feat(realtime): Add Liquid Audio s2s model and assistant mode on talk page

.agents/api-endpoints-and-auth.md

@@ -284,7 +284,17 @@ Also bump the expected-length count in `api_instructions_test.go` and add the na
 
 ### 3. `capabilities.js` symbol (for new model-config FLAG_* flags)
 
-If your feature needs a new `FLAG_*` usecase flag in `core/config/model_config.go` (so users can filter gallery models by it, and so `/v1/models` surfaces it), also declare the matching symbol in `core/http/react-ui/src/utils/capabilities.js`:
+If your feature needs a new `FLAG_*` usecase flag in `core/config/model_config.go` (so users can filter gallery models by it, and so `/v1/models` surfaces it), you need to update **all** of:
+
+- `Usecase<Name>` string constant in `core/config/backend_capabilities.go`
+- `UsecaseInfoMap` entry mapping the string to its flag + gRPC method
+- `FLAG_<NAME>` bitmask in `core/config/model_config.go`
+- `GetAllModelConfigUsecases()` map entry (otherwise the YAML loader silently ignores the string)
+- `ModalityGroups` membership if the flag should affect `IsMultimodal()` (e.g. realtime_audio is in both speech-input and audio-output groups so a lone flag still reads as multimodal)
+- `GuessUsecases()` branch listing the backends that own this capability
+- `usecaseFilters` in `core/http/routes/ui_api.go` (drives the gallery filter dropdown)
+- `Models.jsx` `FILTERS` array + matching `filters.<camelCase>` i18n key in `core/http/react-ui/public/locales/en/models.json`
+- `core/http/react-ui/src/utils/capabilities.js`:
 
 ```js
 export const CAP_MY_CAPABILITY = 'FLAG_MY_CAPABILITY'

.github/backend-matrix.yml

@@ -278,6 +278,19 @@ include:
     dockerfile: "./backend/Dockerfile.python"
     context: "./"
     ubuntu-version: '2404'
+  - build-type: 'cublas'
+    cuda-major-version: "12"
+    cuda-minor-version: "8"
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-nvidia-cuda-12-liquid-audio'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "liquid-audio"
+    dockerfile: "./backend/Dockerfile.python"
+    context: "./"
+    ubuntu-version: '2404'
   - build-type: 'cublas'
     cuda-major-version: "12"
     cuda-minor-version: "8"
@@ -808,6 +821,19 @@ include:
     dockerfile: "./backend/Dockerfile.python"
     context: "./"
     ubuntu-version: '2404'
+  - build-type: 'cublas'
+    cuda-major-version: "13"
+    cuda-minor-version: "0"
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-nvidia-cuda-13-liquid-audio'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "liquid-audio"
+    dockerfile: "./backend/Dockerfile.python"
+    context: "./"
+    ubuntu-version: '2404'
   - build-type: 'cublas'
     cuda-major-version: "13"
     cuda-minor-version: "0"
@@ -1088,6 +1114,19 @@ include:
     backend: "vibevoice"
     dockerfile: "./backend/Dockerfile.python"
     context: "./"
+  - build-type: 'l4t'
+    cuda-major-version: "13"
+    cuda-minor-version: "0"
+    platforms: 'linux/arm64'
+    tag-latest: 'auto'
+    tag-suffix: '-nvidia-l4t-cuda-13-arm64-liquid-audio'
+    runs-on: 'ubuntu-24.04-arm'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    ubuntu-version: '2404'
+    backend: "liquid-audio"
+    dockerfile: "./backend/Dockerfile.python"
+    context: "./"
   - build-type: 'l4t'
     cuda-major-version: "13"
     cuda-minor-version: "0"
@@ -1729,6 +1768,19 @@ include:
     dockerfile: "./backend/Dockerfile.python"
     context: "./"
     ubuntu-version: '2404'
+  - build-type: 'hipblas'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-rocm-hipblas-liquid-audio'
+    runs-on: 'ubuntu-latest'
+    base-image: "rocm/dev-ubuntu-24.04:7.2.1"
+    skip-drivers: 'false'
+    backend: "liquid-audio"
+    dockerfile: "./backend/Dockerfile.python"
+    context: "./"
+    ubuntu-version: '2404'
   - build-type: 'hipblas'
     cuda-major-version: ""
     cuda-minor-version: ""
@@ -2177,6 +2229,19 @@ include:
     dockerfile: "./backend/Dockerfile.python"
     context: "./"
     ubuntu-version: '2404'
+  - build-type: 'intel'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-intel-liquid-audio'
+    runs-on: 'ubuntu-latest'
+    base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
+    skip-drivers: 'false'
+    backend: "liquid-audio"
+    dockerfile: "./backend/Dockerfile.python"
+    context: "./"
+    ubuntu-version: '2404'
   - build-type: 'intel'
     cuda-major-version: ""
     cuda-minor-version: ""
@@ -3503,6 +3568,20 @@ include:
     dockerfile: "./backend/Dockerfile.python"
     context: "./"
     ubuntu-version: '2404'
+  - build-type: ''
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    platform-tag: 'amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-cpu-liquid-audio'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "liquid-audio"
+    dockerfile: "./backend/Dockerfile.python"
+    context: "./"
+    ubuntu-version: '2404'
   - build-type: ''
     cuda-major-version: ""
     cuda-minor-version: ""

.github/workflows/test-extra.yml

@@ -28,6 +28,7 @@ jobs:
       qwen-asr: ${{ steps.detect.outputs.qwen-asr }}
       nemo: ${{ steps.detect.outputs.nemo }}
       voxcpm: ${{ steps.detect.outputs.voxcpm }}
+      liquid-audio: ${{ steps.detect.outputs.liquid-audio }}
       llama-cpp-quantization: ${{ steps.detect.outputs.llama-cpp-quantization }}
       llama-cpp: ${{ steps.detect.outputs.llama-cpp }}
       ik-llama-cpp: ${{ steps.detect.outputs.ik-llama-cpp }}
@@ -447,6 +448,32 @@ jobs:
         run: |
           make --jobs=5 --output-sync=target -C backend/python/voxcpm
           make --jobs=5 --output-sync=target -C backend/python/voxcpm test
+  # liquid-audio: LFM2.5-Audio any-to-any backend. The CI smoke test
+  # exercises Health() and LoadModel(mode:finetune) — fine-tune mode
+  # short-circuits before pulling weights (backend.py:192), so no
+  # HuggingFace download or GPU is needed. The full-inference path is
+  # gated on LIQUID_AUDIO_MODEL_ID, which we don't set here.
+  tests-liquid-audio:
+    needs: detect-changes
+    if: needs.detect-changes.outputs.liquid-audio == '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 ffmpeg
+          sudo apt-get install -y ca-certificates cmake curl patch python3-pip
+          # Install UV
+          curl -LsSf https://astral.sh/uv/install.sh | sh
+          pip install --user --no-cache-dir grpcio-tools==1.64.1
+      - name: Test liquid-audio
+        run: |
+          make --jobs=5 --output-sync=target -C backend/python/liquid-audio
+          make --jobs=5 --output-sync=target -C backend/python/liquid-audio test
   tests-llama-cpp-quantization:
     needs: detect-changes
     if: needs.detect-changes.outputs.llama-cpp-quantization == 'true' || needs.detect-changes.outputs.run-all == 'true'

Makefile

@@ -1,5 +1,5 @@
 # Disable parallel execution for backend builds
-.NOTPARALLEL: backends/diffusers backends/llama-cpp backends/turboquant backends/outetts backends/piper backends/stablediffusion-ggml backends/whisper backends/faster-whisper backends/silero-vad backends/local-store backends/huggingface backends/rfdetr backends/insightface backends/speaker-recognition 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/sglang 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 backends/sam3-cpp backends/qwen3-tts-cpp backends/vibevoice-cpp backends/localvqe backends/tinygrad backends/sherpa-onnx backends/ds4 backends/ds4-darwin
+.NOTPARALLEL: backends/diffusers backends/llama-cpp backends/turboquant backends/outetts backends/piper backends/stablediffusion-ggml backends/whisper backends/faster-whisper backends/silero-vad backends/local-store backends/huggingface backends/rfdetr backends/insightface backends/speaker-recognition 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/sglang 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 backends/sam3-cpp backends/qwen3-tts-cpp backends/vibevoice-cpp backends/localvqe backends/tinygrad backends/sherpa-onnx backends/ds4 backends/ds4-darwin backends/liquid-audio
 
 GOCMD=go
 GOTEST=$(GOCMD) test
@@ -463,6 +463,7 @@ prepare-test-extra: protogen-python
 	$(MAKE) -C backend/python/vllm-omni
 	$(MAKE) -C backend/python/sglang
 	$(MAKE) -C backend/python/vibevoice
+	$(MAKE) -C backend/python/liquid-audio
 	$(MAKE) -C backend/python/moonshine
 	$(MAKE) -C backend/python/pocket-tts
 	$(MAKE) -C backend/python/qwen-tts
@@ -488,6 +489,7 @@ test-extra: prepare-test-extra
 	$(MAKE) -C backend/python/vllm test
 	$(MAKE) -C backend/python/vllm-omni test
 	$(MAKE) -C backend/python/vibevoice test
+	$(MAKE) -C backend/python/liquid-audio test
 	$(MAKE) -C backend/python/moonshine test
 	$(MAKE) -C backend/python/pocket-tts test
 	$(MAKE) -C backend/python/qwen-tts test
@@ -1092,6 +1094,7 @@ BACKEND_SGLANG = sglang|python|.|false|true
 BACKEND_DIFFUSERS = diffusers|python|.|--progress=plain|true
 BACKEND_CHATTERBOX = chatterbox|python|.|false|true
 BACKEND_VIBEVOICE = vibevoice|python|.|--progress=plain|true
+BACKEND_LIQUID_AUDIO = liquid-audio|python|.|--progress=plain|true
 BACKEND_MOONSHINE = moonshine|python|.|false|true
 BACKEND_POCKET_TTS = pocket-tts|python|.|false|true
 BACKEND_QWEN_TTS = qwen-tts|python|.|false|true
@@ -1169,6 +1172,7 @@ $(eval $(call generate-docker-build-target,$(BACKEND_SGLANG)))
 $(eval $(call generate-docker-build-target,$(BACKEND_DIFFUSERS)))
 $(eval $(call generate-docker-build-target,$(BACKEND_CHATTERBOX)))
 $(eval $(call generate-docker-build-target,$(BACKEND_VIBEVOICE)))
+$(eval $(call generate-docker-build-target,$(BACKEND_LIQUID_AUDIO)))
 $(eval $(call generate-docker-build-target,$(BACKEND_MOONSHINE)))
 $(eval $(call generate-docker-build-target,$(BACKEND_POCKET_TTS)))
 $(eval $(call generate-docker-build-target,$(BACKEND_QWEN_TTS)))
@@ -1197,7 +1201,7 @@ $(eval $(call generate-docker-build-target,$(BACKEND_SHERPA_ONNX)))
 docker-save-%: backend-images
 	docker save local-ai-backend:$* -o backend-images/$*.tar
 
-docker-build-backends: docker-build-llama-cpp docker-build-ik-llama-cpp docker-build-turboquant docker-build-ds4 docker-build-rerankers docker-build-vllm docker-build-vllm-omni docker-build-sglang 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-tinygrad docker-build-kokoros docker-build-sam3-cpp docker-build-qwen3-tts-cpp docker-build-vibevoice-cpp docker-build-localvqe docker-build-insightface docker-build-speaker-recognition docker-build-sherpa-onnx
+docker-build-backends: docker-build-llama-cpp docker-build-ik-llama-cpp docker-build-turboquant docker-build-ds4 docker-build-rerankers docker-build-vllm docker-build-vllm-omni docker-build-sglang 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-liquid-audio 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-tinygrad docker-build-kokoros docker-build-sam3-cpp docker-build-qwen3-tts-cpp docker-build-vibevoice-cpp docker-build-localvqe docker-build-insightface docker-build-speaker-recognition docker-build-sherpa-onnx
 
 ########################################################
 ### Mock Backend for E2E Tests

backend/backend.proto

@@ -48,6 +48,11 @@ service Backend {
 
   rpc AudioTransform(AudioTransformRequest) returns (AudioTransformResult) {}
   rpc AudioTransformStream(stream AudioTransformFrameRequest) returns (stream AudioTransformFrameResponse) {}
+  // AudioToAudioStream is the bidirectional any-to-any S2S RPC. Backends
+  // that load a speech-to-speech model consume input audio frames and emit
+  // interleaved audio + transcript + tool-call deltas as typed events.
+  // Backends without S2S support return UNIMPLEMENTED.
+  rpc AudioToAudioStream(stream AudioToAudioRequest) returns (stream AudioToAudioResponse) {}
 
   rpc ModelMetadata(ModelOptions) returns (ModelMetadataResponse) {}
 
@@ -768,6 +773,93 @@ message AudioTransformFrameResponse {
   int64 frame_index = 2;
 }
 
+// === AudioToAudioStream messages =========================================
+//
+// Bidirectional stream between the LocalAI core and an any-to-any audio
+// model. The client opens the stream with a Config payload, then alternates
+// Frame (input audio) and Control (turn boundaries, function-call results,
+// session updates) payloads. The server streams back typed events: audio
+// frames carry PCM in `pcm`; transcript / tool-call deltas carry JSON in
+// `meta`; the stream ends with a `response.done` (success) or `error` event.
+
+message AudioToAudioRequest {
+  oneof payload {
+    AudioToAudioConfig  config  = 1;
+    AudioToAudioFrame   frame   = 2;
+    AudioToAudioControl control = 3;
+  }
+}
+
+message AudioToAudioConfig {
+  // PCM format for client→server audio. 0 => backend default
+  // (16 kHz for the LFM2-Audio Conformer encoder).
+  int32 input_sample_rate = 1;
+  // Preferred server→client audio rate. 0 => backend default
+  // (24 kHz for the LFM2-Audio vocoder).
+  int32 output_sample_rate = 2;
+  // Optional system prompt override. Empty => backend chooses based on
+  // mode (e.g. "Respond with interleaved text and audio.").
+  string system_prompt = 3;
+  // Optional baked-voice id. Models that only ship a fixed set of
+  // voices (e.g. LFM2-Audio: us_male/us_female/uk_male/uk_female) match
+  // this against their voice table; an empty string keeps the default.
+  string voice = 4;
+  // JSON-encoded array of tool definitions in OpenAI Chat Completions
+  // format. Empty => no tools.
+  string tools = 5;
+  // Free-form sampling / decoding parameters (temperature, top_k,
+  // max_new_tokens, audio_top_k, etc).
+  map<string, string> params = 6;
+  // True => reset any session-scoped state before processing further
+  // frames on this stream. The first Config implicitly resets.
+  bool reset = 7;
+}
+
+message AudioToAudioFrame {
+  // Raw PCM s16le mono at config.input_sample_rate. Empty pcm + end_of_input
+  // is a valid "user finished speaking" marker without trailing audio.
+  bytes pcm = 1;
+  // Marks the last frame of a user turn. The backend may begin emitting
+  // a response immediately after seeing this.
+  bool end_of_input = 2;
+}
+
+message AudioToAudioControl {
+  // Free-form control event names. Initial set:
+  //   "input_audio_buffer.commit"     — user finished speaking
+  //   "response.cancel"               — abort in-flight generation
+  //   "conversation.item.create"      — inject a non-audio item (e.g.
+  //                                     function_call_output as JSON in
+  //                                     `payload`)
+  //   "session.update"                — re-configure mid-stream
+  string event = 1;
+  // Event-specific JSON payload.
+  bytes payload = 2;
+}
+
+message AudioToAudioResponse {
+  // Event identifies what this frame carries. Mirrors the OpenAI Realtime
+  // API server-event names where applicable. Initial set:
+  //   "response.audio.delta"
+  //   "response.audio_transcript.delta"
+  //   "response.function_call_arguments.delta"
+  //   "response.function_call_arguments.done"
+  //   "response.done"
+  //   "error"
+  string event = 1;
+  // Populated when event = response.audio.delta.
+  bytes pcm = 2;
+  // Populated alongside pcm to identify its rate. 0 => same as the
+  // session's negotiated output_sample_rate.
+  int32 sample_rate = 3;
+  // JSON payload for non-PCM events (transcript chunk, tool args, error
+  // body).
+  bytes meta = 4;
+  // Monotonic per-stream counter, useful for client reordering and
+  // debugging.
+  int64 sequence = 5;
+}
+
 message ModelMetadataResponse {
   bool supports_thinking = 1;
   string rendered_template = 2;  // The rendered chat template with enable_thinking=true (empty if not applicable)