feat: Add Kokoros backend (#9212)

Signed-off-by: Richard Palethorpe <io@richiejp.com>

Author: richiejp

.github/workflows/test-extra.yml

@@ -31,6 +31,7 @@ jobs:
       llama-cpp-quantization: ${{ steps.detect.outputs.llama-cpp-quantization }}
       acestep-cpp: ${{ steps.detect.outputs.acestep-cpp }}
       voxtral: ${{ steps.detect.outputs.voxtral }}
+      kokoros: ${{ steps.detect.outputs.kokoros }}
     steps:
       - name: Checkout repository
         uses: actions/checkout@v6
@@ -528,3 +529,25 @@ jobs:
       - name: Test voxtral
         run: |
           make --jobs=5 --output-sync=target -C backend/go/voxtral test
+  tests-kokoros:
+    needs: detect-changes
+    if: needs.detect-changes.outputs.kokoros == 'true' || needs.detect-changes.outputs.run-all == 'true'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Clone
+        uses: actions/checkout@v6
+        with:
+          submodules: true
+      - name: Dependencies
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y build-essential cmake pkg-config protobuf-compiler clang libclang-dev
+          sudo apt-get install -y espeak-ng libespeak-ng-dev libsonic-dev libpcaudio-dev libopus-dev libssl-dev
+          curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y
+          echo "$HOME/.cargo/bin" >> $GITHUB_PATH
+      - name: Build kokoros
+        run: |
+          make -C backend/rust/kokoros kokoros-grpc
+      - name: Test kokoros
+        run: |
+          make -C backend/rust/kokoros test

.gitmodules

@@ -1,3 +1,6 @@
 [submodule "docs/themes/hugo-theme-relearn"]
 	path = docs/themes/hugo-theme-relearn
 	url = https://github.com/McShelby/hugo-theme-relearn.git
+[submodule "backend/rust/kokoros/sources/Kokoros"]
+	path = backend/rust/kokoros/sources/Kokoros
+	url = https://github.com/lucasjinreal/Kokoros

Makefile

@@ -1,5 +1,5 @@
 # Disable parallel execution for backend builds
-.NOTPARALLEL: backends/diffusers backends/llama-cpp backends/outetts backends/piper backends/stablediffusion-ggml backends/whisper backends/faster-whisper backends/silero-vad backends/local-store backends/huggingface backends/rfdetr backends/kitten-tts backends/kokoro backends/chatterbox backends/llama-cpp-darwin backends/neutts build-darwin-python-backend build-darwin-go-backend backends/mlx backends/diffuser-darwin backends/mlx-vlm backends/mlx-audio backends/mlx-distributed backends/stablediffusion-ggml-darwin backends/vllm backends/vllm-omni backends/moonshine backends/pocket-tts backends/qwen-tts backends/faster-qwen3-tts backends/qwen-asr backends/nemo backends/voxcpm backends/whisperx backends/ace-step backends/acestep-cpp backends/fish-speech backends/voxtral backends/opus backends/trl backends/llama-cpp-quantization
+.NOTPARALLEL: backends/diffusers backends/llama-cpp backends/outetts backends/piper backends/stablediffusion-ggml backends/whisper backends/faster-whisper backends/silero-vad backends/local-store backends/huggingface backends/rfdetr backends/kitten-tts backends/kokoro backends/chatterbox backends/llama-cpp-darwin backends/neutts build-darwin-python-backend build-darwin-go-backend backends/mlx backends/diffuser-darwin backends/mlx-vlm backends/mlx-audio backends/mlx-distributed backends/stablediffusion-ggml-darwin backends/vllm backends/vllm-omni backends/moonshine backends/pocket-tts backends/qwen-tts backends/faster-qwen3-tts backends/qwen-asr backends/nemo backends/voxcpm backends/whisperx backends/ace-step backends/acestep-cpp backends/fish-speech backends/voxtral backends/opus backends/trl backends/llama-cpp-quantization backends/kokoros
 
 GOCMD=go
 GOTEST=$(GOCMD) test
@@ -431,6 +431,7 @@ prepare-test-extra: protogen-python
 	$(MAKE) -C backend/python/whisperx
 	$(MAKE) -C backend/python/ace-step
 	$(MAKE) -C backend/python/trl
+	$(MAKE) -C backend/rust/kokoros kokoros-grpc
 
 test-extra: prepare-test-extra
 	$(MAKE) -C backend/python/transformers test
@@ -451,6 +452,7 @@ test-extra: prepare-test-extra
 	$(MAKE) -C backend/python/whisperx test
 	$(MAKE) -C backend/python/ace-step test
 	$(MAKE) -C backend/python/trl test
+	$(MAKE) -C backend/rust/kokoros test
 
 DOCKER_IMAGE?=local-ai
 IMAGE_TYPE?=core
@@ -586,6 +588,9 @@ BACKEND_MLX_DISTRIBUTED = mlx-distributed|python|./|false|true
 BACKEND_TRL = trl|python|.|false|true
 BACKEND_LLAMA_CPP_QUANTIZATION = llama-cpp-quantization|python|.|false|true
 
+# Rust backends
+BACKEND_KOKOROS = kokoros|rust|.|false|true
+
 # Helper function to build docker image for a backend
 # Usage: $(call docker-build-backend,BACKEND_NAME,DOCKERFILE_TYPE,BUILD_CONTEXT,PROGRESS_FLAG,NEEDS_BACKEND_ARG)
 define docker-build-backend
@@ -644,12 +649,13 @@ $(eval $(call generate-docker-build-target,$(BACKEND_ACESTEP_CPP)))
 $(eval $(call generate-docker-build-target,$(BACKEND_MLX_DISTRIBUTED)))
 $(eval $(call generate-docker-build-target,$(BACKEND_TRL)))
 $(eval $(call generate-docker-build-target,$(BACKEND_LLAMA_CPP_QUANTIZATION)))
+$(eval $(call generate-docker-build-target,$(BACKEND_KOKOROS)))
 
 # Pattern rule for docker-save targets
 docker-save-%: backend-images
 	docker save local-ai-backend:$* -o backend-images/$*.tar
 
-docker-build-backends: docker-build-llama-cpp docker-build-rerankers docker-build-vllm docker-build-vllm-omni docker-build-transformers docker-build-outetts docker-build-diffusers docker-build-kokoro docker-build-faster-whisper docker-build-coqui docker-build-chatterbox docker-build-vibevoice docker-build-moonshine docker-build-pocket-tts docker-build-qwen-tts docker-build-fish-speech docker-build-faster-qwen3-tts docker-build-qwen-asr docker-build-nemo docker-build-voxcpm docker-build-whisperx docker-build-ace-step docker-build-acestep-cpp docker-build-voxtral docker-build-mlx-distributed docker-build-trl docker-build-llama-cpp-quantization
+docker-build-backends: docker-build-llama-cpp docker-build-rerankers docker-build-vllm docker-build-vllm-omni docker-build-transformers docker-build-outetts docker-build-diffusers docker-build-kokoro docker-build-faster-whisper docker-build-coqui docker-build-chatterbox docker-build-vibevoice docker-build-moonshine docker-build-pocket-tts docker-build-qwen-tts docker-build-fish-speech docker-build-faster-qwen3-tts docker-build-qwen-asr docker-build-nemo docker-build-voxcpm docker-build-whisperx docker-build-ace-step docker-build-acestep-cpp docker-build-voxtral docker-build-mlx-distributed docker-build-trl docker-build-llama-cpp-quantization docker-build-kokoros
 
 ########################################################
 ### Mock Backend for E2E Tests

backend/Dockerfile.rust

@@ -0,0 +1,39 @@
+ARG BASE_IMAGE=ubuntu:24.04
+
+FROM ${BASE_IMAGE} AS builder
+ARG BACKEND=kokoros
+ENV DEBIAN_FRONTEND=noninteractive
+ARG TARGETARCH
+ARG TARGETVARIANT
+
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends \
+        build-essential \
+        git ccache \
+        ca-certificates \
+        make cmake wget \
+        curl unzip \
+        clang \
+        pkg-config \
+        libssl-dev \
+        espeak-ng libespeak-ng-dev \
+        libsonic-dev libpcaudio-dev \
+        libopus-dev \
+        protobuf-compiler && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+
+# Install Rust
+RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y
+ENV PATH="/root/.cargo/bin:${PATH}"
+
+COPY . /LocalAI
+
+RUN git config --global --add safe.directory /LocalAI
+
+RUN make -C /LocalAI/backend/rust/${BACKEND} build
+
+FROM scratch
+ARG BACKEND=kokoros
+
+COPY --from=builder /LocalAI/backend/rust/${BACKEND}/package/. ./

backend/index.yaml

@@ -469,6 +469,26 @@
     nvidia-cuda-13: "cuda13-kokoro"
     nvidia-cuda-12: "cuda12-kokoro"
     nvidia-l4t-cuda-12: "nvidia-l4t-arm64-kokoro"
+- &kokoros
+  icon: https://avatars.githubusercontent.com/u/166769057?v=4
+  description: |
+    Kokoros is a pure Rust TTS backend using the Kokoro ONNX model (82M parameters).
+    It provides fast, high-quality text-to-speech with streaming support, built on
+    ONNX Runtime for efficient CPU inference. Supports English, Japanese, Mandarin
+    Chinese, and German.
+  urls:
+    - https://huggingface.co/hexgrad/Kokoro-82M
+    - https://github.com/lucasjinreal/Kokoros
+  tags:
+    - text-to-speech
+    - TTS
+    - Rust
+    - ONNX
+  license: apache-2.0
+  alias: "kokoros"
+  name: "kokoros"
+  capabilities:
+    default: "cpu-kokoros"
 - &coqui
   urls:
     - https://github.com/idiap/coqui-ai-TTS
@@ -2043,6 +2063,21 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-kokoro"
   mirrors:
     - localai/localai-backends:master-metal-darwin-arm64-kokoro
+## kokoros (Rust)
+- !!merge <<: *kokoros
+  name: "kokoros-development"
+  capabilities:
+    default: "cpu-kokoros-development"
+- !!merge <<: *kokoros
+  name: "cpu-kokoros"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-kokoros"
+  mirrors:
+    - localai/localai-backends:latest-cpu-kokoros
+- !!merge <<: *kokoros
+  name: "cpu-kokoros-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-cpu-kokoros"
+  mirrors:
+    - localai/localai-backends:master-cpu-kokoros
 ## faster-whisper
 - !!merge <<: *faster-whisper
   name: "faster-whisper-development"

backend/rust/kokoros/.gitignore

@@ -0,0 +1,3 @@
+/target/
+/proto/
+/package/