Unverified90% confidenceFactTime unknown
Dia能根据输入文本自动生成两人对话音频，可模拟咳嗽声、笑声等非语言细节
1
Sources
90%
Confidence
Long-term
Relevance
6/1/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe workflow offers two voice generation modes: a lip-sync mode (which freezes the user's voice into the audio latent space) and a model-generated speech mode.72% similarVerifiedEnd-to-end voice models take audio directly as input and output, performing understanding and generation at the audio token level while preserving acoustic features such as intonation, speaking rate, sighs, and laughter.70% similarUnverifiedThe new model can perceive paralinguistic information such as the speaker's volume and tone, and proactively raise its volume or switch states.69% similarUnverifiedUsing voice input instead of typing allows true intent to be conveyed more naturally and quickly.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/16637API
curl https://kongchang.com/api/v1/knowledge/claims/16637MCP
get_claim(id=16637)