Local Voice Assistant based on Qwen3.5 4B with skills/toolcalling. No dedicated GPU. Local STT+TTS
Summary
一个基于 Qwen3.5 4B 的本地语音助手项目，支持技能与工具调用，无需独立 GPU，集成 Voxtral 本地语音识别与 Pocket TTS 语音合成。
Similar Articles
@OpenBMB: Build with VoxCPM: Whispera — Your Local AI Voice Assistant What if your AI assistant could listen, think, remember, an…
Whispera 是一个基于 VoxCPM 的 Windows 本地实时语音助手，集成了 SenseVoice ASR、llama-server 本地 LLM 推理、VoxCPM 流式 TTS 和 Mem0 长期记忆，完全离线运行。
Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice
Alibaba's Qwen team releases Qwen3-TTS-12Hz-1.7B-CustomVoice, a powerful text-to-speech model supporting 10 languages with low-latency streaming, instruction-based voice control, and robust contextual understanding.
I built a local realtime voice stack for Ollama: Parakeet STT → Qwen 2.5 7B → Qwen3-TTS
The author built a local realtime voice stack using Parakeet STT, Qwen 2.5 7B, and Qwen3-TTS, integrated with Ollama.
@yiyirats: When relying on third-party voice services, data privacy and stability are always factors to consider. Voicebox is a locally run AI voice studio; all processing is done locally, data is not uploaded to the cloud, and no account registration is required. The features are quite comprehensive: supports Qwen3-TTS, LuxTTS, Chatterbo…
Voicebox is a locally run open-source AI voice studio that supports 7 TTS engines, 23 languages, and voice cloning. All processing is done locally to protect privacy. The project has received 33.8k stars on GitHub.
@IndieDevHailey: VoiceStudio: local version of ElevenLabs, voice cloning, sound design, video dubbing, dictation, audiobooks, all included, supporting 646 languages. 16 TTS engines switchable at will, completely local, no account needed, no API, no subscription, all data on your machine. Just renamed from OmniVoice, already has 1…
VoiceStudio is a locally running AI voice tool, offering features such as voice cloning, sound design, video dubbing, etc., supporting 646 languages, with no need for network connection or subscription, and all data processed locally.