Unverified50% confidenceFactExact time
This local voice assistant system is fully self-hosted, with voice detection and recognition running on the CPU, the LLM (Gemma 4 E4B, QAT q4_0 quantization, based on llama.cpp) responsible for generating answers, and the TTS (Qwen3-TTS 1.7B) synthesizing speech sentence by sentence.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/16/2026
First Seen
Valid until: 1/14/2027
Sources
Related Entities
Related Claims
Unverified语音智能体典型系统架构由VAD、STT、意图识别/LLM推理、TTS等环节串联构成，工业界通常将端到端目标设定在首字节音频输出500ms以内75% similarUnverified本地语音识别模型经过INT8/INT4量化和ONNX等推理框架优化后，可在无专用GPU下以接近实时速度完成转写，支持近百种语言74% similarVerifiedTraditional voice dialogue systems consist of three independent modules connected in series—ASR (Automatic Speech Recognition), LLM (Large Language Model), and TTS (Text-to-Speech)—each trained separately and executed sequentially.72% similarVerifiedFor an AI voice assistant to achieve full duplex, four modules must run simultaneously—automatic speech recognition (ASR), natural language understanding (NLU), language model inference, and text-to-speech (TTS)—while also handling voice activity detection (VAD) in real time.72% similarUnverified语音编码器 + LLM 解码器的组合是 2023 年以来语音大模型的主流范式，Qwen-Audio、Gemini Audio、Phi-4-audio 等均采用类似设计72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1043818API
curl https://kongchang.com/api/v1/knowledge/claims/1043818MCP
get_claim(id=1043818)