2.2,<4"
 flask = ">=3.1.2,<4"
@@ -71,6 +72,7 @@ psutil = ">=7.1.3,<8"
 pthread-stubs = ">=0.4,<0.5"
 pybind11 = ">=3.0.1,<4"
 pyqt = ">=5.15.11,<6"
+pysoundcard = ">=0.4.5,<0.5"
 pytest = ">=9.0.1,<10"
 pytest-mock = ">=3.15.1,<4"
 pyyaml = ">=6.0.3,<7"
@@ -193,6 +195,7 @@ ros-jazzy-better-launch = ">=1.0.3,<2"
 # Neural network models / data packages
 bitbots_model_2023_04_04_philipp_yoeox_with_team_colors = ">=1.0.0,<2"
 bitbots_model_2022_10_07_flo_torso21_yoeox = ">=1.0.0,<2"
+tts-supertonic = ">=1.0.0,<2"
 
 # Local packages
 bitbots_rust_nav = { path = "src/bitbots_navigation/bitbots_rust_nav" }
@@ -222,8 +225,6 @@ pre-commit = ">=4.4.0,<5"
 construct = ">=2.10.56, <3"
 syrupy = ">=5.0.0, <6"
 exhale = ">=0.3.7, <0.4"
-mycroft-mimic3-tts = ">=0.2.4, <0.3"
-pyttsx3 = ">=2.99, <3"
 
 [feature.ros.target.linux-64.pypi-dependencies]
 onnxruntime-webgpu = ">=1.24.0.dev20251218001, <2"

pixi.toml

@@ -4,7 +4,6 @@
     <arg name="torqueless_mode" default="false"/>
     <arg name="only_imu" default="false"/>
     <arg name="only_pressure" default="false"/>
-    <arg name="tts" default="true" description="Whether to speak" />
 
     <node pkg="bitbots_ros_control" exec="ros_control" output="screen" >
         <param from="$(find-pkg-share bitbots_ros_control)/config/wolfgang.yaml" />
@@ -25,9 +24,5 @@
         <include file="$(find-pkg-share bitbots_buttons)/launch/buttons.launch"/>
         <!--include file="$(find-pkg-share bitbots_ros_control)/launch/pressure_converter.launch"/-->
     </group>
-
-    <group if="$(var tts)">
-        <include file="$(find-pkg-share bitbots_tts)/launch/tts.launch"/>
-    </group >
 </launch>
 

src/bitbots_lowlevel/bitbots_ros_control/launch/ros_control.launch

@@ -3,6 +3,7 @@
     <arg name="sim" default="false"/>
     <arg name="viz" default="false"/>
     <arg name="torqueless_mode" default="false" description="start without torque, for example for testing the falling detection"/>
+    <arg name="tts" default="true" description="Whether to enable text-to-speech"/>
 
     <include file="$(find-pkg-share bitbots_parameter_blackboard)/launch/parameter_blackboard.launch">
         <arg name="sim" value="$(var sim)"/>
@@ -12,6 +13,10 @@
         <arg name="sim" value="$(var sim)"/>
     </include>
 
+    <group if="$(var tts)">
+        <include file="$(find-pkg-share bitbots_tts)/launch/tts.launch"/>
+    </group>
+
     <group if="$(var viz)">
         <node pkg="bitbots_utils" exec="motor_goals_viz_helper.py" output="screen" args="--all"/>
         <node pkg="rviz2" exec="rviz2" args="-d $(find-pkg-share bitbots_quintic_walk)/config/walk.rviz"/>

src/bitbots_misc/bitbots_bringup/launch/motion_standalone.launch

@@ -26,6 +26,11 @@
         <arg name="fieldname" value="$(var fieldname)" />
     </include>
 
+    <!-- load the text to speech engine -->
+    <group if="$(var tts)">
+        <include file="$(find-pkg-share bitbots_tts)/launch/tts.launch"/>
+    </group >
+
     <!-- load the diagnostic aggregator -->
     <include file="$(find-pkg-share bitbots_diagnostic)/launch/aggregator.launch" />