Unverified50% confidenceSolutionExact time
When selecting components, the metrics Reimer focuses on include: the audio framework's input and output latency, STT's confidence time, the LLM's time to first sentence (a combination of time to first token and tokens per second), and TTS's time to first audio (which must be measured up to the point where the user actually hears sound).
1
Sources
50%
Confidence
Long-term
Relevance
10/29/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe industry typically uses Time to First Audio Chunk as the core metric for real-time TTS.77% similarUnverifiedAcoustic model inference is the primary source of TTS latency.77% similarUnverifiedLow latency and high recognition accuracy involve the selection of Voice Activity Detection (VAD) and Speech-to-Text (STT) engines76% similarUnverified语音智能体技术栈通常包含STT、LLM推理、TTS三个串行环节，STT约耗时200-400ms，LLM首token延迟约100-500ms，TTS生成约100-300ms75% similarUnverified语音AI系统中的中断处理需要在毫秒级别内完成停止TTS音频流、丢弃未播放内容、重置LLM上下文状态、重新进入STT监听模式等操作74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1113194API
curl https://kongchang.com/api/v1/knowledge/claims/1113194MCP
get_claim(id=1113194)