Add Qwen3-TTS streaming endpoint for voice synthesis (#40)

* Task completion checkpoint

* Task completion checkpoint

* Task completion checkpoint

* Add Qwen3-TTS research document for live TTS replacement

Research findings for replacing Chatterbox TTS with Qwen3-TTS-12Hz-0.6B-Base:

- Current TTS: Chatterbox-Turbo-ONNX with batch-only generation, no streaming
- Qwen3-TTS: 97ms end-to-end latency, streaming support, 3-second voice cloning
- Voice cloning: Requires 3s reference audio + transcript (Makima voice planned)
- Integration: Python service with WebSocket bridge (no ONNX export available)
- Languages: 10 supported including English and Japanese

Document includes:
- Current architecture analysis (makima/src/tts.rs)
- Qwen3-TTS capabilities and requirements
- Feasibility assessment for live/streaming TTS
- Audio clip requirements for voice cloning
- Preliminary technical approach with architecture diagrams

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* [WIP] Heartbeat checkpoint - 2026-01-27 03:11:15 UTC

* Add Qwen3-TTS research documentation

Comprehensive research on replacing Chatterbox TTS with Qwen3-TTS-12Hz-0.6B-Base:

- Current TTS implementation analysis (Chatterbox-Turbo-ONNX in makima/src/tts.rs)
- Qwen3-TTS capabilities: 97ms streaming latency, voice cloning with 3s reference
- Cross-lingual support: Japanese voice (Makima/Tomori Kusunoki) speaking English
- Python microservice architecture recommendation (FastAPI + WebSocket)
- Implementation phases and technical approach
- Hardware requirements and dependencies

Key findings:
- Live/streaming TTS is highly feasible with 97ms latency
- Voice cloning fully supported with 0.95 speaker similarity
- Recommended: Python microservice with WebSocket streaming

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* Add comprehensive Qwen3-TTS integration specification

This specification document defines the complete integration of
Qwen3-TTS-12Hz-0.6B-Base as a replacement for the existing Chatterbox-Turbo
TTS implementation. The document covers:

## Functional Requirements
- WebSocket endpoint /api/v1/speak for streaming TTS
- Voice cloning with default Makima voice (Japanese VA speaking English)
- Support for custom voice references
- Detailed client-to-server and server-to-client message protocols
- Integration with Listen page for bidirectional speech

## Non-Functional Requirements
- Latency targets: < 200ms first audio byte
- Audio quality: 24kHz, mono, PCM16/PCM32f
- Hardware requirements: CUDA GPU with 4-8GB VRAM
- Scalability: 10 concurrent sessions per GPU

## Architecture Specification
- Python TTS microservice with FastAPI/WebSocket
- Rust proxy endpoint in makima server
- Voice prompt caching mechanism (LRU cache)
- Error handling and recovery strategies

## API Contract
- Complete WebSocket message format definitions (TypeScript)
- Error codes and responses (TTS_UNAVAILABLE, SYNTHESIS_ERROR, etc.)
- Session state machine and lifecycle management

## Voice Asset Requirements
- Makima voice clip specifications (5-10s WAV, transcript required)
- Storage location: models/voices/makima/
- Metadata format for voice management

## Testing Strategy
- Unit tests for Python TTS service and Rust proxy
- Integration tests for WebSocket flow
- Latency benchmarks with performance targets
- Test data fixtures for various text lengths

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* Add Qwen3-TTS implementation plan

Comprehensive implementation plan for replacing Chatterbox-TTS with
Qwen3-TTS streaming TTS service, including:

- Task breakdown with estimated hours for each phase
- Phase 1: Python TTS microservice (FastAPI, WebSocket)
- Phase 2: Rust proxy integration (speak.rs, tts_client.rs)
- Detailed file changes and new module structure
- Testing plan with unit, integration, and latency benchmarks
- Risk assessment with mitigation strategies
- Success criteria for each phase

Based on specification in docs/specs/qwen3-tts-spec.md

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* Add author and research references to TTS implementation plan

Add links to research documentation and author attribution.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* [WIP] Heartbeat checkpoint - 2026-01-27 03:25:06 UTC

* Add Python TTS service project structure (Phase 1.1-1.3)

Create the initial makima-tts Python service directory structure with:
- pyproject.toml with FastAPI, Qwen-TTS, and torch dependencies
- config.py with pydantic-settings TTSConfig class
- models.py with Pydantic message models (Start, Speak, Stop, Ready, etc.)

This implements tasks P1.1, P1.2, and P1.3 from the Qwen3-TTS implementation plan.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* Add TTS engine and voice manager for Qwen3-TTS (Phase 1.4-1.5)

Implement core TTS functionality:
- tts_engine.py: Qwen3-TTS wrapper with streaming audio chunk generation
- voice_manager.py: Voice prompt caching with LRU eviction and TTL support

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* [WIP] Heartbeat checkpoint - 2026-01-27 03:30:06 UTC

* Add TTS proxy client and message types (Phase 2.1, 2.2, 2.4)

- Add tts_client.rs with TtsConfig, TtsCircuitBreaker, TtsError,
  TtsProxyClient, and TtsConnection structs for WebSocket proxying
- Add TTS message types to messages.rs (TtsAudioEncoding, TtsPriority,
  TtsStartMessage, TtsSpeakMessage, TtsStopMessage, TtsClientMessage,
  TtsReadyMessage, TtsAudioChunkMessage, TtsCompleteMessage,
  TtsErrorMessage, TtsStoppedMessage, TtsServerMessage)
- Export tts_client module from server mod.rs
- tokio-tungstenite already present in Cargo.toml

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* Add TTS WebSocket handler and route (Phase 2.3, 2.5, 2.6)

- Create speak.rs WebSocket handler that proxies to Python TTS service
- Add TtsState fields (tts_client, tts_config) to AppState
- Add with_tts() builder and is_tts_healthy() methods to AppState
- Register /api/v1/speak route in the router
- Add speak module export in handlers/mod.rs

The handler forwards WebSocket messages bidirectionally between
the client and the Python TTS microservice with proper error handling.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* Add Makima voice profile assets for TTS voice cloning

Creates the voice assets directory structure with:
- manifest.json containing voice configuration (voice_id, speaker,
  language, reference audio path, and Japanese transcript placeholder)
- README.md with instructions for obtaining voice reference audio

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* Add Rust-native Qwen3-TTS integration research document

Research findings for integrating Qwen3-TTS-12Hz-0.6B-Base directly into
the makima Rust codebase without Python. Key conclusions:
- ONNX export is not viable (unsupported architecture)
- Candle (HF Rust ML framework) is the recommended approach
- Model weights available in safetensors format (2.52GB total)
- Three components needed: LM backbone, code predictor, speech tokenizer
- Crane project has Qwen3-TTS as highest priority (potential upstream)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* [WIP] Heartbeat checkpoint - 2026-01-27 11:21:43 UTC

* [WIP] Heartbeat checkpoint - 2026-01-27 11:24:19 UTC

* [WIP] Heartbeat checkpoint - 2026-01-27 11:26:43 UTC

* feat: implement Rust-native Qwen3-TTS using candle framework

Replace monolithic tts.rs with modular tts/ directory structure:

- tts/mod.rs: TtsEngine trait, TtsEngineFactory, shared types (AudioChunk,
  TtsError), and utility functions (save_wav, resample, argmax)
- tts/chatterbox.rs: existing ONNX-based ChatterboxTTS adapted to implement
  TtsEngine trait with Mutex-wrapped sessions for Send+Sync
- tts/qwen3/mod.rs: Qwen3Tts entry point with HuggingFace model loading
- tts/qwen3/config.rs: Qwen3TtsConfig parsing from HF config.json
- tts/qwen3/model.rs: 28-layer Qwen3 transformer with RoPE, GQA (16 heads,
  8 KV heads), SiLU MLP, RMS norm, and KV cache
- tts/qwen3/code_predictor.rs: 5-layer MTP module predicting 16 codebooks
- tts/qwen3/speech_tokenizer.rs: ConvNet encoder/decoder with 16-layer RVQ
- tts/qwen3/generate.rs: autoregressive generation loop with streaming support

Add candle-core, candle-nn, candle-transformers, safetensors to Cargo.toml.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* feat: integrate TTS engine into speak WebSocket handler

- Update speak.rs handler to use TTS engine directly from SharedState
  instead of returning a stub "not implemented" error
- Add TtsEngine (OnceCell lazy-loaded) to AppState in state.rs with
  get_tts_engine() method for lazy initialization on first connection
- Implement full WebSocket protocol: client sends JSON speak/cancel/stop
  messages, server streams binary PCM audio chunks and audio_end signals
- Create voices/makima/manifest.json for Makima voice profile configuration
- All files compile successfully with zero errors

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* feat: add /speak TTS page with WebSocket audio playback

Add a new /speak frontend page for text-to-speech via WebSocket.
The page accepts text input and streams synthesized PCM audio through
the Web Audio API. Includes model loading indicator, cancel support,
and connection status. Also adds a loading bar to the listen page
ControlPanel during WebSocket connection.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>

2 files changed, 160 insertions, 0 deletions

diff --git a/makima/frontend/src/routes/listen.tsx b/makima/frontend/src/routes/listen.tsx
index 55cf7e6..8af538e 100644
--- a/makima/frontend/src/routes/listen.tsx
+++ b/makima/frontend/src/routes/listen.tsx
@@ -207,6 +207,7 @@ export default function ListenPage() {
             selectedContractId={selectedContractId}
             onContractChange={setSelectedContractId}
             contractsLoading={contractsLoading}
+            connectionStatus={ws.status}
           />
         </div>
       </main>
diff --git a/makima/frontend/src/routes/speak.tsx b/makima/frontend/src/routes/speak.tsx
new file mode 100644
index 0000000..c4692ff
--- /dev/null
+++ b/makima/frontend/src/routes/speak.tsx
@@ -0,0 +1,159 @@
+import { useState, useCallback } from "react";
+import { Masthead } from "../components/Masthead";
+import { useSpeakWebSocket } from "../hooks/useSpeakWebSocket";
+
+export default function SpeakPage() {
+  const [text, setText] = useState("");
+  const tts = useSpeakWebSocket();
+
+  const handleSpeak = useCallback(() => {
+    if (!text.trim()) return;
+    tts.speak(text);
+  }, [text, tts]);
+
+  const handleCancel = useCallback(() => {
+    tts.cancel();
+  }, [tts]);
+
+  const handleKeyDown = useCallback(
+    (e: React.KeyboardEvent<HTMLTextAreaElement>) => {
+      // Ctrl/Cmd + Enter to speak
+      if ((e.ctrlKey || e.metaKey) && e.key === "Enter") {
+        e.preventDefault();
+        handleSpeak();
+      }
+    },
+    [handleSpeak]
+  );
+
+  const statusLabel = (() => {
+    switch (tts.status) {
+      case "disconnected":
+        return "DISCONNECTED";
+      case "connecting":
+        return "CONNECTING...";
+      case "connected":
+        return "CONNECTED";
+      case "loading_model":
+        return "LOADING TTS MODEL...";
+      case "speaking":
+        return "SPEAKING";
+      case "error":
+        return "ERROR";
+      default:
+        return "IDLE";
+    }
+  })();
+
+  const statusColor = (() => {
+    switch (tts.status) {
+      case "connected":
+      case "speaking":
+        return "border-[#3f6fb3] text-[#75aafc]";
+      case "error":
+        return "border-red-400/50 text-red-400";
+      default:
+        return "border-[rgba(117,170,252,0.25)] text-[#9bc3ff]";
+    }
+  })();
+
+  const dotColor = (() => {
+    switch (tts.status) {
+      case "connected":
+      case "speaking":
+        return "bg-[#75aafc]";
+      case "error":
+        return "bg-red-400";
+      default:
+        return "bg-[#3f6fb3]";
+    }
+  })();
+
+  return (
+    <div className="relative z-10 h-screen flex flex-col overflow-hidden">
+      <Masthead showTicker={false} showNav />
+
+      <main className="flex-1 flex flex-col items-center justify-center p-4 md:p-8 gap-6 min-h-0 overflow-auto">
+        {/* Text input area */}
+        <div className="w-full max-w-2xl">
+          <textarea
+            value={text}
+            onChange={(e) => setText(e.target.value)}
+            onKeyDown={handleKeyDown}
+            placeholder="Enter text to speak..."
+            disabled={tts.isSpeaking || tts.isModelLoading}
+            className="w-full h-48 p-4 font-mono text-sm text-[#dbe7ff] bg-[#0d1b2d] border border-[#0f3c78] focus:border-[#3f6fb3] focus:outline-none placeholder-[#3f6fb3] resize-none transition-colors disabled:opacity-50"
+          />
+          <div className="mt-1 text-right font-mono text-xs text-[#3f6fb3]">
+            Ctrl+Enter to speak
+          </div>
+        </div>
+
+        {/* Controls row */}
+        <div className="w-full max-w-2xl flex items-center gap-4">
+          {/* Speak / Cancel button */}
+          {tts.isSpeaking || tts.isModelLoading ? (
+            <button
+              onClick={handleCancel}
+              className="px-6 py-2 font-mono text-sm text-red-400 bg-[#0d1b2d] border border-red-400/50 hover:border-red-400 transition-colors uppercase tracking-wide"
+            >
+              Cancel
+            </button>
+          ) : (
+            <button
+              onClick={handleSpeak}
+              disabled={!text.trim()}
+              className="px-6 py-2 font-mono text-sm text-[#dbe7ff] bg-[#0d1b2d] border border-[#0f3c78] hover:border-[#3f6fb3] transition-colors uppercase tracking-wide disabled:opacity-50 disabled:cursor-not-allowed"
+            >
+              Speak
+            </button>
+          )}
+
+          {/* Status indicator */}
+          <div
+            className={`inline-flex items-center gap-1.5 px-2 py-1 border font-mono text-xs tracking-wide uppercase ${statusColor}`}
+          >
+            <span className={`w-1.5 h-1.5 rounded-full ${dotColor}`} />
+            {statusLabel}
+          </div>
+        </div>
+
+        {/* Loading bar (indeterminate) */}
+        {tts.isModelLoading && (
+          <div className="w-full max-w-2xl">
+            <div className="w-full h-1.5 bg-[#0f1c2f] overflow-hidden">
+              <div
+                className="h-full w-1/3 bg-[#75aafc]"
+                style={{
+                  animation: "loading-slide 1.5s ease-in-out infinite",
+                }}
+              />
+            </div>
+            <div className="mt-2 font-mono text-xs text-[#9bc3ff] text-center tracking-wide uppercase">
+              Loading TTS model... This may take a moment on first use.
+            </div>
+          </div>
+        )}
+
+        {/* Speaking animation bar */}
+        {tts.isSpeaking && (
+          <div className="w-full max-w-2xl">
+            <div className="w-full h-1.5 bg-[#0f1c2f] overflow-hidden">
+              <div
+                className="h-full w-full bg-[#75aafc] animate-pulse"
+              />
+            </div>
+          </div>
+        )}
+
+        {/* Error display */}
+        {tts.error && (
+          <div className="w-full max-w-2xl font-mono text-xs text-red-400 text-center px-4 py-2 border border-red-400/50 bg-red-400/10">
+            {tts.error}
+          </div>
+        )}
+      </main>
+
+    </div>
+  );
+}