Unverified50% confidenceFactExact time
Moshi and its derivative model PersonaPlex are speech-to-speech LLMs capable of listening and speaking simultaneously, enabling concurrent generation.
1
Sources
50%
Confidence
Long-term
Relevance
9/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe MosiAI team open-sourced MOSS-Transcribe-Diarize-0.9B, an end-to-end multi-speaker speech recognition model with only 0.9B parameters.65% similarUnverifiedFor voice agents, multimodal large models must support not only voice, images, text, and video as inputs, but also voice as output.62% similarUnverifiedModelStack provides multiple preset voice tones, and users can switch between male and female voices during text-to-speech.62% similarUnverifiedMeta的Voicebox和Google的AudioPaLM是尝试将感知-理解-生成链路压缩进单一Transformer架构的语音系统62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/921844API
curl https://kongchang.com/api/v1/knowledge/claims/921844MCP
get_claim(id=921844)