elbruno/Qwen3-TTS-12Hz-0.6B-Base-ONNX

Qwen3-TTS 12Hz 0.6B Base — ONNX (Voice Cloning)

ONNX export of Qwen/Qwen3-TTS-12Hz-0.6B-Base for local inference with C# / ONNX Runtime. Includes ECAPA-TDNN speaker encoder for 3-second voice cloning.

Files

File	Description	Size
speaker_encoder.onnx + .data	ECAPA-TDNN speaker encoder	~34 MB
talker_prefill.onnx + .data	Talker LM prefill (28 layers)	~1.7 GB
talker_decode.onnx + .data	Talker LM single-step decode	~1.7 GB
code_predictor.onnx	Code Predictor (5 layers, 15 groups)	~440 MB
vocoder.onnx	Vocoder decoder (24kHz output)	~2.7 MB
embeddings/	Text/codec embeddings as .npy + config	~1.4 GB
tokenizer/	BPE tokenizer (vocab.json, merges.txt)	~4 MB

Usage with C#

dotnet add package ElBruno.QwenTTS.VoiceCloning

using ElBruno.QwenTTS.VoiceCloning.Pipeline;

var cloner = await VoiceClonePipeline.CreateAsync();
await cloner.SynthesizeAsync("Hello world!", "reference.wav", "output.wav", "english");

Architecture

• Speaker Encoder: ECAPA-TDNN, 128 mel bins input, 1024-dim output
• Talker: 28 transformer layers, 16 attn heads, 8 KV heads, hidden=1024
• Code Predictor: 5 layers, generates codebook groups 1-15
• Vocoder: RVQ dequantize → transformer → BigVGAN decoder, 12Hz → 24kHz

License

Apache-2.0 (same as base model)