Unverified50% confidenceReleaseExact time
Google has launched Google AI Edge Foresight, a voice notes application for macOS, equipped with the Gemma series and Embedding Gemma models, with voice processed by local models during transcription.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/8/2026
First Seen
Valid until: 1/6/2027
Sources
Related Entities
Related Claims
Unverified端到端语音架构的早期探索可追溯到2014年前后Google提出的Sequence-to-Sequence模型，以及2016年百度提出的Deep Speech 267% similarUnverifiedAudioPaLM, released by Google in 2023, was the first to inject speech tokens directly into a language model's vocabulary, enabling joint modeling of text and audio in the same representation space.67% similarUnverifiedGoogle's previous speech recognition capabilities were primarily provided in the form of the Cloud Speech-to-Text API, oriented toward backend integration for enterprises and developers.66% similarUnverifiedEmbeddingGemma 2 is a multimodal embedding model built by Google on the Gemma 4 architecture, capable of encoding text, images, audio, and video into a shared 768-dimensional vector space.65% similarUnverifiedGoogle Brain团队2012年发表了DNN-HMM混合模型，代表深度神经网络语音识别系统63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/988720API
curl https://kongchang.com/api/v1/knowledge/claims/988720MCP
get_claim(id=988720)