Replace TTS endpoint with Rust-native Qwen3-TTS (#41)

* chore: fix unused import warnings in qwen3-tts module

- Remove unused import 'IndexOp' in model.rs
- Remove unused import 'DType' in speech_tokenizer.rs
- Add #[allow(dead_code)] to codebook_dim field in RvqCodebook

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

* feat: add voice loading and selection for TTS cloning

Add voice reference audio loading so the TTS speak handler can perform
voice cloning using reference WAV files from the voices/ directory.

- Add voice.rs module: loads manifest.json and reference.wav for a given
  voice_id, decodes via symphonia, resamples to 24kHz for the TTS engine
- Update speak.rs: resolve voice_id from the speak request (default
  "makima"), load reference audio, pass it to engine.generate()
- Add voices/makima/README.md with instructions for obtaining reference
  audio (extraction from YouTube, recording, ffmpeg conversion)
- Graceful fallback: if reference audio is missing, TTS proceeds without
  voice cloning using the model's default voice

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

* [WIP] Heartbeat checkpoint - 2026-01-28 03:49:13 UTC

---------

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

1 files changed, 2 insertions, 1 deletions

diff --git a/makima/src/tts/qwen3/speech_tokenizer.rs b/makima/src/tts/qwen3/speech_tokenizer.rs
index 752050a..86e00f2 100644
--- a/makima/src/tts/qwen3/speech_tokenizer.rs
+++ b/makima/src/tts/qwen3/speech_tokenizer.rs
@@ -11,7 +11,7 @@
 //! The speech tokenizer is a separate model (~682MB) loaded from
 //! `Qwen/Qwen3-TTS-Tokenizer-12Hz`.
 
-use candle_core::{DType, Device, Module, Result, Tensor, D};
+use candle_core::{Device, Module, Result, Tensor, D};
 use candle_nn::{
     conv1d, embedding, linear_no_bias, Conv1d, Conv1dConfig, Embedding, Linear, VarBuilder,
 };
@@ -259,6 +259,7 @@ impl DecoderBlock {
 pub struct RvqCodebook {
     codebooks: Vec<Embedding>,
     num_codebooks: usize,
+    #[allow(dead_code)]
     codebook_dim: usize,
 }