Unverified50% confidenceFactExact time
Voice/performance models such as Minimax H3 support embedding emotion tags within text scripts to control a character's tone and mood.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/12/2026
First Seen
Valid until: 12/11/2026
Sources
Related Entities
Related Claims
UnverifiedGoogle released a text-to-speech (TTS) model capable of controllable emotion.70% similarUnverified情感语音合成系统通过对音调、语速、能量等声学特征向量的精细控制来实现情绪表达68% similarUnverified情感建模依赖对语调（Prosody）的精细控制，包括音高、语速、音量包络等多维度参数的联合建模67% similarUnverifiedCosyVoice v3 supports system-preset voice profiles but only allows users to choose from predefined emotion tags such as joy, sadness, and frustration66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/910745API
curl https://kongchang.com/api/v1/knowledge/claims/910745MCP
get_claim(id=910745)