From 1e1f0ee3215eacaffd7e0a2d6367efdea7a00521 Mon Sep 17 00:00:00 2001
From: Ettore Di Giacinto <mudler@users.noreply.github.com>
Date: Wed, 18 Jun 2025 19:48:50 +0200
Subject: [PATCH] chore(backends): move `bark-cpp` to the backend gallery
 (#5682)

chore(bark-cpp): move outside from binary

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---
 .../{python_backend.yml => backend.yml}       | 101 +++++++++++++-
 ...on_backend_build.yml => backend_build.yml} |   8 ++
 Makefile                                      |   1 -
 backend/Dockerfile.go                         | 131 ++++++++++++++++++
 backend/go/bark/run.sh                        |   3 +
 backend/index.yaml                            | 115 +++++++++------
 6 files changed, 313 insertions(+), 46 deletions(-)
 rename .github/workflows/{python_backend.yml => backend.yml} (81%)
 rename .github/workflows/{python_backend_build.yml => backend_build.yml} (97%)
 create mode 100644 backend/Dockerfile.go
 create mode 100755 backend/go/bark/run.sh

diff --git a/.github/workflows/python_backend.yml b/.github/workflows/backend.yml
similarity index 81%
rename from .github/workflows/python_backend.yml
rename to .github/workflows/backend.yml
index 8cd5e712..6af0748f 100644
--- a/.github/workflows/python_backend.yml
+++ b/.github/workflows/backend.yml
@@ -1,5 +1,5 @@
 ---
-name: 'build python backend container images'
+name: 'build backend container images'
 
 on:
   push:
@@ -15,7 +15,7 @@ concurrency:
 
 jobs:
   backend-jobs:
-    uses: ./.github/workflows/python_backend_build.yml
+    uses: ./.github/workflows/backend_build.yml
     with:
       tag-latest: ${{ matrix.tag-latest }}
       tag-suffix: ${{ matrix.tag-suffix }}
@@ -27,6 +27,8 @@ jobs:
       base-image: ${{ matrix.base-image }}
       backend: ${{ matrix.backend }}
       latest-image: ${{ matrix.latest-image }}
+      dockerfile: $${ matrix.dockerfile }}
+      context: $${ matrix.context }}
     secrets:
       dockerUsername: ${{ secrets.DOCKERHUB_USERNAME }}
       dockerPassword: ${{ secrets.DOCKERHUB_PASSWORD }}
@@ -48,6 +50,8 @@ jobs:
             base-image: "ubuntu:22.04"
             backend: "rerankers"
             latest-image: 'latest-gpu-nvidia-cuda-11-rerankers'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "11"
             cuda-minor-version: "7"
@@ -58,6 +62,8 @@ jobs:
             base-image: "ubuntu:22.04"
             backend: "vllm"
             latest-image: 'latest-gpu-nvidia-cuda-11-vllm'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "11"
             cuda-minor-version: "7"
@@ -68,6 +74,8 @@ jobs:
             base-image: "ubuntu:22.04"
             backend: "transformers"
             latest-image: 'latest-gpu-nvidia-cuda-11-transformers'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "11"
             cuda-minor-version: "7"
@@ -78,6 +86,8 @@ jobs:
             base-image: "ubuntu:22.04"
             backend: "diffusers"
             latest-image: 'latest-gpu-nvidia-cuda-11-diffusers'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           # CUDA 11 additional backends
           - build-type: 'cublas'
             cuda-major-version: "11"
@@ -89,6 +99,8 @@ jobs:
             base-image: "ubuntu:22.04"
             backend: "kokoro"
             latest-image: 'latest-gpu-nvidia-cuda-11-kokoro'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "11"
             cuda-minor-version: "7"
@@ -99,6 +111,8 @@ jobs:
             base-image: "ubuntu:22.04"
             backend: "faster-whisper"
             latest-image: 'latest-gpu-nvidia-cuda-11-faster-whisper'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "11"
             cuda-minor-version: "7"
@@ -109,6 +123,8 @@ jobs:
             base-image: "ubuntu:22.04"
             backend: "coqui"
             latest-image: 'latest-gpu-nvidia-cuda-11-coqui'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "11"
             cuda-minor-version: "7"
@@ -119,6 +135,8 @@ jobs:
             base-image: "ubuntu:22.04"
             backend: "bark"
             latest-image: 'latest-gpu-nvidia-cuda-11-bark'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "11"
             cuda-minor-version: "7"
@@ -129,6 +147,8 @@ jobs:
             base-image: "ubuntu:22.04"
             backend: "chatterbox"
             latest-image: 'latest-gpu-nvidia-cuda-11-chatterbox'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           # CUDA 12 builds
           - build-type: 'cublas'
             cuda-major-version: "12"
@@ -140,6 +160,8 @@ jobs:
             base-image: "ubuntu:22.04"
             backend: "rerankers"
             latest-image: 'latest-gpu-nvidia-cuda-12-rerankers'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "0"
@@ -150,6 +172,8 @@ jobs:
             base-image: "ubuntu:22.04"
             backend: "vllm"
             latest-image: 'latest-gpu-nvidia-cuda-12-vllm'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "0"
@@ -160,6 +184,8 @@ jobs:
             base-image: "ubuntu:22.04"
             backend: "transformers"
             latest-image: 'latest-gpu-nvidia-cuda-12-transformers'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "0"
@@ -170,6 +196,8 @@ jobs:
             base-image: "ubuntu:22.04"
             backend: "diffusers"
             latest-image: 'latest-gpu-nvidia-cuda-12-diffusers'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           # CUDA 12 additional backends
           - build-type: 'cublas'
             cuda-major-version: "12"
@@ -181,6 +209,8 @@ jobs:
             base-image: "ubuntu:22.04"
             backend: "kokoro"
             latest-image: 'latest-gpu-nvidia-cuda-12-kokoro'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "0"
@@ -191,6 +221,8 @@ jobs:
             base-image: "ubuntu:22.04"
             backend: "faster-whisper"
             latest-image: 'latest-gpu-nvidia-cuda-12-faster-whisper'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "0"
@@ -201,6 +233,8 @@ jobs:
             base-image: "ubuntu:22.04"
             backend: "coqui"
             latest-image: 'latest-gpu-nvidia-cuda-12-coqui'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "0"
@@ -211,6 +245,8 @@ jobs:
             base-image: "ubuntu:22.04"
             backend: "bark"
             latest-image: 'latest-gpu-nvidia-cuda-12-bark'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "0"
@@ -221,6 +257,8 @@ jobs:
             base-image: "ubuntu:22.04"
             backend: "chatterbox"
             latest-image: 'latest-gpu-nvidia-cuda-12-chatterbox'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           # hipblas builds
           - build-type: 'hipblas'
             cuda-major-version: ""
@@ -232,6 +270,8 @@ jobs:
             base-image: "rocm/dev-ubuntu-22.04:6.1"
             backend: "rerankers"
             latest-image: 'latest-gpu-rocm-hipblas-rerankers'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'hipblas'
             cuda-major-version: ""
             cuda-minor-version: ""
@@ -242,6 +282,8 @@ jobs:
             base-image: "rocm/dev-ubuntu-22.04:6.1"
             backend: "vllm"
             latest-image: 'latest-gpu-rocm-hipblas-vllm'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'hipblas'
             cuda-major-version: ""
             cuda-minor-version: ""
@@ -252,6 +294,8 @@ jobs:
             base-image: "rocm/dev-ubuntu-22.04:6.1"
             backend: "transformers"
             latest-image: 'latest-gpu-rocm-hipblas-transformers'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'hipblas'
             cuda-major-version: ""
             cuda-minor-version: ""
@@ -262,6 +306,8 @@ jobs:
             base-image: "rocm/dev-ubuntu-22.04:6.1"
             backend: "diffusers"
             latest-image: 'latest-gpu-rocm-hipblas-diffusers'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           # ROCm additional backends
           - build-type: 'hipblas'
             cuda-major-version: ""
@@ -273,6 +319,8 @@ jobs:
             base-image: "rocm/dev-ubuntu-22.04:6.1"
             backend: "kokoro"
             latest-image: 'latest-gpu-rocm-hipblas-kokoro'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'hipblas'
             cuda-major-version: ""
             cuda-minor-version: ""
@@ -283,6 +331,8 @@ jobs:
             base-image: "rocm/dev-ubuntu-22.04:6.1"
             backend: "faster-whisper"
             latest-image: 'latest-gpu-rocm-hipblas-faster-whisper'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'hipblas'
             cuda-major-version: ""
             cuda-minor-version: ""
@@ -293,6 +343,8 @@ jobs:
             base-image: "rocm/dev-ubuntu-22.04:6.1"
             backend: "coqui"
             latest-image: 'latest-gpu-rocm-hipblas-coqui'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'hipblas'
             cuda-major-version: ""
             cuda-minor-version: ""
@@ -303,6 +355,8 @@ jobs:
             base-image: "rocm/dev-ubuntu-22.04:6.1"
             backend: "bark"
             latest-image: 'latest-gpu-rocm-hipblas-bark'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           # sycl builds
           - build-type: 'sycl_f32'
             cuda-major-version: ""
@@ -314,6 +368,8 @@ jobs:
             base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
             backend: "rerankers"
             latest-image: 'latest-gpu-intel-sycl-f32-rerankers'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'sycl_f16'
             cuda-major-version: ""
             cuda-minor-version: ""
@@ -324,6 +380,8 @@ jobs:
             base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
             backend: "rerankers"
             latest-image: 'latest-gpu-intel-sycl-f16-rerankers'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'sycl_f32'
             cuda-major-version: ""
             cuda-minor-version: ""
@@ -334,6 +392,8 @@ jobs:
             base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
             backend: "vllm"
             latest-image: 'latest-gpu-intel-sycl-f32-vllm'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'sycl_f16'
             cuda-major-version: ""
             cuda-minor-version: ""
@@ -344,6 +404,8 @@ jobs:
             base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
             backend: "vllm"
             latest-image: 'latest-gpu-intel-sycl-f16-vllm'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'sycl_f32'
             cuda-major-version: ""
             cuda-minor-version: ""
@@ -354,6 +416,8 @@ jobs:
             base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
             backend: "transformers"
             latest-image: 'latest-gpu-intel-sycl-f32-transformers'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'sycl_f16'
             cuda-major-version: ""
             cuda-minor-version: ""
@@ -364,6 +428,8 @@ jobs:
             base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
             backend: "transformers"
             latest-image: 'latest-gpu-intel-sycl-f16-transformers'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'sycl_f32'
             cuda-major-version: ""
             cuda-minor-version: ""
@@ -374,6 +440,8 @@ jobs:
             base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
             backend: "diffusers"
             latest-image: 'latest-gpu-intel-sycl-f32-diffusers'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           # SYCL additional backends
           - build-type: 'sycl_f32'
             cuda-major-version: ""
@@ -385,6 +453,8 @@ jobs:
             base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
             backend: "kokoro"
             latest-image: 'latest-gpu-intel-sycl-f32-kokoro'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'sycl_f16'
             cuda-major-version: ""
             cuda-minor-version: ""
@@ -395,6 +465,8 @@ jobs:
             base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
             backend: "kokoro"
             latest-image: 'latest-gpu-intel-sycl-f16-kokoro'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'sycl_f32'
             cuda-major-version: ""
             cuda-minor-version: ""
@@ -405,6 +477,8 @@ jobs:
             base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
             backend: "faster-whisper"
             latest-image: 'latest-gpu-intel-sycl-f32-faster-whisper'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'sycl_f16'
             cuda-major-version: ""
             cuda-minor-version: ""
@@ -415,6 +489,8 @@ jobs:
             base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
             backend: "faster-whisper"
             latest-image: 'latest-gpu-intel-sycl-f16-faster-whisper'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'sycl_f32'
             cuda-major-version: ""
             cuda-minor-version: ""
@@ -425,6 +501,8 @@ jobs:
             base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
             backend: "coqui"
             latest-image: 'latest-gpu-intel-sycl-f32-coqui'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'sycl_f16'
             cuda-major-version: ""
             cuda-minor-version: ""
@@ -435,6 +513,8 @@ jobs:
             base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
             backend: "coqui"
             latest-image: 'latest-gpu-intel-sycl-f16-coqui'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'sycl_f32'
             cuda-major-version: ""
             cuda-minor-version: ""
@@ -445,6 +525,8 @@ jobs:
             base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
             backend: "bark"
             latest-image: 'latest-gpu-intel-sycl-f32-bark'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'sycl_f16'
             cuda-major-version: ""
             cuda-minor-version: ""
@@ -455,3 +537,18 @@ jobs:
             base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
             backend: "bark"
             latest-image: 'latest-gpu-intel-sycl-f16-bark'
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
+          # bark-cpp
+          - build-type: ''
+            cuda-major-version: ""
+            cuda-minor-version: ""
+            platforms: 'linux/amd64'
+            tag-latest: 'true'
+            tag-suffix: '-bark-cpp'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:22.04"
+            backend: "bark"
+            latest-image: 'latest-bark-cpp'
+            dockerfile: "./backend/Dockerfile.go"
+            context: "./"
\ No newline at end of file
diff --git a/.github/workflows/python_backend_build.yml b/.github/workflows/backend_build.yml
similarity index 97%
rename from .github/workflows/python_backend_build.yml
rename to .github/workflows/backend_build.yml
index 6ef7ea8f..d840a37a 100644
--- a/.github/workflows/python_backend_build.yml
+++ b/.github/workflows/backend_build.yml
@@ -45,6 +45,14 @@ on:
         description: 'Backend to build'
         required: true
         type: string
+      context:
+        description: 'Build context'
+        required: true
+        type: string
+      dockerfile:
+        description: 'Build Dockerfile'
+        required: true
+        type: string
     secrets:
       dockerUsername:
         required: true
diff --git a/Makefile b/Makefile
index 61831f62..18749193 100644
--- a/Makefile
+++ b/Makefile
@@ -225,7 +225,6 @@ ALL_GRPC_BACKENDS+=backend-assets/grpc/whisper
 
 ifeq ($(ONNX_OS),linux)
 ifeq ($(ONNX_ARCH),x64)
-	ALL_GRPC_BACKENDS+=backend-assets/grpc/bark-cpp
 	ALL_GRPC_BACKENDS+=backend-assets/grpc/stablediffusion-ggml
 endif
 endif
diff --git a/backend/Dockerfile.go b/backend/Dockerfile.go
new file mode 100644
index 00000000..7770e09c
--- /dev/null
+++ b/backend/Dockerfile.go
@@ -0,0 +1,131 @@
+ARG BASE_IMAGE=ubuntu:22.04
+
+FROM ${BASE_IMAGE} AS builder
+ARG BACKEND=rerankers
+ARG BUILD_TYPE
+ENV BUILD_TYPE=${BUILD_TYPE}
+ARG CUDA_MAJOR_VERSION
+ARG CUDA_MINOR_VERSION
+ARG SKIP_DRIVERS=false
+ENV CUDA_MAJOR_VERSION=${CUDA_MAJOR_VERSION}
+ENV CUDA_MINOR_VERSION=${CUDA_MINOR_VERSION}
+ENV DEBIAN_FRONTEND=noninteractive
+ARG TARGETARCH
+ARG TARGETVARIANT
+ARG GO_VERSION=1.22.6
+
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends \
+        build-essential \
+        ccache \
+        ca-certificates \
+        make \
+        curl unzip \
+        libssl-dev && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+
+
+# Cuda
+ENV PATH=/usr/local/cuda/bin:${PATH}
+
+# HipBLAS requirements
+ENV PATH=/opt/rocm/bin:${PATH}
+
+# Vulkan requirements
+RUN <<EOT bash
+    if [ "${BUILD_TYPE}" = "vulkan" ] && [ "${SKIP_DRIVERS}" = "false" ]; then
+        apt-get update && \
+        apt-get install -y  --no-install-recommends \
+            software-properties-common pciutils wget gpg-agent && \
+        wget -qO - https://packages.lunarg.com/lunarg-signing-key-pub.asc | apt-key add - && \
+        wget -qO /etc/apt/sources.list.d/lunarg-vulkan-jammy.list https://packages.lunarg.com/vulkan/lunarg-vulkan-jammy.list && \
+        apt-get update && \
+        apt-get install -y \
+            vulkan-sdk && \
+        apt-get clean && \
+        rm -rf /var/lib/apt/lists/*
+    fi
+EOT
+
+# CuBLAS requirements
+RUN <<EOT bash
+    if [ "${BUILD_TYPE}" = "cublas" ] && [ "${SKIP_DRIVERS}" = "false" ]; then
+        apt-get update && \
+        apt-get install -y  --no-install-recommends \
+            software-properties-common pciutils
+        if [ "amd64" = "$TARGETARCH" ]; then
+            curl -O https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-keyring_1.1-1_all.deb
+        fi
+        if [ "arm64" = "$TARGETARCH" ]; then
+            curl -O https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/arm64/cuda-keyring_1.1-1_all.deb
+        fi
+        dpkg -i cuda-keyring_1.1-1_all.deb && \
+        rm -f cuda-keyring_1.1-1_all.deb && \
+        apt-get update && \
+        apt-get install -y --no-install-recommends \
+            cuda-nvcc-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} \
+            libcufft-dev-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} \
+            libcurand-dev-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} \
+            libcublas-dev-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} \
+            libcusparse-dev-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} \
+            libcusolver-dev-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} && \
+        apt-get clean && \
+        rm -rf /var/lib/apt/lists/*
+    fi
+EOT
+
+# If we are building with clblas support, we need the libraries for the builds
+RUN if [ "${BUILD_TYPE}" = "clblas" ] && [ "${SKIP_DRIVERS}" = "false" ]; then \
+        apt-get update && \
+        apt-get install -y --no-install-recommends \
+            libclblast-dev && \
+        apt-get clean && \
+        rm -rf /var/lib/apt/lists/* \
+    ; fi
+
+RUN if [ "${BUILD_TYPE}" = "hipblas" ] && [ "${SKIP_DRIVERS}" = "false" ]; then \
+        apt-get update && \
+        apt-get install -y --no-install-recommends \
+            hipblas-dev \
+            rocblas-dev && \
+        apt-get clean && \
+        rm -rf /var/lib/apt/lists/* && \
+        # I have no idea why, but the ROCM lib packages don't trigger ldconfig after they install, which results in local-ai and others not being able
+        # to locate the libraries. We run ldconfig ourselves to work around this packaging deficiency
+        ldconfig \
+    ; fi
+
+# Install Go
+RUN curl -L -s https://go.dev/dl/go${GO_VERSION}.linux-${TARGETARCH}.tar.gz | tar -C /usr/local -xz
+ENV PATH=$PATH:/root/go/bin:/usr/local/go/bin:/usr/local/bin
+
+# Install grpc compilers
+RUN go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.2 && \
+    go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@1958fcbe2ca8bd93af633f11e97d44e567e945af
+RUN echo "TARGETARCH: $TARGETARCH"
+
+# We need protoc installed, and the version in 22.04 is too old.  We will create one as part installing the GRPC build below
+# but that will also being in a newer version of absl which stablediffusion cannot compile with.  This version of protoc is only
+# here so that we can generate the grpc code for the stablediffusion build
+RUN <<EOT bash
+    if [ "amd64" = "$TARGETARCH" ]; then
+        curl -L -s https://github.com/protocolbuffers/protobuf/releases/download/v27.1/protoc-27.1-linux-x86_64.zip -o protoc.zip && \
+        unzip -j -d /usr/local/bin protoc.zip bin/protoc && \
+        rm protoc.zip
+    fi
+    if [ "arm64" = "$TARGETARCH" ]; then
+        curl -L -s https://github.com/protocolbuffers/protobuf/releases/download/v27.1/protoc-27.1-linux-aarch_64.zip -o protoc.zip && \
+        unzip -j -d /usr/local/bin protoc.zip bin/protoc && \
+        rm protoc.zip
+    fi
+EOT
+
+COPY . /LocalAI
+
+RUN cd /LocalAI && make backend-assets/grpc/bark-cpp
+
+FROM scratch
+
+COPY --from=builder /LocalAI/backend-assets/grpc/bark-cpp ./
+COPY --from=builder /LocalAI/backend/go/bark/run.sh ./
\ No newline at end of file
diff --git a/backend/go/bark/run.sh b/backend/go/bark/run.sh
new file mode 100755
index 00000000..84bf4533
--- /dev/null
+++ b/backend/go/bark/run.sh
@@ -0,0 +1,3 @@
+#!/bin/bash
+set -ex
+exec ./bark-cpp
\ No newline at end of file
diff --git a/backend/index.yaml b/backend/index.yaml
index 962b3558..71b19f72 100644
--- a/backend/index.yaml
+++ b/backend/index.yaml
@@ -42,19 +42,19 @@
   name: "intel-sycl-f16-vllm"
   uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-vllm"
 - !!merge <<: *vllm
-  name: "cuda11-vllm-master"
+  name: "cuda11-vllm-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-vllm"
 - !!merge <<: *vllm
-  name: "cuda12-vllm-master"
+  name: "cuda12-vllm-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-vllm"
 - !!merge <<: *vllm
-  name: "rocm-vllm-master"
+  name: "rocm-vllm-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-vllm"
 - !!merge <<: *vllm
-  name: "intel-sycl-f32-vllm-master"
+  name: "intel-sycl-f32-vllm-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-vllm"
 - !!merge <<: *vllm
-  name: "intel-sycl-f16-vllm-master"
+  name: "intel-sycl-f16-vllm-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-vllm"
 ## Rerankers
 - name: "cuda11-rerankers"
@@ -72,22 +72,22 @@
 - name: "rocm-rerankers"
   uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-rerankers"
   alias: "rocm-rerankers"
-- name: "cuda11-rerankers-master"
+- name: "cuda11-rerankers-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-rerankers"
   alias: "rerankers"
 
-- name: "cuda12-rerankers-master"
+- name: "cuda12-rerankers-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-rerankers"
   alias: "rerankers"
-- name: "rocm-rerankers-master"
+- name: "rocm-rerankers-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-rerankers"
   alias: "rerankers"
 
-- name: "intel-sycl-f32-rerankers-master"
+- name: "intel-sycl-f32-rerankers-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-rerankers"
   alias: "rerankers"
 
-- name: "intel-sycl-f16-rerankers-master"
+- name: "intel-sycl-f16-rerankers-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-rerankers"
   alias: "rerankers"
 ## Transformers
@@ -115,22 +115,22 @@
   name: "intel-sycl-f16-transformers"
   uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-transformers"
 - !!merge <<: *transformers
-  name: "cuda11-transformers-master"
+  name: "cuda11-transformers-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-transformers"
 - !!merge <<: *transformers
   name: "cuda11-transformers"
   uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-11-transformers"
 - !!merge <<: *transformers
-  name: "cuda12-transformers-master"
+  name: "cuda12-transformers-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-transformers"
 - !!merge <<: *transformers
-  name: "rocm-transformers-master"
+  name: "rocm-transformers-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-transformers"
 - !!merge <<: *transformers
-  name: "intel-sycl-f32-transformers-master"
+  name: "intel-sycl-f32-transformers-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-transformers"
 - !!merge <<: *transformers
-  name: "intel-sycl-f16-transformers-master"
+  name: "intel-sycl-f16-transformers-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-transformers"
 ## Diffusers
 - &diffusers
@@ -157,16 +157,16 @@
   name: "intel-sycl-f32-diffusers"
   uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-diffusers"
 - !!merge <<: *diffusers
-  name: "cuda11-diffusers-master"
+  name: "cuda11-diffusers-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-diffusers"
 - !!merge <<: *diffusers
-  name: "cuda12-diffusers-master"
+  name: "cuda12-diffusers-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-diffusers"
 - !!merge <<: *diffusers
-  name: "rocm-diffusers-master"
+  name: "rocm-diffusers-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-diffusers"
 - !!merge <<: *diffusers
-  name: "intel-sycl-f32-diffusers-master"
+  name: "intel-sycl-f32-diffusers-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-diffusers"
   ## exllama2
 - &exllama2
@@ -186,10 +186,10 @@
   name: "cuda12-exllama2"
   uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-exllama2"
 - !!merge <<: *exllama2
-  name: "cuda11-exllama2-master"
+  name: "cuda11-exllama2-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-exllama2"
 - !!merge <<: *exllama2
-  name: "cuda12-exllama2-master"
+  name: "cuda12-exllama2-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-exllama2"
 ## kokoro
 - &kokoro
@@ -204,14 +204,14 @@
     - TTS
     - LLM
   license: apache-2.0
-  name: "cuda11-kokoro-master"
+  name: "cuda11-kokoro-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-kokoro"
   alias: "kokoro"
 - !!merge <<: *kokoro
-  name: "cuda12-kokoro-master"
+  name: "cuda12-kokoro-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-kokoro"
 - !!merge <<: *kokoro
-  name: "rocm-kokoro-master"
+  name: "rocm-kokoro-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-kokoro"
 - !!merge <<: *kokoro
   name: "sycl-f32-kokoro"
@@ -220,10 +220,10 @@
   name: "sycl-f16-kokoro"
   uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-kokoro"
 - !!merge <<: *kokoro
-  name: "sycl-f16-kokoro-master"
+  name: "sycl-f16-kokoro-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-kokoro"
 - !!merge <<: *kokoro
-  name: "sycl-f32-kokoro-master"
+  name: "sycl-f32-kokoro-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-kokoro"
 ## faster-whisper
 - &faster-whisper
@@ -237,14 +237,14 @@
     - speech-to-text
     - Whisper
   license: MIT
-  name: "cuda11-faster-whisper-master"
+  name: "cuda11-faster-whisper-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-faster-whisper"
   alias: "faster-whisper"
 - !!merge <<: *faster-whisper
-  name: "cuda12-faster-whisper-master"
+  name: "cuda12-faster-whisper-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-faster-whisper"
 - !!merge <<: *faster-whisper
-  name: "rocm-faster-whisper-master"
+  name: "rocm-faster-whisper-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-faster-whisper"
 - !!merge <<: *faster-whisper
   name: "sycl-f32-faster-whisper"
@@ -253,10 +253,10 @@
   name: "sycl-f16-faster-whisper"
   uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-faster-whisper"
 - !!merge <<: *faster-whisper
-  name: "sycl-f32-faster-whisper-master"
+  name: "sycl-f32-faster-whisper-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-faster-whisper"
 - !!merge <<: *faster-whisper
-  name: "sycl-f16-faster-whisper-master"
+  name: "sycl-f16-faster-whisper-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-faster-whisper"
 ## coqui
 - &coqui
@@ -274,15 +274,15 @@
     - text-to-speech
     - TTS
   license: mpl-2.0
-  name: "cuda11-coqui-master"
+  name: "cuda11-coqui-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-coqui"
   alias: "coqui"
   icon: https://avatars.githubusercontent.com/u/1338804?s=200&v=4
 - !!merge <<: *coqui
-  name: "cuda12-coqui-master"
+  name: "cuda12-coqui-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-coqui"
 - !!merge <<: *coqui
-  name: "rocm-coqui-master"
+  name: "rocm-coqui-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-coqui"
 - !!merge <<: *coqui
   name: "sycl-f32-coqui"
@@ -291,10 +291,10 @@
   name: "sycl-f16-coqui"
   uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-coqui"
 - !!merge <<: *coqui
-  name: "sycl-f32-coqui-master"
+  name: "sycl-f32-coqui-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-coqui"
 - !!merge <<: *coqui
-  name: "sycl-f16-coqui-master"
+  name: "sycl-f16-coqui-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-coqui"
 ## bark
 - &bark
@@ -306,15 +306,15 @@
     - text-to-speech
     - TTS
   license: MIT
-  name: "cuda11-bark-master"
+  name: "cuda11-bark-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-bark"
   alias: "bark"
   icon: https://avatars.githubusercontent.com/u/99442120?s=200&v=4
 - !!merge <<: *bark
-  name: "cuda12-bark-master"
+  name: "cuda12-bark-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-bark"
 - !!merge <<: *bark
-  name: "rocm-bark-master"
+  name: "rocm-bark-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-bark"
 - !!merge <<: *bark
   name: "sycl-f32-bark"
@@ -323,11 +323,40 @@
   name: "sycl-f16-bark"
   uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-bark"
 - !!merge <<: *bark
-  name: "sycl-f32-bark-master"
+  name: "sycl-f32-bark-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-bark"
 - !!merge <<: *bark
-  name: "sycl-f16-bark-master"
+  name: "sycl-f16-bark-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-bark"
+- &barkcpp
+  urls:
+    - https://github.com/PABannier/bark.cpp
+  description: |
+      With bark.cpp, our goal is to bring real-time realistic multilingual text-to-speech generation to the community.
+
+      Plain C/C++ implementation without dependencies
+      AVX, AVX2 and AVX512 for x86 architectures
+      CPU and GPU compatible backends
+      Mixed F16 / F32 precision
+      4-bit, 5-bit and 8-bit integer quantization
+      Metal and CUDA backends
+
+      Models supported
+
+          Bark Small
+          Bark Large
+  tags:
+    - text-to-speech
+    - TTS
+  license: MIT
+  icon: https://github.com/PABannier/bark.cpp/raw/main/assets/banner.png
+  name: "bark-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-bark-cpp"
+  alias: "bark-cpp"
+- !!merge <<: *barkcpp
+  name: "bark-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-bark-cpp"
+  alias: "bark-cpp"
 ## chatterbox
 - &chatterbox
   urls:
@@ -340,11 +369,11 @@
     - TTS
   license: MIT
   icon: https://private-user-images.githubusercontent.com/660224/448166653-bd8c5f03-e91d-4ee5-b680-57355da204d1.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTUiLCJleHAiOjE3NTAxOTE0MDAsIm5iZiI6MTc1MDE5MTEwMCwicGF0aCI6Ii82NjAyMjQvNDQ4MTY2NjUzLWJkOGM1ZjAzLWU5MWQtNGVlNS1iNjgwLTU3MzU1ZGEyMDRkMS5wbmc_WC1BbXotQWxnb3JpdGhtPUFXUzQtSE1BQy1TSEEyNTYmWC1BbXotQ3JlZGVudGlhbD1BS0lBVkNPRFlMU0E1M1BRSzRaQSUyRjIwMjUwNjE3JTJGdXMtZWFzdC0xJTJGczMlMkZhd3M0X3JlcXVlc3QmWC1BbXotRGF0ZT0yMDI1MDYxN1QyMDExNDBaJlgtQW16LUV4cGlyZXM9MzAwJlgtQW16LVNpZ25hdHVyZT1hMmI1NGY3OGFiZTlhNGFkNTVlYTY4NTIwMWEzODRiZGE4YzdhNGQ5MGNhNzE3MDYyYTA2NDIxYTkyYzhiODkwJlgtQW16LVNpZ25lZEhlYWRlcnM9aG9zdCJ9.mR9kM9xX0TdzPuSpuspCllHYQiq79dFQ2rtuNvjrl6w
-  name: "cuda11-chatterbox-master"
+  name: "cuda11-chatterbox-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-chatterbox"
   alias: "chatterbox"
 - !!merge <<: *chatterbox
-  name: "cuda12-chatterbox-master"
+  name: "cuda12-chatterbox-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-chatterbox"
 - !!merge <<: *chatterbox
   name: "cuda11-chatterbox"