First upload to the repo.

Dockerfile

@@ -0,0 +1,21 @@
+FROM python:3.12 AS base
+
+RUN apt-get update
+RUN apt-get install -y portaudio19-dev
+
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+	PATH=/home/user/.local/bin:$PATH
+
+WORKDIR $HOME/app
+
+COPY --chown=user ./requirements.txt ./requirements.txt
+
+RUN pip3 install -r requirements.txt
+
+COPY --chown=user . $HOME/app
+
+FROM base AS run
+
+CMD ["python", "webui.py"]

requirements.txt

@@ -0,0 +1,2 @@
+gradio==5.23.3
+mlx-audio==0.0.3

webui.py

@@ -0,0 +1,18 @@
+import gradio as gr
+import os
+
+def speech_to_text(input_text):
+    os.system(f"python -m mlx_audio.tts.generate --model mlx-community/csm-1b --text \"{input_text}\"")
+    
+    return 'audio_000.wav'
+
+demo = gr.Interface(
+    speech_to_text,
+    [
+        gr.Textbox(label="Text prompt"),
+    ],
+    [
+        gr.Audio(type="filepath"),
+    ]
+)
+demo.launch(server_name="0.0.0.0", server_port=7860)