Unverified50% confidenceReleaseExact time
Cognition launched Devin Voice, an interaction mode that allows users to delegate programming tasks directly by voice.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/5/2026
First Seen
Valid until: 1/3/2027
Sources
Related Entities
Related Claims
UnverifiedA voice-native application is one that, starting from first principles of interaction design, constructs application logic with voice as the primary or even sole input/output channel, rather than layering voice control on top of an existing GUI application.78% similarUnverifiedDevin Voice adopts an architecture that decouples the conversational experience from execution capability, with the conversational model ensuring low latency and naturalness, and the coding model ensuring code quality.77% similarUnverifiedThe goal of the VOICE trial is to directly convert a patient's communicative intent into outputtable speech or text by reading neural signals related to language from the brain.75% similarVerifiedFor voice agents, multimodal large models must support not only voice, images, text, and video as inputs, but also voice as output.73% similarUnverifiedThe new generation voice AI model takes audio directly as modal input, skipping the transcription step to achieve more natural emotional perception and intonation variation.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/976945API
curl https://kongchang.com/api/v1/knowledge/claims/976945MCP
get_claim(id=976945)