diff --git a/voice/Dockerfile b/voice/Dockerfile
index 1ede1bc..88cc876 100644
--- a/voice/Dockerfile
+++ b/voice/Dockerfile
@@ -1,18 +1,7 @@
 # use base image
-FROM quay.io/ohsu-comp-bio/bridge2ai-jupyter:restricted-gpu-root
+FROM quay.io/ohsu-comp-bio/bridge2ai-jupyter:cpu-root
 
-# return to non-root user
-USER $NB_UID
-WORKDIR /home/$NB_USER
-
-# create environment
-# setup environment
-RUN conda create -n voice
-SHELL ["conda", "run", "-n", "voice", "/bin/bash", "-c"]
-RUN conda install python=3.11
 RUN pip install --no-cache-dir b2aiprep ipympl huggingface_hub[cli]
-RUN pip install ipykernel
-RUN python -m ipykernel install --user --name voice --display-name "Python (voice)"
 
 # download models
 RUN MODEL_DIR=$HOME/models && \
@@ -20,4 +9,4 @@ RUN MODEL_DIR=$HOME/models && \
    huggingface-cli download --local-dir $MODEL_DIR/openai/whisper-base openai/whisper-base --cache-dir ${MODEL_DIR}/cache
 
 # allow use of conda envs
-RUN conda init bash && exec bash
\ No newline at end of file
+RUN conda init bash && exec bash