diff --git a/qwen_tts_service.py b/qwen_tts_service.py index 8b03388..1eb187a 100644 --- a/qwen_tts_service.py +++ b/qwen_tts_service.py @@ -1,7 +1,7 @@ """qwen_tts_service.py Qwen3-TTS Service for Pipecat using MLX on Apple Silicon. -Provides local speech synthesis using Alibaba Qwen3-TTS 1.7B +Provides local speech synthesis using Alibaba Qwen3-TTS 0.6B with zero-shot voice cloning capabilities via mlx-audio. """ diff --git a/test_qwen_tts_service.py b/test_qwen_tts_service.py index 37d88c8..868cb21 100644 --- a/test_qwen_tts_service.py +++ b/test_qwen_tts_service.py @@ -1,7 +1,7 @@ """test_qwen_tts_service.py Unit test for QwenTTSService. -Verifies loading MLX Qwen3-TTS 1.7B model and generating audio frames. +Verifies loading MLX Qwen3-TTS 0.6B model and generating audio frames. """ import asyncio @@ -10,11 +10,11 @@ from pipecat.frames.frames import TTSAudioRawFrame async def main(): - print("Testing QwenTTSService with MLX Qwen3-TTS 1.7B...") + print("Testing QwenTTSService with MLX Qwen3-TTS 0.6B...") service = QwenTTSService(voice="qwen_jv") frames = [] - async for frame in service.run_tts("Hello! This is a test of Qwen 1.7B TTS service.", context_id="test_ctx"): + async for frame in service.run_tts("Hello! This is a test of Qwen 0.6B TTS service.", context_id="test_ctx"): frames.append(frame) assert len(frames) > 0, "No frames generated by QwenTTSService" diff --git a/voice_manager.py b/voice_manager.py index 5a5d985..d80b051 100644 --- a/voice_manager.py +++ b/voice_manager.py @@ -31,7 +31,7 @@ KOKORO_VOICES = { "bm_stuart": "British Male - Stuart Bell", "custom_pocket": "Pocket Voice Clone (Default)", "jv_pocket": "JV Voice Profile (Kyutai Pocket TTS)", - "qwen_jv": "JV Voice Profile (MLX Qwen 1.7B TTS)", + "qwen_jv": "JV Voice Profile (MLX Qwen 0.6B TTS)", } MACOS_VOICES = { @@ -74,6 +74,9 @@ VOICE_ALIASES = { "jv voice": "jv_pocket", "qwen": "qwen_jv", "qwen_jv": "qwen_jv", + "qwen 0.6b": "qwen_jv", + "qwen_0.6b": "qwen_jv", + "qwen0.6b": "qwen_jv", "qwen 1.7b": "qwen_jv", "qwen3": "qwen_jv", }