Qwen3-TTS-12Hz-1.7B-VoiceDesign — GGUF
GGUF conversion of Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign for use with qwen3-tts.cpp.
VoiceDesign generates speech from a natural-language voice description (instruct), no reference audio required. Great for designing reusable voice personas: design once → save the generated wav → extract a speaker embedding from it → use that embedding with the Base model for fast inference.
Files
| File | Type | Size | Notes |
|---|---|---|---|
qwen3-tts-1.7b-voicedesign-f16.gguf | F16 | 3.84 GB | Recommended. Same precision as upstream safetensors. |
You also need the tokenizer/codec gguf — convert it from Qwen/Qwen3-TTS-Tokenizer-12Hz using the same convert_tts_to_gguf.py script, or grab one from the existing cgisky/qwen3-tts-custom-gguf repo (look for qwen3-tts-tokenizer-f16.gguf).
Quickstart with qwen3-tts.cpp CLI
./qwen3-tts-cli \
--model models \
--model-name qwen3-tts-1.7b-voicedesign-f16.gguf \
--text "Hello, I'm a custom-designed voice." \
--instruction "warm middle-aged male voice, slow pace, friendly tone" \
--output designed_voice.wav
Persona-design flow
- Generate a reference clip with VoiceDesign:
./qwen3-tts-cli -m models --model-name qwen3-tts-1.7b-voicedesign-f16.gguf \ -t "The quick brown fox jumps over the lazy dog." \ --instruction "deep authoritative male voice" \ -o persona_reference.wav - Extract a reusable speaker embedding from that clip (using the Base model):
./qwen3-tts-cli -m models --model-name qwen3-tts-1.7b-base-f16.gguf \ -t "test" -r persona_reference.wav \ --dump-speaker-embedding persona.json - Use the saved embedding for fast, consistent inference:
./qwen3-tts-cli -m models --model-name qwen3-tts-1.7b-base-f16.gguf \ -t "Anything you want to say." \ --speaker-embedding persona.json \ -o output.wav
Conversion details
Converted with scripts/convert_tts_to_gguf.py from the qwen3-tts.cpp repo. No quantization (F16, identical numeric precision to the original safetensors).
python scripts/convert_tts_to_gguf.py \
--input Qwen3-TTS-12Hz-1.7B-VoiceDesign \
--output qwen3-tts-1.7b-voicedesign-f16.gguf \
--type f16
Hardware tested
- NVIDIA RTX 3090 (compute capability 8.6) — works
- CUDA 12.6, driver-side ggml-cuda (with
GGML_CUDA_USE_GRAPHS)
License
Apache 2.0, inheriting from upstream Qwen3-TTS-VoiceDesign.
Citation
@misc{qwen3tts,
title = {Qwen3-TTS},
author = {Qwen Team},
year = {2026},
url = {https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign}
}