Use chatterbox TTS

1 files changed, 2 insertions, 3 deletions

diff --git a/makima/src/server/handlers/speak.rs b/makima/src/server/handlers/speak.rs
index 3ed2620..b235c65 100644
--- a/makima/src/server/handlers/speak.rs
+++ b/makima/src/server/handlers/speak.rs
@@ -1,19 +1,18 @@
 //! WebSocket handler for TTS streaming (direct in-process inference).
 //!
 //! This module implements the `/api/v1/speak` endpoint which performs
-//! text-to-speech synthesis directly using the candle-based TTS engine.
+//! text-to-speech synthesis directly using the Chatterbox ONNX TTS engine.
 //! No external Python service or proxy — the model runs in-process.
 //!
 //! ## Architecture
 //!
 //! The speak handler will:
 //! 1. Accept a WebSocket connection from the client
-//! 2. Lazily load the TTS model (candle) on first request
+//! 2. Lazily load the TTS model (Chatterbox ONNX) on first request
 //! 3. Parse JSON control messages (start, speak, stop, cancel)
 //! 4. Run inference directly and stream audio chunks back
 //!
 //! See `makima/src/tts/` for the TTS engine implementation.
-//! See `docs/specs/qwen3-tts-spec.md` for the full protocol specification.
 
 use std::sync::atomic::{AtomicBool, Ordering};
 use std::sync::Arc;