From 9b53f6c6b01da85ef73bd5960b32ec319df0b947 Mon Sep 17 00:00:00 2001 From: soryu Date: Wed, 28 Jan 2026 03:50:45 +0000 Subject: 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 * 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 * [WIP] Heartbeat checkpoint - 2026-01-28 03:49:13 UTC --------- Co-authored-by: Claude Opus 4.5 --- makima/src/tts/mod.rs | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'makima/src/tts/mod.rs') diff --git a/makima/src/tts/mod.rs b/makima/src/tts/mod.rs index 2cd0412..b66f4a5 100644 --- a/makima/src/tts/mod.rs +++ b/makima/src/tts/mod.rs @@ -5,6 +5,8 @@ //! - **Qwen3**: Pure Rust candle-based Qwen3-TTS-12Hz-0.6B use std::path::Path; +use std::sync::atomic::AtomicBool; +use std::sync::Arc; pub mod chatterbox; pub mod qwen3; @@ -109,11 +111,17 @@ pub enum TtsBackend { #[async_trait::async_trait] pub trait TtsEngine: Send + Sync { /// Generate complete audio from text with a voice reference. + /// + /// The optional `cancel_flag` can be set to `true` by another thread/task + /// to request early termination of the generation loop. Engines that + /// support cancellation will check this flag periodically and return + /// whatever audio has been produced so far. async fn generate( &self, text: &str, reference_audio: Option<&[f32]>, reference_sample_rate: Option, + cancel_flag: Option>, ) -> Result, TtsError>; /// Check if the engine is loaded and ready. -- cgit v1.2.3