by forkjoin-ai
Open source · 587 downloads · 0 likes
The Qwen3 TTS 12Hz 1.7B Voicedesign model is an optimized version of the Qwen3-TTS-12Hz-1.7B-VoiceDesign speech synthesis model designed for edge deployment. It generates natural-sounding speech from text with reduced latency thanks to its 12 Hz sampling rate, making it ideal for real-time applications. Key use cases include voiceovers, voice assistants, and accessibility features, particularly on mobile or embedded devices with limited resources. This model stands out for its lightweight design (1.7 billion parameters) and edge compatibility, providing a high-performance alternative to cloud-based solutions while maintaining high audio quality.
Forkjoin.ai conversion of Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign to GGUF format for edge deployment.
./llama-cli -m qwen3-tts-12hz-1.7b-voicedesign-gguf.gguf -p "Your prompt here" -n 256
Create a Modelfile:
FROM ./qwen3-tts-12hz-1.7b-voicedesign-gguf.gguf
ollama create qwen3-tts-12hz-1.7b-voicedesign-gguf -f Modelfile
ollama run qwen3-tts-12hz-1.7b-voicedesign-gguf
Forkjoin.ai runs AI models at the edge -- in-browser, on-device, zero cloud cost. These converted models power real-time inference, speech recognition, and natural language capabilities.
All conversions are optimized for edge deployment within browser and mobile memory constraints.
Apache 2.0 (follows upstream model license)