1 files changed, 6 insertions, 38 deletions

diff --git a/makima/src/tts/mod.rs b/makima/src/tts/mod.rs
index b66f4a5..31f4204 100644
--- a/makima/src/tts/mod.rs
+++ b/makima/src/tts/mod.rs
@@ -1,19 +1,15 @@
 //! TTS engine abstraction and implementations.
 //!
-//! Provides a trait-based TTS engine interface with two backends:
-//! - **Chatterbox**: ONNX-based TTS (legacy)
-//! - **Qwen3**: Pure Rust candle-based Qwen3-TTS-12Hz-0.6B
+//! Provides a trait-based TTS engine interface using Chatterbox ONNX-based TTS.
 
 use std::path::Path;
 use std::sync::atomic::AtomicBool;
 use std::sync::Arc;
 
 pub mod chatterbox;
-pub mod qwen3;
 
 // Re-export primary types
 pub use chatterbox::ChatterboxTTS;
-pub use qwen3::Qwen3Tts;
 
 /// Audio output sample rate (both engines output 24kHz).
 pub const SAMPLE_RATE: u32 = 24_000;
@@ -51,8 +47,6 @@ pub enum TtsError {
     Audio(crate::audio::AudioError),
     Io(std::io::Error),
     VoiceRequired,
-    Config(String),
-    Candle(String),
 }
 
 impl std::fmt::Display for TtsError {
@@ -66,8 +60,6 @@ impl std::fmt::Display for TtsError {
             TtsError::VoiceRequired => {
                 write!(f, "voice reference audio is required")
             }
-            TtsError::Config(msg) => write!(f, "config error: {msg}"),
-            TtsError::Candle(msg) => write!(f, "candle error: {msg}"),
         }
     }
 }
@@ -92,22 +84,7 @@ impl From<ort::Error> for TtsError {
     }
 }
 
-impl From<candle_core::Error> for TtsError {
-    fn from(value: candle_core::Error) -> Self {
-        TtsError::Candle(value.to_string())
-    }
-}
-
-/// Which TTS backend to use.
-#[derive(Debug, Clone, Copy, PartialEq, Eq)]
-pub enum TtsBackend {
-    /// ONNX-based Chatterbox TTS (legacy).
-    Chatterbox,
-    /// Candle-based Qwen3-TTS (preferred).
-    Qwen3,
-}
-
-/// TTS engine trait — implemented by both Chatterbox and Qwen3.
+/// TTS engine trait for text-to-speech synthesis.
 #[async_trait::async_trait]
 pub trait TtsEngine: Send + Sync {
     /// Generate complete audio from text with a voice reference.
@@ -137,19 +114,10 @@ pub trait TtsEngine: Send + Sync {
 pub struct TtsEngineFactory;
 
 impl TtsEngineFactory {
-    /// Create a TTS engine of the specified backend type.
-    pub fn create(backend: TtsBackend, model_dir: Option<&str>) -> Result<Box<dyn TtsEngine>, TtsError> {
-        match backend {
-            TtsBackend::Chatterbox => {
-                let engine = ChatterboxTTS::from_pretrained(model_dir)?;
-                Ok(Box::new(engine))
-            }
-            TtsBackend::Qwen3 => {
-                let device = candle_core::Device::Cpu; // Default to CPU; GPU selection happens at higher level
-                let engine = Qwen3Tts::from_pretrained(model_dir, &device)?;
-                Ok(Box::new(engine))
-            }
-        }
+    /// Create a Chatterbox TTS engine.
+    pub fn create(model_dir: Option<&str>) -> Result<Box<dyn TtsEngine>, TtsError> {
+        let engine = ChatterboxTTS::from_pretrained(model_dir)?;
+        Ok(Box::new(engine))
     }
 }